diff --git a/articles/01_data_preparationhelpers.html b/articles/01_data_preparationhelpers.html index 75c59670..e63adda3 100644 --- a/articles/01_data_preparationhelpers.html +++ b/articles/01_data_preparationhelpers.html @@ -96,7 +96,7 @@

Martin Jung

-

2024-01-25

+

2024-02-06

Source: vignettes/articles/01_data_preparationhelpers.Rmd
01_data_preparationhelpers.Rmd
@@ -159,7 +159,7 @@

Adding pseudo-absenc ## Lets load some testing data from the package # Background layer -background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM", mustWork = TRUE)) +background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM", mustWork = TRUE)) # Load virtual species points virtual_species <- sf::st_read(system.file("extdata/input_data.gpkg",package = "ibis.iSDM", mustWork = TRUE), "points",quiet = TRUE) # Add a range @@ -199,7 +199,7 @@

Adding pseudo-absenc # --- # # Another option sampling inside the range, but biased by a bias layer -bias <- terra::rast(system.file("extdata/predictors/hmi_mean_50km.tif", +bias <- terra::rast(system.file("extdata/predictors/hmi_mean_50km.tif", package = "ibis.iSDM", mustWork = TRUE)) abs <- pseudoabs_settings(background = background, @@ -264,7 +264,7 @@

Thinning observations # Another way: Use environmental thinning to retain enough points # across the niche defined by a set of covariates -covariates <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE)) +covariates <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE)) point2 <- thin_observations(data = virtual_species, background = background, @@ -274,7 +274,7 @@

Thinning observations ) #> (environmental) thinning completed! #> Original number of records: 208 -#> Number of retained records: 33 +#> Number of retained records: 28 plot(point2['Observed'], main = "Environmentally stratified data")

@@ -298,7 +298,7 @@

Preparing and altering predictor terra package).

 # Load some test covariates
-predictors <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE))
+predictors <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE))

Transforming predictors

@@ -317,8 +317,8 @@

Transforming predictorsnew2 <- predictor_transform(layer, option = "scale") new <- c(layer, new1, new2) -names(new) <- c("original", "normalized", "scaled") -terra::plot( new )

+names(new) <- c("original", "normalized", "scaled") +terra::plot( new ) 

 
@@ -330,8 +330,8 @@ 
Transforming predictors                            windsor_props = c(0,.9))
 
 new <- c(layer, new3)
-names(new) <- c("original", "windsorized")
-terra::plot( new )
+names(new) <- c("original", "windsorized") +terra::plot( new )

Other options for transformation are also available and are listed in the methods file.

@@ -361,8 +361,8 @@

Derivates of predictorsnew1 <- predictor_derivate(layer, option = "quadratic") new <- c(layer, new1) -names(new) <- c("original", "quadratic") -terra::plot( new ) +names(new) <- c("original", "quadratic") +terra::plot( new ) 

 
@@ -371,14 +371,14 @@ 
Derivates of predictors                           # The number is controlled by the number of knots
                             nknots = 4 
                            )
-terra::plot( new2 )
+terra::plot( new2 ) 

 
 # What does this do precisely?
 # Lets check
-df <- data.frame( ndvi = terra::values(layer),
-                  terra::values(new2))
+df <- data.frame( ndvi = terra::values(layer),
+                  terra::values(new2))
 
 plot(df$ndvi_mean_50km, df[,2], ylab = "First hinge of ndvi", xlab = "NDVI")

@@ -417,23 +417,23 @@

Homogenize missing data among preparation.

 # Make a subset of all predictors to show the concept
-layers <- subset(predictors,  c("aspect_mean_50km",
+layers <- subset(predictors,  c("aspect_mean_50km",
                                         "CLC3_312_mean_50km",
                                         "elevation_mean_50km"))
 
 # All these layers have identical data coverage.
 # Now add missing data in one of the layers for testing
-layers$CLC3_312_mean_50km[sample(1:ncell(layers), 1000)] <- NA 
+layers$CLC3_312_mean_50km[sample(1:ncell(layers), 1000)] <- NA 
 
 # Harmonize the predictors
 new <- predictor_homogenize_na(env = layers)
 
 # Now all the predictors have identical coverage of NA values
-terra::plot(new)
+terra::plot(new) 

 # Or assess like this
-plot(!terra::noNA(new$aspect_mean_50km), main = "Missing observations")
+plot(!terra::noNA(new$aspect_mean_50km), main = "Missing observations")

diff --git a/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-1.png b/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-1.png index b65089f8..b67da092 100644 Binary files a/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-1.png and b/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-1.png differ diff --git a/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-2.png b/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-2.png index 3f93f19f..49d1143c 100644 Binary files a/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-2.png and b/articles/01_data_preparationhelpers_files/figure-html/Define and add pseudo-absence data-2.png differ diff --git a/articles/01_data_preparationhelpers_files/figure-html/Thinning-2.png b/articles/01_data_preparationhelpers_files/figure-html/Thinning-2.png index 6fb7ad8e..8f5f60ad 100644 Binary files a/articles/01_data_preparationhelpers_files/figure-html/Thinning-2.png and b/articles/01_data_preparationhelpers_files/figure-html/Thinning-2.png differ diff --git a/articles/01_data_preparationhelpers_files/figure-html/Thinning-3.png b/articles/01_data_preparationhelpers_files/figure-html/Thinning-3.png index 668332e6..8b19bce3 100644 Binary files a/articles/01_data_preparationhelpers_files/figure-html/Thinning-3.png and b/articles/01_data_preparationhelpers_files/figure-html/Thinning-3.png differ diff --git a/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-1.png b/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-1.png index baa85133..48f01bb9 100644 Binary files a/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-1.png and b/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-1.png differ diff --git a/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-2.png b/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-2.png index 84ac9131..6e837302 100644 Binary files a/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-2.png and b/articles/01_data_preparationhelpers_files/figure-html/unnamed-chunk-1-2.png differ diff --git a/articles/02_train_simple_model.html b/articles/02_train_simple_model.html index 81d168b5..6eb3e962 100644 --- a/articles/02_train_simple_model.html +++ b/articles/02_train_simple_model.html @@ -96,7 +96,7 @@

Martin Jung

-

2024-01-25

+

2024-02-06

Source: vignettes/articles/02_train_simple_model.Rmd
02_train_simple_model.Rmd
@@ -152,7 +152,7 @@

Load package and make a basic model predictors available for modelling. So first lets load the data:

 # Background layer
-background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM", mustWork = TRUE))
+background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM", mustWork = TRUE))
 # Load virtual species points
 virtual_species <- sf::st_read(system.file("extdata/input_data.gpkg",package = "ibis.iSDM", mustWork = TRUE), "points") 
 #> Reading layer `points' from data source 
@@ -164,9 +164,9 @@ 
Load package and make a basic model
 #> Bounding box:  xmin: 4.109162 ymin: 48.7885 xmax: 24.47594 ymax: 64.69323
 #> Geodetic CRS:  WGS 84
 # Predictors
-predictors <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE))
+predictors <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE))
 # Make use only of a few of them
-predictors <- subset(predictors, c("bio01_mean_50km","bio03_mean_50km","bio19_mean_50km",
+predictors <- subset(predictors, c("bio01_mean_50km","bio03_mean_50km","bio19_mean_50km",
                                             "CLC3_112_mean_50km","CLC3_132_mean_50km",
                                             "CLC3_211_mean_50km","CLC3_312_mean_50km",
                                             "elevation_mean_50km"))
@@ -265,7 +265,7 @@

Load package and make a basic model 
 
 # Other options to explore
-names(mod)
+names(mod)
 #>  [1] "summary"                     "show_biodiversity_length"   
 #>  [3] "show_biodiversity_equations" "show_background_info"       
 #>  [5] "show"                        "set_priors"                 
@@ -417,51 +417,51 @@ 
Validation of model predictionsfit$rm_threshold()
 validate(fit, method = "cont")
 #>                                modelid                 name     method
-#> 1 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous
-#> 2 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous
-#> 3 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous
-#> 4 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous
-#> 5 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous
-#> 6 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous
-#>       metric        value
-#> 1          n 175.00000000
-#> 2       rmse   0.87856015
-#> 3        mae   0.67314153
-#> 4    logloss   1.77608616
-#> 5   normgini  -0.07569721
-#> 6 cont.boyce   0.26208641
+#> 1 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous
+#> 2 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous
+#> 3 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous
+#> 4 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous
+#> 5 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous
+#> 6 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous
+#>       metric       value
+#> 1          n 175.0000000
+#> 2       rmse   0.8779555
+#> 3        mae   0.6723207
+#> 4    logloss   1.7755858
+#> 5   normgini  -0.0749004
+#> 6 cont.boyce   0.2521260
 
 # If the prediction is first thresholded, we can calculate discrete validation estimates (binary being default)
 fit <- threshold(fit, method = "percentile", value = 0.5, format = "binary")
 validate(fit, method = "disc")
 #>                                 modelid                 name   method
-#> 1  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 2  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 3  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 4  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 5  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 6  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 7  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 8  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 9  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 10 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 11 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 12 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
-#> 13 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete
+#> 1  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 2  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 3  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 4  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 5  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 6  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 7  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 8  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 9  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 10 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 11 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 12 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
+#> 13 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete
 #>                 metric       value
-#> 1                    n 506.0000000
-#> 2                  auc   0.6804316
-#> 3     overall.accuracy   0.7351779
-#> 4  true.presence.ratio   0.3963964
-#> 5            precision   0.6518519
+#> 1                    n 513.0000000
+#> 2                  auc   0.6878191
+#> 3     overall.accuracy   0.7465887
+#> 4  true.presence.ratio   0.4036697
+#> 5            precision   0.6717557
 #> 6          sensitivity   0.5028571
-#> 7          specificity   0.8580060
-#> 8                  tss   0.3608632
-#> 9                   f1   0.5677419
-#> 10             logloss   6.2052837
-#> 11   expected.accuracy   0.5718961
-#> 12               kappa   0.3814068
-#> 13         brier.score   0.2648221
+#> 7 specificity 0.8727811 +#> 8 tss 0.3756382 +#> 9 f1 0.5751634 +#> 10 logloss 6.1128139 +#> 11 expected.accuracy 0.5777314 +#> 12 kappa 0.3998812 +#> 13 brier.score 0.2534113

Validating integrated SDMs, particular those fitted with multiple likelihoods is challenging and something that has not yet fully been explored in the scientific literature. For example strong priors can diff --git a/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-1.png b/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-1.png index 6b8c8c38..d7c6c089 100644 Binary files a/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-1.png and b/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-1.png differ diff --git a/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-2.png b/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-2.png index 2e2cd42e..9c310d38 100644 Binary files a/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-2.png and b/articles/02_train_simple_model_files/figure-html/Example for model-based thresholding-2.png differ diff --git a/articles/02_train_simple_model_files/figure-html/Plot the model output-1.png b/articles/02_train_simple_model_files/figure-html/Plot the model output-1.png index d5821780..36eb0dbd 100644 Binary files a/articles/02_train_simple_model_files/figure-html/Plot the model output-1.png and b/articles/02_train_simple_model_files/figure-html/Plot the model output-1.png differ diff --git a/articles/02_train_simple_model_files/figure-html/Prediction limits-1.png b/articles/02_train_simple_model_files/figure-html/Prediction limits-1.png index ff5e97da..51878afe 100644 Binary files a/articles/02_train_simple_model_files/figure-html/Prediction limits-1.png and b/articles/02_train_simple_model_files/figure-html/Prediction limits-1.png differ diff --git a/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-2.png b/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-2.png index 46ef9e91..3623130e 100644 Binary files a/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-2.png and b/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-2.png differ diff --git a/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-3.png b/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-3.png index df7a5a5e..e554aa02 100644 Binary files a/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-3.png and b/articles/02_train_simple_model_files/figure-html/Train models with spatial constrains-3.png differ diff --git a/articles/02_train_simple_model_files/figure-html/partial effect-1.png b/articles/02_train_simple_model_files/figure-html/partial effect-1.png index 5dad6c5f..2b354a0e 100644 Binary files a/articles/02_train_simple_model_files/figure-html/partial effect-1.png and b/articles/02_train_simple_model_files/figure-html/partial effect-1.png differ diff --git a/articles/02_train_simple_model_files/figure-html/partial effect-2.png b/articles/02_train_simple_model_files/figure-html/partial effect-2.png index 5cb62201..48c197bb 100644 Binary files a/articles/02_train_simple_model_files/figure-html/partial effect-2.png and b/articles/02_train_simple_model_files/figure-html/partial effect-2.png differ diff --git a/articles/03_integrate_data.html b/articles/03_integrate_data.html index eed1cbd6..340bac4e 100644 --- a/articles/03_integrate_data.html +++ b/articles/03_integrate_data.html @@ -96,7 +96,7 @@

Martin Jung

-

2024-01-25

+

2024-02-06

Source: vignettes/articles/03_integrate_data.Rmd
03_integrate_data.Rmd
@@ -152,7 +152,7 @@

Load relevant packages and test we are going to make use of several datasets.

 # Background layer
-background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM", mustWork = TRUE))
+background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM", mustWork = TRUE))
 # Load virtual species points
 virtual_species <- sf::st_read(system.file("extdata/input_data.gpkg",package = "ibis.iSDM", mustWork = TRUE), "points", quiet = TRUE) 
 virtual_range <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'range', quiet = TRUE)
@@ -165,9 +165,9 @@ 
Load relevant packages and test
                                        settings = ass)
 
 # Predictors
-predictors <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE))
+predictors <- terra::rast(list.files(system.file("extdata/predictors/", package = "ibis.iSDM", mustWork = TRUE), "*.tif",full.names = TRUE))
 # Make use only of a few of them
-predictors <- subset(predictors, c("bio01_mean_50km","bio03_mean_50km","bio19_mean_50km",
+predictors <- subset(predictors, c("bio01_mean_50km","bio03_mean_50km","bio19_mean_50km",
                                             "CLC3_112_mean_50km","CLC3_132_mean_50km",
                                             "CLC3_211_mean_50km","CLC3_312_mean_50km",
                                             "elevation_mean_50km"))
@@ -328,7 +328,7 @@

Integration with priorspp <- priors(p) # The variables and values in this object can be queried as well pp$varnames() -#> 90173c31-3b9f-4fba-848e-219430b46621 +#> f9eade5e-69a1-40b0-a738-f90a1c441153 #> "CLC3_211_mean_50km" # Priors can then be added via @@ -536,17 +536,17 @@

Joint likelihood estimation#> # A tibble: 11 × 8 #> variable mean sd q05 q50 q95 mode kld #> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> -#> 1 Intercept -0.325 25.8 -4.28e+1 -0.325 42.1 -0.325 0 -#> 2 Intercept_species.._po… -0.325 25.8 -4.28e+1 -0.325 42.1 -0.325 0 -#> 3 Intercept_species.._po… -0.325 25.8 -4.28e+1 -0.325 42.1 -0.325 0 -#> 4 bio01_mean_50km -0.101 0.133 -3.20e-1 -0.101 0.119 -0.101 0 -#> 5 bio03_mean_50km -0.436 0.120 -6.34e-1 -0.436 -0.239 -0.436 0 -#> 6 bio19_mean_50km 0.475 0.0865 3.33e-1 0.475 0.617 0.475 0 -#> 7 CLC3_112_mean_50km 0.373 0.0488 2.92e-1 0.373 0.453 0.373 0 -#> 8 CLC3_132_mean_50km 0.0726 0.0456 -2.35e-3 0.0726 0.148 0.0726 0 -#> 9 CLC3_211_mean_50km 0.911 0.0784 7.82e-1 0.911 1.04 0.911 0 -#> 10 CLC3_312_mean_50km 0.991 0.0662 8.82e-1 0.991 1.10 0.991 0 -#> 11 elevation_mean_50km 0.0122 0.0863 -1.30e-1 0.0122 0.154 0.0122 0 +#> 1 Intercept -0.324 25.8 -42.8 -0.324 42.1 -0.324 0 +#> 2 Intercept_species.._po… -0.324 25.8 -42.8 -0.324 42.1 -0.324 0 +#> 3 Intercept_species.._po… -0.324 25.8 -42.8 -0.324 42.1 -0.324 0 +#> 4 bio01_mean_50km -0.0787 0.132 -0.296 -0.0787 0.138 -0.0787 0 +#> 5 bio03_mean_50km -0.481 0.121 -0.679 -0.481 -0.283 -0.481 0 +#> 6 bio19_mean_50km 0.458 0.0872 0.315 0.458 0.602 0.458 0 +#> 7 CLC3_112_mean_50km 0.390 0.0497 0.308 0.390 0.471 0.390 0 +#> 8 CLC3_132_mean_50km 0.0951 0.0483 0.0157 0.0951 0.174 0.0951 0 +#> 9 CLC3_211_mean_50km 0.887 0.0779 0.759 0.887 1.02 0.887 0 +#> 10 CLC3_312_mean_50km 0.971 0.0662 0.862 0.971 1.08 0.971 0 +#> 11 elevation_mean_50km 0.0250 0.0852 -0.115 0.0250 0.165 0.0250 0

Nearest Neighbour resampling (near) is recommended for discrete and bilinear resampling recommended for continuous data. See also help from -terra::resample for other options.

+terra::resample for other options.

diff --git a/reference/distribution.html b/reference/distribution.html index 4a4e59c4..69114d57 100644 --- a/reference/distribution.html +++ b/reference/distribution.html @@ -216,10 +216,10 @@

Details

  • object$get_biodiversity_types() Lists the type of each specified biodiversity dataset with given id.

    • -

  • object$get_extent() Outputs the terra::ext of the modelling region.

    • -

  • object$show_background_info() Returns a list with the terra::ext -and the terra::crs.

    • -

  • object$get_extent_dimensions() Outputs the terra::ext dimension by +

  • object$get_extent() Outputs the terra::ext of the modelling region.

    • +

  • object$show_background_info() Returns a list with the terra::ext +and the terra::crs.

    • +

  • object$get_extent_dimensions() Outputs the terra::ext dimension by calling the "extent_dimensions()" function.

  • object$get_predictor_names() Returns a character vector with the names of all added predictors.

    • @@ -245,11 +245,10 @@

    See also

    Examples

    # Load background raster
-background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM"))
+background <- terra::rast(system.file("extdata/europegrid_50km.tif",package = "ibis.iSDM"))
 # Define model
 x <- distribution(background)
-#> [Setup] 2024-01-25 21:59:59.645498 | Provide a background with a valid projection!
-#> [Setup] 2024-01-25 21:59:59.656606 | Creating distribution object...
+#> [Setup] 2024-02-06 14:28:51.72418 | Creating distribution object...
 x
 #> <Biodiversity distribution model>
 #> Background extent: 
diff --git a/reference/emptyraster.html b/reference/emptyraster.html
index 62f298ef..5dca1cd4 100644
--- a/reference/emptyraster.html
+++ b/reference/emptyraster.html
@@ -85,22 +85,22 @@ 
    Argumentsterra
    
+
    other arguments that can be passed to terra

    Value

    -

    an empty SpatRaster, i.e. all cells are NA.

    +

    an empty SpatRaster, i.e. all cells are NA.

    Examples

    require(terra)
 #> Loading required package: terra
-#> terra 1.7.65
-r <- rast(matrix(1:100, 5, 20))
+#> terra 1.7.71
+r <- rast(matrix(1:100, 5, 20))
 emptyraster(r)
 #> class       : SpatRaster 
 #> dimensions  : 5, 20, 1  (nrow, ncol, nlyr)
diff --git a/reference/engine_glm.html b/reference/engine_glm.html
index ccfad363..09ccf8d8 100644
--- a/reference/engine_glm.html
+++ b/reference/engine_glm.html
@@ -155,13 +155,12 @@ 
    See also
     
    Examples
    
     
    # Load background
-background <- terra::rast(system.file('extdata/europegrid_50km.tif',
+background <- terra::rast(system.file('extdata/europegrid_50km.tif',
 package='ibis.iSDM',mustWork = TRUE))
 
 # Add GLM as an engine
 x <- distribution(background) |> engine_glm()
-#> [Setup] 2024-01-25 22:00:00.59482 | Provide a background with a valid projection!
-#> [Setup] 2024-01-25 22:00:00.605784 | Creating distribution object...
+#> [Setup] 2024-02-06 14:28:52.694211 | Creating distribution object...
    diff --git a/reference/ensemble.html b/reference/ensemble.html index 55386cf1..633d8706 100644 --- a/reference/ensemble.html +++ b/reference/ensemble.html @@ -138,7 +138,7 @@

    Usage

    Arguments

    ...
    -

    Provided DistributionModel or SpatRaster objects.

    +

    Provided DistributionModel or SpatRaster objects.

    method
    @@ -185,7 +185,7 @@

    ArgumentsValue

    -

    A SpatRaster object containing the ensemble of the provided +

    A SpatRaster object containing the ensemble of the provided predictions specified by method and a coefficient of variation across all models.

    @@ -210,7 +210,7 @@

    DetailsNote

    If a list is supplied, then it is assumed that each entry in the list is a fitted DistributionModel object. Take care not to create an ensemble -of models constructed with different link functions, e.g. logistic vs log. +of models constructed with different link functions, e.g. logistic vs log. In this case the "normalize" parameter has to be set.

    @@ -224,16 +224,16 @@

    References

    Examples

    # Method works for fitted models as well as as rasters
-r1 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,
+r1 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,
  xmax = 1.5, ymin = -1.5, ymax = 1.5, vals = rnorm(3600,mean = .5,sd = .1))
-r2 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,
+r2 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,
  xmax = 1.5, ymin = -1.5, ymax = 1.5, vals = rnorm(3600,mean = .5,sd = .5))
-names(r1) <- names(r2) <- "mean"
+names(r1) <- names(r2) <- "mean"
 
 # Assumes previously computed predictions
 ex <- ensemble(r1, r2, method = "mean")
 
-terra::plot(ex)
+terra::plot(ex)
    diff --git a/reference/ensemble_partial.html b/reference/ensemble_partial.html index dcf2febf..f804772f 100644 --- a/reference/ensemble_partial.html +++ b/reference/ensemble_partial.html @@ -137,7 +137,7 @@

    Argumentsdata.frame or SpatRaster object supplied to +

    A optional data.frame or SpatRaster object supplied to the model (DefaultL NULL). This object needs to have identical names as the original predictors.

    @@ -161,7 +161,7 @@

    DetailsNote

    If a list is supplied, then it is assumed that each entry in the list is a fitted DistributionModel object. Take care not to create an ensemble -of models constructed with different link functions, e.g. logistic vs log. +of models constructed with different link functions, e.g. logistic vs log. By default the response functions of each model are normalized.

    diff --git a/reference/ensemble_spartial.html b/reference/ensemble_spartial.html index ce4a4bb9..e54f9829 100644 --- a/reference/ensemble_spartial.html +++ b/reference/ensemble_spartial.html @@ -139,7 +139,7 @@

    Argumentsdata.frame or SpatRaster object supplied to +

    A optional data.frame or SpatRaster object supplied to the model (DefaultL NULL). This object needs to have identical names as the original predictors.

    @@ -158,7 +158,7 @@

    ArgumentsValue

    -

    A SpatRaster object with the combined partial effects of the supplied models.

    +

    A SpatRaster object with the combined partial effects of the supplied models.

    Details

    @@ -169,7 +169,7 @@

    DetailsNote

    If a list is supplied, then it is assumed that each entry in the list is a fitted DistributionModel object. Take care not to create an ensemble -of models constructed with different link functions, e.g. logistic vs log. +of models constructed with different link functions, e.g. logistic vs log. By default the response functions of each model are normalized.

    diff --git a/reference/formatGLOBIOM.html b/reference/formatGLOBIOM.html index 4c6b22f0..ce9900a1 100644 --- a/reference/formatGLOBIOM.html +++ b/reference/formatGLOBIOM.html @@ -105,7 +105,7 @@

    ArgumentsSpatRaster object towards which projects +

    An optional SpatRaster object towards which projects should be transformed.

    @@ -126,7 +126,7 @@

    ArgumentsValue

    -

    A SpatRaster stack with the formatted GLOBIOM predictors.

    +

    A SpatRaster stack with the formatted GLOBIOM predictors.

    diff --git a/reference/get_rastervalue.html b/reference/get_rastervalue.html index ffe196d8..bd73b1bd 100644 --- a/reference/get_rastervalue.html +++ b/reference/get_rastervalue.html @@ -71,7 +71,7 @@

    This function simply extracts the values from a provided -SpatRaster, SpatRasterDataset or SpatRasterCollection object. For +SpatRaster, SpatRasterDataset or SpatRasterCollection object. For points where or NA values were extracted a small buffer is applied to try and obtain the remaining values.

    @@ -88,7 +88,7 @@

    ArgumentsSpatRaster object with the provided predictors.

    +

    A SpatRaster object with the provided predictors.

    ngb_fill
    @@ -110,7 +110,7 @@

    Value

    Details

    -

    It is essentially a wrapper for terra::extract.

    +

    It is essentially a wrapper for terra::extract.

    diff --git a/reference/ibis_options.html b/reference/ibis_options.html index 2ab1d247..0e896e78 100644 --- a/reference/ibis_options.html +++ b/reference/ibis_options.html @@ -140,7 +140,7 @@

    Examples#> [1] FALSE #> #> $ibis.seed -#> [1] 8459 +#> [1] 11283 #> #> $ibis.setupmessages #> [1] TRUE diff --git a/reference/interpolate_gaps.html b/reference/interpolate_gaps.html index 1741f5c4..1b57ea1d 100644 --- a/reference/interpolate_gaps.html +++ b/reference/interpolate_gaps.html @@ -93,7 +93,7 @@

    ArgumentsValue

    -

    logical indicating if the two SpatRaster objects have the same

    +

    logical indicating if the two SpatRaster objects have the same

    diff --git a/reference/limiting.html b/reference/limiting.html index eb121dbe..7233c259 100644 --- a/reference/limiting.html +++ b/reference/limiting.html @@ -78,7 +78,7 @@
    -

    Calculates a SpatRaster of locally limiting factors from a +

    Calculates a SpatRaster of locally limiting factors from a given projected model. To calculate this first the spartial effect of each individual covariate in the model is calculated.

    The effect is estimated as that variable most responsible for decreasing diff --git a/reference/load_model.html b/reference/load_model.html index c4a8d1b1..39e560a7 100644 --- a/reference/load_model.html +++ b/reference/load_model.html @@ -74,7 +74,7 @@

    The load_model function (opposed to the write_model) loads previous saved DistributionModel. It is essentially a wrapper to -readRDS.

    +readRDS.

    When models are loaded, they are briefly checked for their validity and presence of necessary components.

    diff --git a/reference/mask.html b/reference/mask.html index 7454fb44..2d5c1d17 100644 --- a/reference/mask.html +++ b/reference/mask.html @@ -78,7 +78,7 @@ by the ibis.iSDM package and an external layer, then intersects both. It currently takes either a DistributionModel, BiodiversityDatasetCollection, PredictorDataset or BiodiversityScenario as input.

    -

    As mask either a sf or SpatRaster object can be chosen. The mask will +

    As mask either a sf or SpatRaster object can be chosen. The mask will be converted internally depending on the object.

    @@ -101,7 +101,7 @@

    ArgumentsSpatRaster object.

    +

    A sf or SpatRaster object.

    inverse
    @@ -121,7 +121,7 @@

    Value

    See also

    -

    terra::mask()

    +

    terra::mask()

    diff --git a/reference/new_id.html b/reference/new_id.html index 00acd0d3..07d88bad 100644 --- a/reference/new_id.html +++ b/reference/new_id.html @@ -94,11 +94,11 @@

    Examples # print id print(i) -#> id: c4c1b581-e3a3-4f31-9edb-42b13c778037 +#> id: f6b8a01a-e065-4252-bae7-00c58d8d941c # convert to character as.character(i) -#> [1] "c4c1b581-e3a3-4f31-9edb-42b13c778037" +#> [1] "f6b8a01a-e065-4252-bae7-00c58d8d941c" # check if it is an Id object is.Id(i) diff --git a/reference/plot.html b/reference/plot.html index f61f9522..6827cd2f 100644 --- a/reference/plot.html +++ b/reference/plot.html @@ -96,7 +96,7 @@

    ArgumentsSpatRaster is supplied, this parameter specifies the layer +

    In case a SpatRaster is supplied, this parameter specifies the layer to be shown (Default: "mean").

    diff --git a/reference/predictor_derivate.html b/reference/predictor_derivate.html index 381293e4..3f8345e8 100644 --- a/reference/predictor_derivate.html +++ b/reference/predictor_derivate.html @@ -95,7 +95,7 @@

    Usage

    Arguments

    env
    -

    A SpatRaster object.

    +

    A SpatRaster object.

    option
    @@ -129,7 +129,7 @@

    ArgumentsValue

    -

    Returns the derived adjusted SpatRaster objects of identical resolution.

    +

    Returns the derived adjusted SpatRaster objects of identical resolution.

    Details

    diff --git a/reference/predictor_homogenize_na.html b/reference/predictor_homogenize_na.html index 6f83efa5..6d716293 100644 --- a/reference/predictor_homogenize_na.html +++ b/reference/predictor_homogenize_na.html @@ -95,7 +95,7 @@

    Usage

    Arguments

    env
    -

    A SpatRaster object with the predictors.

    +

    A SpatRaster object with the predictors.

    fill
    @@ -117,7 +117,7 @@

    ArgumentsValue

    -

    A SpatRaster object with the same number of layers as the input.

    +

    A SpatRaster object with the same number of layers as the input.

    diff --git a/reference/predictor_transform.html b/reference/predictor_transform.html index cb426a2d..e191b62e 100644 --- a/reference/predictor_transform.html +++ b/reference/predictor_transform.html @@ -71,9 +71,9 @@

    This function allows the transformation of provided environmental -predictors (in SpatRaster format). A common use case is for instance the +predictors (in SpatRaster format). A common use case is for instance the standardization (or scaling) of all predictors prior to model fitting. This -function works both with SpatRaster as well as with stars objects.

    +function works both with SpatRaster as well as with stars objects.

    @@ -91,7 +91,7 @@

    Usage

    Arguments

    env
    -

    A SpatRaster object.

    +

    A SpatRaster object.

    option
    @@ -123,12 +123,12 @@

    ArgumentsValue

    -

    Returns a adjusted SpatRaster object of identical resolution.

    +

    Returns a adjusted SpatRaster object of identical resolution.

    Details

    Available options are:

    • 'none' The original layer(s) are returned.

      • -

    • 'scale' This run the scale() function with default settings +

    • 'scale' This run the scale() function with default settings (1 Standard deviation) across all predictors. A sensible default to for most model fitting.

    • 'norm' This normalizes all predictors to a range from 0-1.

    • 'windsor' This applies a 'windsorization' to an existing raster layer @@ -139,7 +139,7 @@

      Details

      'percentile' This converts and bins all values into percentiles, e.g. the top 10% or lowest 10% of values and so on.

    • 'pca' This option runs a principal component decomposition of all -predictors (via prcomp()). It returns new predictors resembling all components +predictors (via prcomp()). It returns new predictors resembling all components in order of the most important ones. Can be useful to reduce collinearity, however note that this changes all predictor names to 'PCX', where X is the number of the component. The parameter 'pca.var' can be modified to specify the diff --git a/reference/pseudoabs_settings.html b/reference/pseudoabs_settings.html index cdb4acd6..545ae2f2 100644 --- a/reference/pseudoabs_settings.html +++ b/reference/pseudoabs_settings.html @@ -125,7 +125,7 @@

      Usage

      Arguments

      background
      -

      A SpatRaster or sf object over which background +

      A SpatRaster or sf object over which background points can be sampled. Default is NULL (Default) and the background is then added when the sampling is first called.

      @@ -161,13 +161,13 @@

      ArgumentsSpatRaster (in the case of method 'zones') +

      A sf or SpatRaster (in the case of method 'zones') object indicating the range of a species. Only used with method = "range" or method = "zones" (Default: NULL).

      bias
      -

      A SpatRaster with the same extent and projection and background. +

      A SpatRaster with the same extent and projection and background. Absence points will be preferentially sampled in areas with higher (!) bias. (Default: NULL).

      @@ -189,13 +189,13 @@

      Details

      'range' Absence points are created either inside or outside a provided additional layer that indicates for example a range of species (controlled through parameter inside).

      • -

    • 'zones' A ratified (e.g. of type factor) SpatRaster layer depicting zones from which absence +

    • 'zones' A ratified (e.g. of type factor) SpatRaster layer depicting zones from which absence points are to be sampled. This method checks which points fall within which zones and then samples absence points either within or outside these zones exclusively. Both 'layer' and 'inside' have to be set for this option.

    • 'target' Make use of a target background for sampling absence points. -Here a SpatRaster object has to be provided through the parameter 'layer'. +Here a SpatRaster object has to be provided through the parameter 'layer'. Absence points are then sampled exclusively within the target areas for grid cells with non-zero values.

    diff --git a/reference/scenario.html b/reference/scenario.html index c422e9d8..015095cd 100644 --- a/reference/scenario.html +++ b/reference/scenario.html @@ -85,7 +85,7 @@

    ArgumentsSpatRaster or sf object that limits the projection +

    A SpatRaster or sf object that limits the projection surface when intersected with the prediction data (Default: NULL). This can for instance be set as an expert-delineated constrain to limit spatial projections.

    diff --git a/reference/similarity.html b/reference/similarity.html index 3c0a8862..a6c217c7 100644 --- a/reference/similarity.html +++ b/reference/similarity.html @@ -118,7 +118,7 @@

    Usage

    Arguments

    obj

    A BiodiversityDistribution, DistributionModel or alternatively -a SpatRaster object.

    +a SpatRaster object.

    ref
    diff --git a/reference/simulate_population_steps.html b/reference/simulate_population_steps.html index 9ba3651a..09387e08 100644 --- a/reference/simulate_population_steps.html +++ b/reference/simulate_population_steps.html @@ -130,7 +130,7 @@

    ArgumentsSpatRaster or a numeric estimate of the +

    Either SpatRaster or a numeric estimate of the maximum carrying capacity, e.g. how many adult individual are likely to occur per grid cell. If set to numeric, then carrying capacity is estimated up to a maximum set (Note: a more clever way would be to use a species-area relationship @@ -138,7 +138,7 @@

    ArgumentsSpatRaster giving the initial population size. If not +

    A SpatRaster giving the initial population size. If not provided, then initial populations are guessed (see details) from the projected suitability rasters (Default: NULL).

    @@ -179,7 +179,7 @@

    Note

    The steps package has multiple options for simulating species population and not all possible options are represented in this wrapper.

    Furthermore, the package still makes use of the raster package for much -of its internal data processing. Since ibis.iSDM switched to terra a while +of its internal data processing. Since ibis.iSDM switched to terra a while ago, there can be efficiency problems as layers need to be translated between packages.

    diff --git a/reference/spartial.html b/reference/spartial.html index 7155e43d..2f7ae8c2 100644 --- a/reference/spartial.html +++ b/reference/spartial.html @@ -72,7 +72,7 @@

    Similar as partial this function calculates a partial response of a trained model for a given variable. Differently from partial in space. -However the result is a SpatRaster showing the spatial magnitude of the +However the result is a SpatRaster showing the spatial magnitude of the partial response.

    @@ -99,7 +99,7 @@

    Argumentsnumeric constant to be inserted for all other variables. -Default calculates the mean per variable.

    +Default calculates the mean per variable.

    newdata
    @@ -119,11 +119,11 @@

    ArgumentsValue

    -

    A SpatRaster containing the mapped partial response of the variable.

    +

    A SpatRaster containing the mapped partial response of the variable.

    Details

    -

    By default the mean is calculated across all parameters that are +

    By default the mean is calculated across all parameters that are not x.var. Instead a constant can be set (for instance 0) to be applied to the output.

    diff --git a/reference/thin_observations.html b/reference/thin_observations.html index 1b5195d9..601cfae3 100644 --- a/reference/thin_observations.html +++ b/reference/thin_observations.html @@ -119,12 +119,12 @@

    ArgumentsSpatRaster object with the background of the study +

    A SpatRaster object with the background of the study region. Use for assessing point density.

    env
    -

    A SpatRaster object with environmental covariates. Needed when +

    A SpatRaster object with environmental covariates. Needed when method is set to "environmental" or "bias" (Default: NULL).

    @@ -143,7 +143,7 @@

    ArgumentsSpatRaster to be supplied when option "zones" is chosen +

    A SpatRaster to be supplied when option "zones" is chosen (Default: NULL).

    diff --git a/reference/threshold.html b/reference/threshold.html index c462694c..87a26378 100644 --- a/reference/threshold.html +++ b/reference/threshold.html @@ -93,7 +93,7 @@ discrete representations of where suitable habitat might or might not exist. This so called threshold'ing can be done in various ways which are further described in the details.

    -

    In case a SpatRaster is provided as input in this function for +

    In case a SpatRaster is provided as input in this function for obj, it is furthermore necessary to provide a sf object for validation as there is no DistributionModel to read this information from.

    @@ -194,7 +194,7 @@

    ArgumentsValue

    -

    A SpatRaster if a SpatRaster object as input. Otherwise the threshold +

    A SpatRaster if a SpatRaster object as input. Otherwise the threshold is added to the respective DistributionModel or BiodiversityScenario object.

    diff --git a/reference/train.html b/reference/train.html index 33e87b66..eaf0e928 100644 --- a/reference/train.html +++ b/reference/train.html @@ -211,7 +211,7 @@

    DetailsThis function acts as a generic training function that - based on the provided BiodiversityDistribution object creates a new distribution model. The resulting object contains both a "fit_best" object of the estimated -model and, if inference_only is FALSE a SpatRaster object named +model and, if inference_only is FALSE a SpatRaster object named "prediction" that contains the spatial prediction of the model. These objects can be requested via object$get_data("fit_best").

    Other parameters in this function:

    • "filter_predictors" The parameter can be set to various options to @@ -262,7 +262,7 @@

      See also

      Examples

       # Load example data
- background <- terra::rast(system.file('extdata/europegrid_50km.tif',
+ background <- terra::rast(system.file('extdata/europegrid_50km.tif',
  package='ibis.iSDM',mustWork = TRUE))
  # Get test species
  virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg',
@@ -272,7 +272,7 @@ 
      Examples ll <- list.files(system.file('extdata/predictors/', package = 'ibis.iSDM',
  mustWork = TRUE),full.names = TRUE)
  # Load them as rasters
- predictors <- terra::rast(ll);names(predictors) <- tools::file_path_sans_ext(basename(ll))
+ predictors <- terra::rast(ll);names(predictors) <- tools::file_path_sans_ext(basename(ll))
 
  # Use a basic GLM to fit a SDM
  x <- distribution(background) |>
@@ -282,21 +282,20 @@ 
      Examples        add_predictors(env = predictors, transform = "scale", derivates = "none") |>
         # Use GLM as engine
         engine_glm()
-#> [Setup] 2024-01-25 22:00:11.717918 | Provide a background with a valid projection!
-#> [Setup] 2024-01-25 22:00:11.72865 | Creating distribution object...
-#> [Setup] 2024-01-25 22:00:11.72943 | Adding poipo dataset...
-#> [Setup] 2024-01-25 22:00:11.801099 | Adding predictors...
-#> [Setup] 2024-01-25 22:00:11.879135 | Transforming predictors...
+#> [Setup] 2024-02-06 14:29:04.125701 | Creating distribution object...
+#> [Setup] 2024-02-06 14:29:04.126564 | Adding poipo dataset...
+#> [Setup] 2024-02-06 14:29:04.202381 | Adding predictors...
+#> [Setup] 2024-02-06 14:29:04.282382 | Transforming predictors...
 
  # Train the model, Also filter out co-linear predictors using a pearson threshold
  mod <- train(x, only_linear = TRUE, filter_predictors = 'pearson')
-#> [Estimation] 2024-01-25 22:00:11.99227 | Collecting input parameters.
-#> [Estimation] 2024-01-25 22:00:12.05278 | Filtering predictors via pearson...
-#> [Estimation] 2024-01-25 22:00:12.059666 | Adding engine-specific parameters.
-#> [Estimation] 2024-01-25 22:00:12.060823 | Engine setup.
-#> [Estimation] 2024-01-25 22:00:12.251369 | Starting fitting: Species: 
-#> [Estimation] 2024-01-25 22:00:12.293568 | Starting prediction...
-#> [Done] 2024-01-25 22:00:12.417486 | Completed after 0.42 secs
+#> [Estimation] 2024-02-06 14:29:04.400893 | Collecting input parameters.
+#> [Estimation] 2024-02-06 14:29:04.465414 | Filtering predictors via pearson...
+#> [Estimation] 2024-02-06 14:29:04.472977 | Adding engine-specific parameters.
+#> [Estimation] 2024-02-06 14:29:04.474246 | Engine setup.
+#> [Estimation] 2024-02-06 14:29:04.671971 | Starting fitting: Species: 
+#> [Estimation] 2024-02-06 14:29:04.714102 | Starting prediction...
+#> [Done] 2024-02-06 14:29:04.840259 | Completed after 0.44 secs
  mod
 #> Trained GLM-Model (Unnamed run)
 #>   Strongest summary effects:
diff --git a/reference/validate.html b/reference/validate.html
index 0c76f0ea..d4133633 100644
--- a/reference/validate.html
+++ b/reference/validate.html
@@ -109,7 +109,7 @@ 
      Usage
     
      Arguments
      
     
      mod
      
 
      A fitted BiodiversityDistribution object with set predictors.
-Alternatively one can also provide directly a SpatRaster, however in this
+Alternatively one can also provide directly a SpatRaster, however in this
 case the point layer also needs to be provided.
      
 
 
diff --git a/reference/write_model.html b/reference/write_model.html
index d3b2999f..5e067e84 100644
--- a/reference/write_model.html
+++ b/reference/write_model.html
@@ -72,7 +72,7 @@
     
      
     
      The write_model function (opposed to the write_output) is a
 generic wrapper to writing a DistributionModel to disk. It is essentially
-a wrapper to saveRDS. Models can be loaded again via the load_model
+a wrapper to saveRDS. Models can be loaded again via the load_model
 function.
      
     
      
 
diff --git a/reference/write_output.html b/reference/write_output.html
index 2b499148..381682db 100644
--- a/reference/write_output.html
+++ b/reference/write_output.html
@@ -79,7 +79,7 @@
     
      The write_output function is a generic wrapper to writing any
 output files (e.g. projections) created with the ibis.iSDM-package. It is
 possible to write outputs of fitted DistributionModel,
-BiodiversityScenario or individual terra or stars objects. In
+BiodiversityScenario or individual terra or stars objects. In
 case a data.frame is supplied, the output is written as csv file.
 For creating summaries of distribution and scenario parameters and performance,
 see write_summary()
      
@@ -144,7 +144,7 @@ 
      Usage
     
      
     
      Arguments
      
     
      mod
      
-
      Provided DistributionModel, BiodiversityScenario, terra
+
      Provided DistributionModel, BiodiversityScenario, terra
 or stars object.
      
 
 
@@ -153,7 +153,7 @@ 
      Argumentscharacter for the output datatype. Following the terra::writeRaster
+
      A character for the output datatype. Following the terra::writeRaster
 options (Default: 'FLT4S').
      
 
 
diff --git a/search.json b/search.json
index 8550ce00..6ee6970b 100644
--- a/search.json
+++ b/search.json
@@ -1 +1 @@
-[{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"preparing-and-altering-biodiversity-data","dir":"Articles","previous_headings":"","what":"Preparing and altering biodiversity data","title":"Preparation of biodiversity and predictor data","text":"SDM approaches require observation biodiversity data, typically form presence-presence-absence data, can available range different formats points polygons. range existing tools assist modellers preparing cleaning input data (instance biases). vignette intend give overview options. Rather highlights functions created specifically ibis.iSDM package might help situations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"adding-pseudo-absence-points-to-presence-only-data","dir":"Articles","previous_headings":"Preparing and altering biodiversity data","what":"Adding pseudo-absence points to presence-only data","title":"Preparation of biodiversity and predictor data","text":"Although philosophy ibis.iSDM package advisable use presence-models Poisson point process modelling framework (‘poipo’ modelling functions use background points (see Warton Sheperd 2010). Yet, good case can also made instead add pseudo-absence points existing presence-data. allows use logistic regressions ‘poipa’ methods ibis.iSDM generally easier interpret (response scale 0 1) also faster fit model. Adding pseudo-absence data ibis.iSDM package works first specifiying Pseudoabsence options object contains parameters many pseudo-absences sampled. respective function called pseudoabs_settings(). details available options (many) can found help file. default packages uses random sampling absence points settings can queried ibis_options()$ibis.pseudoabsence. options defined, pseudoa-absence data can added point dataset via add_pseudoabsence(). Example:","code":"## Lets load some testing data from the package  # Background layer background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\", mustWork = TRUE)) # Load virtual species points virtual_species <- sf::st_read(system.file(\"extdata/input_data.gpkg\",package = \"ibis.iSDM\", mustWork = TRUE), \"points\",quiet = TRUE)  # Add a range  virtual_range <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'range', quiet = TRUE) # Define new settings for sampling points outside the minimum convex polygon of # the known presence data abs <- pseudoabs_settings(background = background,                           nrpoints = 1000, # Sample 1000 points                           method = \"mcp\", # Option for minimum convex polygon                           inside =  FALSE # Sample exclusively outside                             ) print( abs ) # See object, check abs$data for the options  # Now add to the point data point1 <- add_pseudoabsence(virtual_species,                             # Point to the column with the presence information                             field_occurrence = 'Observed',                             settings = abs)  plot(point1['Observed']) # --- # # Another option sampling inside the range, but biased by a bias layer bias <- terra::rast(system.file(\"extdata/predictors/hmi_mean_50km.tif\",                                 package = \"ibis.iSDM\", mustWork = TRUE))  abs <- pseudoabs_settings(background = background,                           nrpoints = 100, # Sample 100 points                           method = \"range\", # Define range as method                           inside =  TRUE, # Sample exclusively inside                           layer = virtual_range, # Define the range                           bias = bias # Set a bias layer                             )  # Add again to the point data point2 <- add_pseudoabsence(virtual_species,                             # Point to the column with the presence information                             field_occurrence = 'Observed',                             settings = abs)  plot(point2['Observed'])"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"thinning-observations","dir":"Articles","previous_headings":"Preparing and altering biodiversity data","what":"Thinning observations","title":"Preparation of biodiversity and predictor data","text":"Many presence-records often spatially highly biased varying observational processes resulting quite clustered point observations. example, urban areas natural sites near considerably often frequented citizens observed wildlife sites remote areas. Particular Poisson process models can problematic models critically assume - without accounting - observational process homogeneous space. Thinning observations method remove point observations areas “oversampled”. Critically however remove points grid cells provided background case never removes entire grid cell fully. can also beneficial model convergence modelling speed, particular well-sampled species (e.g. common blackbird Turdus merula) diminishing returns fitting SDM like 1 million presence-points instead just 20000 well separated ones. ibis.iSDM package implementation spatial thinning, one can also refer Aiello-Lammens et al. alternative implementation rationale thinning. Thinning needs conducted care effectively discards data!","code":"## We use the data loaded in above plot(virtual_species['Observed'], main = \"Original data\") # Random thinning. Note the messages of number of thinned points point1 <- thin_observations(data = virtual_species,                   background = background,                   method = 'random',                   remainpoints = 1 # Retain at minimum one point per grid cell!                   ) #> (random) thinning completed!  #> Original number of records: 208 #> Number of retained records: 175  plot(point1['Observed'], main = \"Random thinning\") # Another way: Use environmental thinning to retain enough points # across the niche defined by a set of covariates covariates <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE))  point2 <- thin_observations(data = virtual_species,                   background = background,                   env = covariates,                   method = 'environmental',                   remainpoints = 5 # Retain at minimum five points!                   ) #> (environmental) thinning completed!  #> Original number of records: 208 #> Number of retained records: 33  plot(point2['Observed'], main = \"Environmentally stratified data\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"preparing-and-altering-predictor-data","dir":"Articles","previous_headings":"","what":"Preparing and altering predictor data","title":"Preparation of biodiversity and predictor data","text":"order used species distribution modelling predictors need provided common extent, grain size geographic projections. need align provided background extent distribution() ideally contain missing data. missing data, package check remove model fitting points fall grid cells missing data. ibis.iSDM package number convenience functions modify input predictors. functions rather provide nuance(s) variation modelling process, rather preparing input data (needs undertaken using terra package).","code":"# Load some test covariates predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE))"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"transforming-predictors","dir":"Articles","previous_headings":"Preparing and altering predictor data","what":"Transforming predictors","title":"Preparation of biodiversity and predictor data","text":"better model convergence usually makes sense bring predictors common unit, example noramlizing scaling . ibis.iSDM package convenience function can applied terra ‘SpatRaster’ object. NOTE: functionality also available directly add_predictors() parameter!   options transformation also available listed methods file.","code":"# Let's take a simple layer for an example layer <- predictors$bio19_mean_50km  # Transform it in various way new1 <- predictor_transform(layer, option = \"norm\") new2 <- predictor_transform(layer, option = \"scale\")  new <- c(layer, new1, new2) names(new) <- c(\"original\", \"normalized\", \"scaled\") terra::plot( new ) # Another common use case is to windsorize a layer, for example by removing # top outliers form a prediction. # Here the values are capped to a defined percentile new3 <- predictor_transform(layer, option = \"windsor\",                             # Clamp the upper values to the 90% percentile                             windsor_props = c(0,.9))  new <- c(layer, new3) names(new) <- c(\"original\", \"windsorized\") terra::plot( new )"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"derivates-of-predictors","dir":"Articles","previous_headings":"Preparing and altering predictor data","what":"Derivates of predictors","title":"Preparation of biodiversity and predictor data","text":"simple linear SDM (e.g. engine_glmnet()) includes predictors thus assumes increase response variable follows linear relationship covariate. However, reality always simple usually can assumed many relationships highly non-linear otherwise complex. standard way introduce non-linearities linear algorithm create derivates predictors, example quadratic transformation temperature. ibis.iSDM package convenience function can applied terra ‘SpatRaster’ object create additional derivates model. Note creates (cases substantial) additional predictors. NOTE: functionality also available directly add_predictors() parameter!       fine-tuned control can also achieved creating specific interactions among variables, example one expects climate interact forest cover.","code":"# Let's take a simple layer for an example layer <- predictors$ndvi_mean_50km  # Make a quadratic transformation new1 <- predictor_derivate(layer, option = \"quadratic\")  new <- c(layer, new1) names(new) <- c(\"original\", \"quadratic\") terra::plot( new ) # Create some hinge transformations new2 <- predictor_derivate(layer, option = \"hinge\",                            # The number is controlled by the number of knots                             nknots = 4                             ) terra::plot( new2 ) # What does this do precisely? # Lets check df <- data.frame( ndvi = terra::values(layer),                   terra::values(new2))  plot(df$ndvi_mean_50km, df[,2], ylab = \"First hinge of ndvi\", xlab = \"NDVI\") plot(df$ndvi_mean_50km, df[,3], ylab = \"Second hinge of ndvi\",xlab = \"NDVI\") plot(df$ndvi_mean_50km, df[,4], ylab = \"Third hinge of ndvi\", xlab = \"NDVI\") plot(df$ndvi_mean_50km, df[,5], ylab = \"Fourth hinge of ndvi\",xlab = \"NDVI\") # Create interacting variables  new <- predictor_derivate(predictors,option = \"interaction\",                           int_variables = c(\"bio01_mean_50km\", \"CLC3_312_mean_50km\"))  plot(new, main = \"Interaction variable\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"homogenize-missing-data-among-predictors","dir":"Articles","previous_headings":"Preparing and altering predictor data","what":"Homogenize missing data among predictors","title":"Preparation of biodiversity and predictor data","text":"mentioned , model training covariates extracted biodiversity observational record. Missing data case discarded. example 10 predictors considered single one missing value one grid cell, grid cell considered missing among predictors well. ibis.iSDM package convenience functions easily harmonize check extent missing data set predictors can convenient assessing errors data preparation.","code":"# Make a subset of all predictors to show the concept layers <- subset(predictors,  c(\"aspect_mean_50km\",                                         \"CLC3_312_mean_50km\",                                         \"elevation_mean_50km\"))  # All these layers have identical data coverage. # Now add missing data in one of the layers for testing layers$CLC3_312_mean_50km[sample(1:ncell(layers), 1000)] <- NA   # Harmonize the predictors new <- predictor_homogenize_na(env = layers)  # Now all the predictors have identical coverage of NA values terra::plot(new) # Or assess like this plot(!terra::noNA(new$aspect_mean_50km), main = \"Missing observations\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"preparing-and-altering-future-scenario-data","dir":"Articles","previous_headings":"","what":"Preparing and altering future scenario data","title":"Preparation of biodiversity and predictor data","text":"Creating scenarios R requires input predictors formatted different format . ibis.iSDM package makes extensive use stars prepare load multi-dimensional data. One common issue predictors requested time dimension. example climate data might available decadal scale (e.g. 2020, 2030, 2040), yet predictions often required finer temporal grain. purpose ibis.iSDM contains dedicated function (interpolate_gaps()), can also directly called within project().","code":"# Load some stars rasters ll <- list.files(system.file('extdata/predictors_presfuture/',                              package = 'ibis.iSDM',                              mustWork = TRUE),full.names = TRUE)  # Load the same files future ones suppressWarnings(   pred_future <- stars::read_stars(ll) |> dplyr::slice('Time', seq(1, 86, by = 10)) ) sf::st_crs(pred_future) <- sf::st_crs(4326)  # The predictors are here only available every 10 years stars::st_get_dimension_values(pred_future, 3) #> Units: [(days since 1970-1-1)] #> [1] 16436 20089 23741 27394 31046 34699 38351 42004 45656  # --- # # The ibis.iSDM contains here a function to make interpolation among timesteps, # thus filling gaps in between.  # As an example, # Here we make a temporal interpolation to create an annual time series new <- interpolate_gaps(pred_future, date_interpolation = \"annual\")  stars::st_get_dimension_values(new, 3) #>  [1] \"2015-07-02\" \"2025-07-02\" \"2035-07-02\" \"2045-07-02\" \"2055-07-02\" #>  [6] \"2065-07-02\" \"2075-07-02\" \"2085-07-02\" \"2095-07-02\" \"2016-07-02\" #> [11] \"2017-07-02\" \"2018-07-02\" \"2019-07-02\" \"2020-07-02\" \"2021-07-02\" #> [16] \"2022-07-02\" \"2023-07-02\" \"2024-07-02\" \"2026-07-02\" \"2027-07-02\" #> [21] \"2028-07-02\" \"2029-07-02\" \"2030-07-02\" \"2031-07-02\" \"2032-07-02\" #> [26] \"2033-07-02\" \"2034-07-02\" \"2036-07-02\" \"2037-07-02\" \"2038-07-02\" #> [31] \"2039-07-02\" \"2040-07-02\" \"2041-07-02\" \"2042-07-02\" \"2043-07-02\" #> [36] \"2044-07-02\" \"2046-07-02\" \"2047-07-02\" \"2048-07-02\" \"2049-07-02\" #> [41] \"2050-07-02\" \"2051-07-02\" \"2052-07-02\" \"2053-07-02\" \"2054-07-02\" #> [46] \"2056-07-02\" \"2057-07-02\" \"2058-07-02\" \"2059-07-02\" \"2060-07-02\" #> [51] \"2061-07-02\" \"2062-07-02\" \"2063-07-02\" \"2064-07-02\" \"2066-07-02\" #> [56] \"2067-07-02\" \"2068-07-02\" \"2069-07-02\" \"2070-07-02\" \"2071-07-02\" #> [61] \"2072-07-02\" \"2073-07-02\" \"2074-07-02\" \"2076-07-02\" \"2077-07-02\" #> [66] \"2078-07-02\" \"2079-07-02\" \"2080-07-02\" \"2081-07-02\" \"2082-07-02\" #> [71] \"2083-07-02\" \"2084-07-02\" \"2086-07-02\" \"2087-07-02\" \"2088-07-02\" #> [76] \"2089-07-02\" \"2090-07-02\" \"2091-07-02\" \"2092-07-02\" \"2093-07-02\" #> [81] \"2094-07-02\""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"load-package-and-make-a-basic-model","dir":"Articles","previous_headings":"","what":"Load package and make a basic model","title":"Train a basic model","text":"Creating model ibis.iSDM package relatively straight forward demonstrate testdata come package. data show distribution simulated forest-associated species northern Europe. also test predictors available modelling. first lets load data: example model going use ‘Integrated Nested Laplace approximation (INLA)’ modelling framework available INLA inlabru packages. implemented separately ibis.iSDM package, especially dealing future scenarios use inlabru package advised. Now lets build simple model object. case make use presence-biodiversity records (add_biodiversity_poipo). presence-records added object created distribution() default modelled intensity \\(\\lambda\\) inhomogeneous Poisson point process model (PPM), Number Individuals \\(N\\) integrated relative rate occurrence per unit area: \\(N_i \\sim Poisson(\\lambda_i|A_i)\\). \\(\\lambda\\) can estimated relating environmental covariates \\(log(\\lambda_i) = \\alpha + \\beta(x_i)\\), \\(\\) grid cell. inhomogeneous since \\(lambda\\) varies whole sampling extent. context species distribution modelling PPMs structurally similar popular Maxent modelling framework (see Renner & Warton 2013 Renner et al. 2015. Critically, presence-records can give indication biased sampling thus sampling bias taken somehow account, either careful data preparation, apriori thinning model-based control including covariates \\(\\sigma_i\\) might explain sampling bias. print call end now shows summary statistics contained object, extent modelling background projection used, number biodiversity datasets added statistics predictors, eventual priors engine used. course steps can also done “pipe” using |> syntax. Also helpful know object contains number helper functions allow easy summary visualization contained data. example, possible plot obtain data added object.  Now finally model can estimated using supplied engine. train function many available parameters affect model fitted. Unless possible, default way fitting linear model based provided engine biodiversity data types.","code":"# Load the package library(ibis.iSDM) library(inlabru) library(xgboost) library(terra) library(uuid) library(assertthat)  # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE) # Background layer background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\", mustWork = TRUE)) # Load virtual species points virtual_species <- sf::st_read(system.file(\"extdata/input_data.gpkg\",package = \"ibis.iSDM\", mustWork = TRUE), \"points\")  #> Reading layer `points' from data source  #>   `/home/runner/work/_temp/Library/ibis.iSDM/extdata/input_data.gpkg'  #>   using driver `GPKG' #> Simple feature collection with 208 features and 5 fields #> Geometry type: POINT #> Dimension:     XY #> Bounding box:  xmin: 4.109162 ymin: 48.7885 xmax: 24.47594 ymax: 64.69323 #> Geodetic CRS:  WGS 84 # Predictors predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE)) # Make use only of a few of them predictors <- subset(predictors, c(\"bio01_mean_50km\",\"bio03_mean_50km\",\"bio19_mean_50km\",                                             \"CLC3_112_mean_50km\",\"CLC3_132_mean_50km\",                                             \"CLC3_211_mean_50km\",\"CLC3_312_mean_50km\",                                             \"elevation_mean_50km\")) # First we define a distribution object using the background layer mod <- distribution(background)  # Then lets add species data to it.  # This data needs to be in sf format and key information is that # the model knows where occurrence data is stored (e.g. how many observations per entry) as # indicated by the field_occurrence field. mod <- add_biodiversity_poipo(mod, virtual_species,                                       name = \"Virtual test species\",                                       field_occurrence = \"Observed\")  # Then lets add predictor information # Here we are interested in basic transformations (scaling), but derivates (like quadratic) # for now, but check options mod <- add_predictors(mod,                        env = predictors,                       transform = \"scale\", derivates = \"none\")  # Finally define the engine for the model # This uses the default data currently backed in the model, # !Note that any other data might require an adaptation of the default mesh parameters used by the engine! mod <- engine_inlabru(mod)  # Print out the object to see the information that is now stored within print(mod) #>  #> Background extent:  #>      xmin: -16.064, xmax: 36.322, #>      ymin: 34.95, ymax: 71.535 #>    projection: +proj=longlat +datum=WGS84 +no_defs #>  ---------  #> Biodiversity data: #>    Point - Presence only <208 records> #>  ---------  #>   predictors:     bio01_mean_50km, bio03_mean_50km, bio19_mean_50km, ... (8 predictors) #>   priors:          #>   latent:         None #>   log:             #>   engine:          print(\"Create model\") #> [1] \"Create model\"  mod <- distribution(background) |>         add_biodiversity_poipo(virtual_species,                               name = \"Virtual test species\",                               field_occurrence = \"Observed\") |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_inlabru() # Make visualization of the contained biodiversity data plot(mod$biodiversity) # Other options to explore names(mod) #>  [1] \"summary\"                     \"show_biodiversity_length\"    #>  [3] \"show_biodiversity_equations\" \"show_background_info\"        #>  [5] \"show\"                        \"set_priors\"                  #>  [7] \"set_predictors\"              \"set_offset\"                  #>  [9] \"set_log\"                     \"set_limits\"                  #> [11] \"set_latent\"                  \"set_engine\"                  #> [13] \"set_control\"                 \"set_biodiversity\"            #> [15] \"rm_priors\"                   \"rm_predictors\"               #> [17] \"rm_offset\"                   \"rm_limits\"                   #> [19] \"rm_latent\"                   \"rm_engine\"                   #> [21] \"rm_control\"                  \"priors\"                      #> [23] \"print\"                       \"predictors\"                  #> [25] \"plot_offsets\"                \"plot_bias\"                   #> [27] \"plot\"                        \"offset\"                      #> [29] \"name\"                        \"log\"                         #> [31] \"limits\"                      \"latentfactors\"               #> [33] \"initialize\"                  \"get_resolution\"              #> [35] \"get_projection\"              \"get_priors\"                  #> [37] \"get_prior_variables\"         \"get_predictor_names\"         #> [39] \"get_offset_type\"             \"get_offset\"                  #> [41] \"get_log\"                     \"get_limits\"                  #> [43] \"get_latent\"                  \"get_extent_dimensions\"       #> [45] \"get_extent\"                  \"get_engine\"                  #> [47] \"get_control\"                 \"get_biodiversity_types\"      #> [49] \"get_biodiversity_names\"      \"get_biodiversity_ids\"        #> [51] \"get_biodiversity_equations\"  \"engine\"                      #> [53] \"control\"                     \"clone\"                       #> [55] \"biodiversity\"                \"background\"                  #> [57] \".__enclos_env__\" print(\"Fit model\") #> [1] \"Fit model\"  # Finally train fit <- train(mod,              runname =  \"Test INLA run\",              verbose = FALSE # Don't be chatty              )"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"summarizing-and-plotting-the-fitted-distribution-object","dir":"Articles","previous_headings":"","what":"Summarizing and plotting the fitted distribution object","title":"Train a basic model","text":"created distribution model object can visualized interacted . print() outputs model, inherent parameters whether predictions contained within. summary() creates summary output contained model. plot() makes visualization prediction background effects() visualizes effects, usually default plot package used fit model.   See reference help pages options including calculating threshold(), partial() similarity() estimate used data.   common practice species distribution modelling resulting predictions thresholded, e.g. abstraction continious prediction created separates background areas environment supporting species presumably suitable non-suitable. Threshold can used ibis.iSDM via threshold() functions suppling either fitted model, RasterLayer Scenario object.   options functions please see help pages!","code":"# Plot the mean of the posterior predictions plot(fit, \"mean\") # Print out some summary statistics summary(fit) #> # A tibble: 9 × 8 #>   variable               mean     sd     q05     q50    q95    mode   kld #>                                   #> 1 Intercept           -2.46   0.126  -2.66   -2.46   -2.25  -2.46       0 #> 2 bio01_mean_50km     -0.0149 0.178  -0.307  -0.0149  0.277 -0.0149     0 #> 3 bio03_mean_50km     -0.492  0.162  -0.759  -0.492  -0.225 -0.492      0 #> 4 bio19_mean_50km      0.511  0.120   0.313   0.511   0.709  0.511      0 #> 5 CLC3_112_mean_50km   0.444  0.0702  0.329   0.444   0.560  0.444      0 #> 6 CLC3_132_mean_50km   0.0216 0.0598 -0.0768  0.0216  0.120  0.0216     0 #> 7 CLC3_211_mean_50km   0.946  0.107   0.771   0.946   1.12   0.946      0 #> 8 CLC3_312_mean_50km   1.09   0.0912  0.944   1.09    1.24   1.09       0 #> 9 elevation_mean_50km  0.0567 0.113  -0.130   0.0567  0.243  0.0567     0  # Show the default effect plot from inlabru effects(fit) # To calculate a partial effect for a given variable o <- partial(fit, x.var = \"CLC3_312_mean_50km\", plot = TRUE) # The object o contains the data underlying this figure  # Similarly the partial effect can be visualized spatially as 'spartial' s <- spartial(fit, x.var = \"CLC3_312_mean_50km\") plot(s[[1]], col = rainbow(10), main = \"Marginal effect of forest on the relative reporting rate\") # Calculate a threshold based on a 50% percentile criterion fit <- threshold(fit, method = \"percentile\", value = 0.5)  # Notice that this is now indicated in the fit object print(fit) #> Trained INLABRU-Model (Test INLA run) #>   Strongest summary effects: #>      Positive: CLC3_312_mean_50km, CLC3_211_mean_50km, bio19_mean_50km, ... (6) #>      Negative: bio01_mean_50km, bio03_mean_50km, Intercept (3) #>   Prediction fitted: yes #>   Threshold created: yes  # There is also a convenient plotting function fit$plot_threshold() # It is also possible to use truncated thresholds, which removes non-suitable areas # while retaining those that are suitable. These are then normalized to a range of [0-1] fit <- threshold(fit, method = \"percentile\", value = 0.5, format = \"normalize\") fit$plot_threshold()"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"validation-of-model-predictions","dir":"Articles","previous_headings":"","what":"Validation of model predictions","title":"Train a basic model","text":"ibis.iSDM package provides convenience function obtain validation results fitted models. Validation can done continious discrete predictions, latter requires computed threshold fits (see ). ‘validate’ fitted model using data used model fitting. scientific paper recommend implement cross-validation scheme obtain withheld data use independently gathered data. Validating integrated SDMs, particular fitted multiple likelihoods challenging something yet fully explored scientific literature. example strong priors can substantially improve modifying response functions model, challenging validate validation data similar biases training data. One way SDMs can validated spatial block validation, however care needs taken datasets part block.","code":"# By Default validation statistics are continuous and evaluate the predicted estimates against the number of records per grid cell. fit$rm_threshold() validate(fit, method = \"cont\") #>                                modelid                 name     method #> 1 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous #> 2 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous #> 3 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous #> 4 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous #> 5 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous #> 6 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species continuous #>       metric        value #> 1          n 175.00000000 #> 2       rmse   0.87856015 #> 3        mae   0.67314153 #> 4    logloss   1.77608616 #> 5   normgini  -0.07569721 #> 6 cont.boyce   0.26208641  # If the prediction is first thresholded, we can calculate discrete validation estimates (binary being default) fit <- threshold(fit, method = \"percentile\", value = 0.5, format = \"binary\") validate(fit, method = \"disc\") #>                                 modelid                 name   method #> 1  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 2  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 3  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 4  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 5  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 6  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 7  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 8  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 9  8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 10 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 11 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 12 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #> 13 8e18b74f-932d-4856-9d8b-cbbf30b86506 Virtual test species discrete #>                 metric       value #> 1                    n 506.0000000 #> 2                  auc   0.6804316 #> 3     overall.accuracy   0.7351779 #> 4  true.presence.ratio   0.3963964 #> 5            precision   0.6518519 #> 6          sensitivity   0.5028571 #> 7          specificity   0.8580060 #> 8                  tss   0.3608632 #> 9                   f1   0.5677419 #> 10             logloss   6.2052837 #> 11   expected.accuracy   0.5718961 #> 12               kappa   0.3814068 #> 13         brier.score   0.2648221"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"constrain-a-model-in-prediction-space","dir":"Articles","previous_headings":"","what":"Constrain a model in prediction space","title":"Train a basic model","text":"Species distribution models quite often extrapolate areas species unlikely persist thus likely predict false presences false absences. “overprediction” can caused multiple factors true biological constraints (e.g. dispersal), used algorithm trying clever overfitting towards complex relationships (machine learning literature problem commonly known bias vs variance tradeoff). One option counter extent SDMs add spatial constraints spatial latent effects. underlying assumption distances geographic space can extent approximate unknown unquantified factors determine species range. options constrains integrate additional data sources add parameter constraints (see [integrate_data] vignette). Currently ibis.iSDM package supports addition spatial latent effects via add_latent_spatial(). See help file information. Note every spatial term accounts spatial autocorrelation, simply add distance observations predictor (thus assuming much spatial pattern can explained commonalities sampling process).   Another option constraining prediction place concrete limits prediction surface. can done adding factor zone layer distribution object. Internally, assessed ‘zones’ biodiversity observations fall, discarding others prediction. approach can particular suitable current future projections larger scale using instance biome layer stratification. assumes rather unlikely species distributions shift different biomes entirely, instance dispersal eco-evolutionary constraints. Note approach effectively also limits prediction background / output!","code":"# Here we are going to use the xgboost algorithm instead and set as engine below. # We are going to fit two separate Poisson Process Models (PPMs) on presence-only data.  # Load the predictors again predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\"), \"*.tif\",full.names = TRUE)) predictors <- subset(predictors, c(\"bio01_mean_50km\",\"bio03_mean_50km\",\"bio19_mean_50km\",                                             \"CLC3_112_mean_50km\",\"CLC3_132_mean_50km\",                                             \"CLC3_211_mean_50km\",\"CLC3_312_mean_50km\",                                             \"elevation_mean_50km\",                                    \"koeppen_50km\")) # One of them (Köppen) is a factor, we will now convert this to a true factor variable predictors$koeppen_50km <- terra::as.factor(predictors$koeppen_50km)  # Create a distribution modelling pipeline x <- distribution(background) |>    add_biodiversity_poipo(virtual_species, field_occurrence = 'Observed', name = 'Virtual points') |>   add_predictors(predictors, transform = 'scale', derivates = \"none\") |>   engine_xgboost(iter = 8000)  # Now train 2 models, one without and one with a spatial latent effect mod_null <- train(x, runname = 'Normal PPM projection', only_linear = TRUE, verbose = FALSE) # And with an added constrain # Calculated as nearest neighbour distance (NND) between all input points mod_dist <- train(x |> add_latent_spatial(method = \"nnd\"),                   runname = 'PPM with NND constrain', only_linear = TRUE, verbose = FALSE) #>  |---------|---------|---------|---------| =========================================                                             # Compare both plot(background, main = \"Biodiversity data\"); plot(virtual_species['Observed'], add = TRUE) plot(mod_null) plot(mod_dist) # Create again a distribution object, but this time with limits (use the Köppen-geiger layer from above) # The zones layer must be a factor layer (e.g. is.factor(layer) )  # Zone layers can be supplied directly to distribution(background, limits = zones) # or through an extrapolation control as shown below. x <- distribution(background) |>    add_biodiversity_poipo(virtual_species, field_occurrence = 'Observed', name = 'Virtual points') |>   add_predictors(predictors, transform = 'scale', derivates = \"none\") |>   # Since we are adding the koeppen layer as zonal layer, we disgard it from the predictors   rm_predictors(\"koeppen_50km\") |>    add_control_extrapolation(layer = predictors$koeppen_50km, method = \"zones\") |>    engine_xgboost(iter = 3000, learning_rate = 0.01)  # Spatially limited prediction mod_limited <- train(x, runname = 'Limited prediction background', only_linear = TRUE, verbose = FALSE)  # Compare the output plot(mod_limited)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"load-relevant-packages-and-testing-data","dir":"Articles","previous_headings":"","what":"Load relevant packages and testing data","title":"Data integration","text":"Lets load prepared test data exercise. time going make use several datasets. can define generic model use sections .","code":"# Load the package library(ibis.iSDM) library(inlabru) library(glmnet) library(xgboost) library(terra) library(igraph) library(assertthat)  # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE) # Background layer background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\", mustWork = TRUE)) # Load virtual species points virtual_species <- sf::st_read(system.file(\"extdata/input_data.gpkg\",package = \"ibis.iSDM\", mustWork = TRUE), \"points\", quiet = TRUE)  virtual_range <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'range', quiet = TRUE)  # In addition we will use the species data to generate a presence-absence dataset with pseudo-absence points. # Here we first specify the settings to use: ass <- pseudoabs_settings(background = background, nrpoints = 200,                           method =  \"random\") virtual_pseudoabs <- add_pseudoabsence(df = virtual_species, field_occurrence = \"Observed\",                                        settings = ass)  # Predictors predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE)) # Make use only of a few of them predictors <- subset(predictors, c(\"bio01_mean_50km\",\"bio03_mean_50km\",\"bio19_mean_50km\",                                             \"CLC3_112_mean_50km\",\"CLC3_132_mean_50km\",                                             \"CLC3_211_mean_50km\",\"CLC3_312_mean_50km\",                                             \"elevation_mean_50km\")) # First define a generic model and engine using the available predictors basemodel <- distribution(background) |>        add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_inlabru()"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-through-predictors","dir":"Articles","previous_headings":"","what":"Integration through predictors","title":"Data integration","text":"simple way integrating prior observations species distribution models add covariate. based assumption instance expert-drawn range map can useful predicting species exist might might find suitable habitat (see instance Domisch et al. 2016). benefit approach predictors can easily added kinds engines ibis.ISDM package also used scenarios. Expert-ranges can currently added simple binary distance transform. latter options available bossMaps R-package described Merow et al. 2017. Another option added possibility add thresholded masks based elevational () limits. idea generate two layers, one areas lower upper range one upper range. Regression thresholded layers can thus approximate lower upper bounds. instance suppose species known occur 300 800m sea level, can added follows:","code":"# Here we simply add the range as simple binary predictor mod1 <- basemodel |>     add_predictor_range(virtual_range, method = \"distance\")  # We can see that the range has been added to the predictors object # 'distance_range' mod1$get_predictor_names() #> [1] \"bio01_mean_50km\"     \"bio03_mean_50km\"     \"bio19_mean_50km\"     #> [4] \"CLC3_112_mean_50km\"  \"CLC3_132_mean_50km\"  \"CLC3_211_mean_50km\"  #> [7] \"CLC3_312_mean_50km\"  \"elevation_mean_50km\" \"distance_range\" # Specification  basemodel <- distribution(background) |>        add_predictors(env = predictors, transform = \"scale\", derivates = \"none\")  |>        engine_inlabru()   mod1 <- basemodel |>    add_predictor_elevationpref(layer = predictors$elevation_mean_50km,                               lower = 300, upper = 800)  # Plot the threshold for an upper plot( mod1$predictors$get_data()[[c(\"elev_low\", \"elev_high\")]] )"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-through-offsets","dir":"Articles","previous_headings":"","what":"Integration through offsets","title":"Data integration","text":"Apart including spatial-explicit prior biodiversity knowledge predictors SDM model, - particular Poisson Process Models (PPM) - also different approach, include variable offset prediction. effectively tells respective engine change intercepts coefficients based existing knowledge, can instance existing coefficient. Offsets can specified addition nuisance model, instance either adding expert-delineated range offset factoring spatial bias areas high sampling density accessibility. Multiple offsets can specified given PPM simply multiplying , since \\(log(off_1 * off_2) = log(off_1) + log(off_2)\\). comprehensive overview including offsets SDMs can found Merow et al. (2016).  ways add offsets model object, either directly (add_offset()) externally calculated RasterLayer instance “BossMaps” R-package, calculate range (add_offset_range()) elevation (add_offset_elevation()) offset, also biased offset (add_offset_bias()) case offset removed prediction.","code":"# Specification  mod1 <- distribution(background)  |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\")  |>        add_biodiversity_poipo(virtual_species,field_occurrence = \"Observed\") |>         add_offset_range(virtual_range, distance_max = 5e5) |>         engine_glmnet() |>     # Train   train(runname = \"Prediction with range offset\",only_linear = TRUE)  plot(mod1)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-with-priors","dir":"Articles","previous_headings":"","what":"Integration with priors","title":"Data integration","text":"different type integration also possible use informed priors, can set fixed random effects model. Bayesian context prior generally understood form uncertain quantity meant reflect direction /magnitude model parameters usually known -priori inference prediction. Offsets can also understood “priors”, however context SDMs, usually included spatial-explicit data, opposed priors available tabular form (known habitat affiliations). Since ibis.iSDM package supports variety engines Bayesian strict sense (engine_gdb engine_xgboost), specification priors differs depending engine question. Generally [Prior-class] objects can grouped : Probabilistic priors estimates placed example mean (\\(\\mu\\)) standard deviation (\\(\\sigma\\)) precision case [engine_inla]. priors usually allow greatest amount flexibility since able incorporate information sign magnitude coefficient. Monotonic constraints direction coefficient predictor model, \\(f(x_1) >= f(x_2)\\) \\(f(x_1) <= f(x_2)\\). Useful incorporate instance prior ecological knowledge certain response function example positive. complex priors specified random spatial effects penalized complexity priors used SPDE effects [add_latent_spatial()]. Probabilistic priors inclusion probability certain variable certainty variable included regularized outcome. example used case [engine_breg] [engine_glmnet]. Prior specifications specific engine information can found individual help pages priors() function.   also now convenience function allows extract coefficients weights existing model can passed another model engine (get_priors()). requirement fitted model provided well target engine coefficients/priors created.","code":"# Set a clean base model with biodiversity data x <- distribution(background) |>        add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        add_biodiversity_poipo(virtual_species, field_occurrence = \"Observed\") |>         engine_inlabru()  # Make a first model mod1 <- train(x, only_linear = TRUE)  # Now assume we now that the species occurs more likely in intensively farmed land.  # We can use this information to construct a prior for the linear coefficient. p <- INLAPrior(variable = \"CLC3_211_mean_50km\",                type = \"normal\",                hyper = c(2, 1000) # Precision priors, thus larger sigmas indicate higher precision                ) # Single/Multiple priors need to be passed to `priors` and then added to the model object. pp <- priors(p) # The variables and values in this object can be queried as well pp$varnames() #> 90173c31-3b9f-4fba-848e-219430b46621  #>                 \"CLC3_211_mean_50km\"  # Priors can then be added via  mod2 <- train(x |> add_priors(pp), only_linear = TRUE) # Or alternatively directly as parameter via add_predictors, # e.g. add_predictors(env = predictors, priors = pp)  # Compare the difference in effects p1 <- partial(mod1, pp$varnames(), plot = TRUE) p2 <- partial(mod2, pp$varnames(), plot = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-with-ensembles","dir":"Articles","previous_headings":"","what":"Integration with ensembles","title":"Data integration","text":"Another straight forward way model-based integration simply fit two separate models different biodiversity dataset create ensemble . approach also works across different engines variety data types (cases requiring normalization given difference units model assumptions). (Note also possible create ensemble partial responses via ensemble_partial()).","code":"# Create and fit two models mod1 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_glmnet() |>        # Add dataset 1        add_biodiversity_poipo(poipo = virtual_species, name = \"Dataset1\",field_occurrence = \"Observed\") |>        train(runname = \"Test1\", only_linear = TRUE)  mod2 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_xgboost(iter = 5000) |>         # Add dataset 2, Here we simple simulate presence-only points from a range       add_biodiversity_polpo(virtual_range, name = \"Dataset2\",field_occurrence = \"Observed\",                              simulate = TRUE,simulate_points = 300) |>         train(runname = \"Test1\", only_linear = FALSE)  # Show outputs of each model individually and combined plot(mod1) plot(mod2) # Now create an ensemble: # By setting normalize to TRUE we furthermore ensure each prediction # is on a comparable scale [0-1]. e <- ensemble(mod1, mod2, method = \"mean\", normalize = TRUE)  # The ensemble contains the mean and the coefficient of variation across all objects plot(e)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"combined-and-joint-likelihood-estimation","dir":"Articles","previous_headings":"","what":"Combined and joint likelihood estimation","title":"Data integration","text":"examples always added single biodiversity data source model trained, add multiple different ones? outlined Isaac et al. 2020 joint, model-based integration different data sources allows borrow strengths different types datasets (quantity, quality) accurate parameter estimations well control biases. Particular SDMs also benefit avoiding make unreasonable assumptions absence species, commonly done addition pseudo-absences (despite called pseudo, logistic likelihood function treats true absence). Depending engine, ibis.iSDM package currently supports either combined joint estimation several datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"combined-integration","dir":"Articles","previous_headings":"Combined and joint likelihood estimation","what":"Combined integration","title":"Data integration","text":"default engines support joint estimation (see ) make use combined integration, currently three different options: “predictor”: predicted output first (previously fitted) models added predictor stack thus predictors subsequent models (Default). “offset”: predicted output first (previously fitted) models added spatial offsets subsequent models. Offsets back-transformed depending model family. might work likelihood functions engines! “prior”: option make use coefficients previous model define priors used next model. Note option creates priors based previous fits can result unreasonable constrains (particular coefficients driven largely latent variables). Can used projections (scenario()). “interaction”: case two datasets type also possible make use factor interactions. case prediction made based first reference level (e.g. first added dataset) others “partialed” prediction. method works one fits model multiple datasets response (e.g. Bernoulli distributed). Can used projections (scenario()). “weights”: type integration works two biodiversity datasets type. datasets combined one, however observations weighted weights parameter add_biodiversity call. can example used give one dataset arbitrary (expert-defined) higher value compared another. can specified parameter train(). Note methods (like “predictor” & “offset”), models trained sequence datasets added!","code":"# Specification  mod1 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>      # A presence only dataset       add_biodiversity_poipo(virtual_species,field_occurrence = \"Observed\") |>       # A Presence absence dataset       add_biodiversity_poipa(virtual_pseudoabs,field_occurrence = \"Observed\") |>         engine_xgboost() |>    # Train   train(runname = \"Combined prediction\",only_linear = TRUE,         method_integration = \"predictor\")  # The resulting object contains only the final prediction, e.g. that of the presence-absence model plot(mod1)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"joint-likelihood-estimation","dir":"Articles","previous_headings":"Combined and joint likelihood estimation","what":"Joint likelihood estimation","title":"Data integration","text":"engines, notably [engine_inla], [engine_inlabru] [engine_stan] support joint estimation multiple likelihoods. algorithmic approach package generally follows approach outlined presence-datasets modelled log-Gaussian Cox process expected number individuals estimated function area \\(\\) following Poisson distribution: \\[\\begin{align*} N() &\\sim {\\sf Poisson}\\left(\\int_{} \\lambda()\\right) \\\\ \\end{align*}\\] \\[\\begin{align*} \\log(\\lambda()) = \\alpha_{1} + \\sum_{k}^{K} \\beta_{k}x_{} \\end{align*}\\] \\(N\\) number individuals, \\(\\) Area given spatial unit \\(\\), \\(N()\\) estimate relative rate occurrence per unit area (ROR). \\(k\\) increment \\(K\\) number predictors. \\(\\lambda\\) intensity function, \\(\\alpha\\) intercept \\(\\beta\\) parameter coefficients environmental covariates. Note interactions Presence-absence data estimated draws Bernoulli distribution: \\[\\begin{align*} Y_{} &\\sim {\\sf Bernoulli(p_{})}, = 1, 2, ... \\\\ \\end{align*}\\] \\[\\begin{align*} \\log(-\\log(1-p_{})) &= \\alpha_{2} + \\sum_{k}^{K} \\beta_{k}x_{} \\end{align*}\\] \\(Y\\) presence-absence record (usually standardized survey) sampled Bernoulli distribution given spatial unit \\(\\). \\(\\alpha\\) intercept \\(\\beta\\) parameter coefficients environmental covariates. log-likelihood can understood cloglog functon. Joint likelihood estimated multiplying two likelihoods \\(\\prod_{l}^{L} f(l)\\), \\(L\\) individual likelihood, \\(\\beta_{k}\\) shared parameters two likelihoods. works assume \\(cloglog(p_i) \\approx log(\\lambda())\\). Equally also possible add shared latent spatial effects Gaussian fields (approximated stochastic partial differential equation (SPDE)) model, assuming shared factors - biases - affecting datasets. See Engine comparison overview engines support level integration.","code":"# Define a model mod1 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>      # A presence only dataset       add_biodiversity_poipo(virtual_species,field_occurrence = \"Observed\") |>       # A Presence absence dataset       add_biodiversity_poipa(virtual_pseudoabs,field_occurrence = \"Observed\") |>       # Use inlabru for estimation and default parameters.     # INLA requires the specification of a mesh which in this example is generated from the data.       engine_inlabru() |>    # Train   train(runname = \"Combined prediction\", only_linear = TRUE,         method_integration = \"predictor\")  # The resulting object contains the combined prediction with shared coefficients among datasets. plot(mod1) # Note how an overall intercept as well as separate intercepts for each dataset are added. summary(mod1) #> # A tibble: 11 × 8 #>    variable                   mean      sd      q05     q50    q95    mode   kld #>                                          #>  1 Intercept               -0.325  25.8    -4.28e+1 -0.325  42.1   -0.325      0 #>  2 Intercept_species.._po… -0.325  25.8    -4.28e+1 -0.325  42.1   -0.325      0 #>  3 Intercept_species.._po… -0.325  25.8    -4.28e+1 -0.325  42.1   -0.325      0 #>  4 bio01_mean_50km         -0.101   0.133  -3.20e-1 -0.101   0.119 -0.101      0 #>  5 bio03_mean_50km         -0.436   0.120  -6.34e-1 -0.436  -0.239 -0.436      0 #>  6 bio19_mean_50km          0.475   0.0865  3.33e-1  0.475   0.617  0.475      0 #>  7 CLC3_112_mean_50km       0.373   0.0488  2.92e-1  0.373   0.453  0.373      0 #>  8 CLC3_132_mean_50km       0.0726  0.0456 -2.35e-3  0.0726  0.148  0.0726     0 #>  9 CLC3_211_mean_50km       0.911   0.0784  7.82e-1  0.911   1.04   0.911      0 #> 10 CLC3_312_mean_50km       0.991   0.0662  8.82e-1  0.991   1.10   0.991      0 #> 11 elevation_mean_50km      0.0122  0.0863 -1.30e-1  0.0122  0.154  0.0122     0"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"load-relevant-packages-and-testing-data","dir":"Articles","previous_headings":"","what":"Load relevant packages and testing data","title":"Creating biodiversity projections","text":"purpose example loading testing data species distributions well contemporary future predictors. Note names predictors used building distribution model consistent creating projections! ## Train model create future projection make use data loaded () first create species distribution model contemporary conditions (b) project obtained coefficients future using future predictors. guidance distribution models trained, see vignettes (1). scenario object can finally trained via project().","code":"# Load the packages library(ibis.iSDM) library(stars) library(xgboost) library(terra) library(igraph) library(ggplot2) library(ncdf4) library(assertthat)  # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE) # Background and biodiversity data background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM')) virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'points', quiet = TRUE)  # Note we are loading different predictors than in previous examples # These are in netcdf4 format, a format specific for storing spatial-temporal data including metadata. ll <- list.files(system.file(\"extdata/predictors_presfuture/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.nc\",full.names = TRUE)  # From those list of predictors are first loading the current ones as raster data # We are loading only data from the very first, contemporary time step for model fitting pred_current <- terra::rast() for(i in ll) suppressWarnings( pred_current <- c(pred_current, terra::rast(i, lyrs = 1) ) ) names(pred_current) <- tools::file_path_sans_ext( basename(ll) )  # Get future predictors # These we will load in using the stars package and also ignoring the first time step pred_future <- stars::read_stars(ll) |> stars:::slice.stars('Time', 2:86) st_crs(pred_future) <- st_crs(4326) # Set projection # Rename future predictors to those of current names(pred_future) <- names(pred_current)  # Plot the test data plot(pred_current['secdf'],      col = colorRampPalette(c(\"grey20\", \"orange\", \"lightgreen\", \"green\"))(10),      main = \"Share of secondary vegetation\") # Train model adding the data loaded above x <- distribution(background) |>    add_biodiversity_poipo(virtual_points, field_occurrence = 'Observed', name = 'Virtual points') |>    # Note that we scale the predictors here   add_predictors(pred_current, transform = 'scale',derivates = 'none') |>    engine_glmnet(alpha = 0)  #> Loaded glmnet 4.1-8  # Train the model modf <- train(x, runname = 'Simple PPM', verbose = FALSE)  # Add a threshold to this model by getting 05 percentile of values modf <- threshold(modf, method = 'percentile', value = 0.05)  # -- # # Now lets create a scenarios object via scenarios sc <- scenario(modf) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from the model object.   threshold()  # This creates a scenario object sc #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2100-01-01 (83.9 years) #>  ---------  #>   Threshold:      0.03 (percentile) #>  ---------  #>   Scenarios fitted: None # The object contains its own functions. See the scenarios help file for more information on  # what is possible with them names(sc) #>  [1] \"threshold\"            \"verify\"               \"t\"                    #>  [4] \"summary_beforeafter\"  \"summary\"              \"show\"                 #>  [7] \"set_simulation\"       \"set_predictors\"       \"set_data\"             #> [10] \"set_constraints\"      \"scenarios\"            \"save\"                 #> [13] \"rm_predictors\"        \"print\"                \"predictors\"           #> [16] \"plot_threshold\"       \"plot_relative_change\" \"plot_migclim\"         #> [19] \"plot_animation\"       \"plot\"                 \"modelobject\"          #> [22] \"modelid\"              \"mask\"                 \"limits\"               #> [25] \"initialize\"           \"get_timeperiod\"       \"get_thresholdvalue\"   #> [28] \"get_threshold\"        \"get_simulation\"       \"get_resolution\"       #> [31] \"get_projection\"       \"get_predictors\"       \"get_predictor_names\"  #> [34] \"get_model\"            \"get_limits\"           \"get_data\"             #> [37] \"get_constraints\"      \"get_centroid\"         \"constraints\"          #> [40] \"clone\"                \"calc_scenarios_slope\" \"apply_threshold\"      #> [43] \".__enclos_env__\" sc.fit1 <- sc |> project() # Note that an indication of fitted scenarios has been added to the object sc.fit1 #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2100-01-01 (83.9 years) #>  ---------  #>   Threshold:      0.03 (percentile) #>  ---------  #>   Scenarios fitted: Yes"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"summarizing-and-plotting-the-fitted-projections","dir":"Articles","previous_headings":"","what":"Summarizing and plotting the fitted projections","title":"Creating biodiversity projections","text":"distribution models number ways scenarios can visualized interacted : plot() makes visualization projections time steps (!) plot_relative_change() calculates change suitability area first last timestep categorizes result accordingly. Note SDMs directly infer colonization extinction, gains losses suitable habitat! calc_scenarios_slope() calculates slope (rate change) across timesteps. Useful summarizing results summary() creates summary output contained scenarios. threshold() specified, function summarize amount area timestep. get_data() gets created scenarios stars object (plus thresholds specified).      Finally, scenarios projections can also saved specific outputs. , enabled via write_output() works just [BiodiversityScenario] objects, difference output can specified netCDF-4 file.","code":"# Plot all scenarios. With a large number of predictors this figure will be messy... plot(sc.fit1) # or sc.fit1$plot() # As an alternative, visualize the linear slope per grid cell and across all time steps o <- sc.fit1$calc_scenarios_slope(plot = TRUE) # Another option is to calculate the relative change between start and finish o <- sc.fit1$plot_relative_change(plot = TRUE) # We can also summarize the thresholded data o <- sc.fit1$summary() plot(area_km2~band, data = o, type = 'b',      main = \"Suitable habitat across Time\",      ylab = \"Amount of area (km2)\", xlab = \"Time\") # How does habitat gain and loss change over time? plot(totchange_gain_km2~band, data = o, type = 'n',      main = \"Habitat gain and loss\", ylim = c(-1.5e4, 1.5e4),      ylab = \"Amount of area (km2)\", xlab = \"Time\") lines(o$totchange_gain_km2~o$band, col = \"blue\") lines((o$totchange_loss_km2)~o$band, col = \"red\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"adding-constraints-to-projections","dir":"Articles","previous_headings":"","what":"Adding constraints to projections","title":"Creating biodiversity projections","text":"simple scenario use naive assumption , depending response functions fitted distribution model, suitable habitat within background modelling region potentially reachable species. reality might however geographic (e.g. islands), environmental biotic constraints far species can disperse. can specified constrain function [add_constraint()] variety constraints currently available, depend packages. add_constraint() Generic wrapper specific ‘method’ can supplied. See documentation information available options parameters. add_constraint_dispersal() add dispersal constraint projections applied time step. Supports various options 'sdd_fixed' fixed dispersal kernels, 'sdd_nexpkernel' negative exponential kernel 'sdd_kissmig' applying kissmig framework. add_constraint_MigClim() Use MigClim R-package simulate dispersal events time steps. number parameters required adding constrain also overwrite default plotting capacities (example via sc$plot_migclim()). See also help file Engler et al. (2012) information. add_constraint_connectivity() Add connectivity constrain projection. Currently hard barriers implemented, future additional sub-modules planned enable options . add_constraint_adaptability() Simple constraints adaptability species novel climatic conditions. Currently simple nichelimits implemented, ‘cap’ projections novel environments observed ranges contemporary predictors. add_constraint_boundary() Specifying hard boundary constraint projections, example limiting (future) projections certain area biome contemporary range. Lastly also options stabilize suitability projections via project() function. Specifying stabilization results projections smoothed informed incremental time steps. can particularly help projections use variables known make sudden, abrupt jumps time steps (e.g. precipitation anomalies).     Another option constraining prediction also imposing zonal limit (instance climatically defined) projections (see alternatively add_constraint_boundary() ). done fitting SDM reference conditions (see example limits (1) ) considered (future) projections.","code":"# Adding a simple negative exponential kernel to constrain the predictions sc.fit2 <- sc |>       add_constraint(method = \"sdd_nex\", value = 1e5) |>     # Directly fit the object    project(stabilize = F)  # Also fit one projection a nichelimit has been added sc.fit3 <- sc |>       add_constraint(method = \"sdd_nex\", value = 1e5) |>     add_constraint_adaptability(method = \"nichelimit\") |>     # Directly fit the object    project(stabilize = F)  # Note how constrains are indicated in the scenario object. sc.fit3 #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2100-01-01 (83.9 years) #>  ---------  #>   Constraints:    dispersal (sdd_nexpkernel), adaptability (nichelimit) #>   Threshold:      0.03 (percentile) #>  ---------  #>   Scenarios fitted: Yes  # The naive assumption is that there is unlimited dispersal across the whole background # Note how the projection with dispersal constrain results in a considerable smaller amount of suitable habitat. sc.fit1$plot(which = 40) # Baseline sc.fit2$plot(which = 40) # With dispersal constrain sc.fit3$plot(which = 40) # With dispersal limit and nichelimitation (within a standard deviation) # Lets compare the difference in projections compared to the naive one defined earlier.  o1 <- sc.fit1$summary() o2 <- sc.fit2$summary() o3 <- sc.fit3$summary() arlim <- c(min(o1$area_km2, o2$area_km2, o3$area_km2)-10000,            max(o1$area_km2, o2$area_km2, o3$area_km2))  plot(area_km2~band, data = o1, type = 'n',      ylim = arlim,      main = \"Suitable habitat projection\",      ylab = \"Amount of area (km2)\", xlab = \"Time\") lines(o1$area_km2~o1$band, col = \"black\", lty = 1) lines(o2$area_km2~o2$band, col = \"black\", lty = 2) lines(o3$area_km2~o3$band, col = \"black\", lty = 3) legend(\"bottomleft\",    legend = c(\"Unlimited dispersal\", \"Constrained dispersal\",              \"Constrained dispersal and niche limit\"),    lty = c(1, 2, 3),   cex = 1.2,   bty = \"n\") # Lastly it is also possible to directly summarize the state  # before (usually first year) and end (last year). sc.fit2$summary_beforeafter() #> # A tibble: 13 × 5 #>    runname    category                  period       value unit       #>                                              #>  1 Simple PPM Current range             2016-01-01 432.    ha         #>  2 Simple PPM Future range              2100-01-01 417.    ha         #>  3 Simple PPM Unsuitable                84 years   190.    ha         #>  4 Simple PPM Loss                      84 years    15.7   ha         #>  5 Simple PPM Gain                      84 years     0.693 ha         #>  6 Simple PPM Stable                    84 years   416.    ha         #>  7 Simple PPM Percent loss              84 years     3.64  %          #>  8 Simple PPM Percent gain              84 years     0.160 %          #>  9 Simple PPM Range change              84 years   -15.0   ha         #> 10 Simple PPM Percent change            84 years    -7.31  %          #> 11 Simple PPM Sorensen index            84 years     0.983 similarity #> 12 Simple PPM Centroid distance         84 years    20.9   km         #> 13 Simple PPM Centroid change direction 84 years    15.4   deg"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"specific-parsers-for-globiom-related-scenarios","dir":"Articles","previous_headings":"","what":"Specific parsers for GLOBIOM related scenarios","title":"Creating biodiversity projections","text":"IIASA’s Global Biosphere Management Model (GLOBIOM) partial equilibrium model used analyze competition land use agriculture, forestry, bioenergy, main land-based production sectors. builds . ibis.iSDM part IIASA’s suite integrated models, direct link available make use downscaled GLOBIOM outputs. Implemented functions either directly format data via [formatGLOBIOM()] add DistributionModel-class BiodiversityScenario-class object directly via add_predictors_globiom() .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"mechanistic-species-distribution-modelling","dir":"Articles","previous_headings":"","what":"Mechanistic species distribution modelling","title":"Mechanistic species distribution modelling","text":"vignette describes available options incorporating mechanistic modelling approaches ibis.iSDM package. approaches can broadly separated “added” existing modelling routines, ibis.iSDM outputs can used input mechanistic modelling. package provides basic wrappers. delve options mechanistic SDMs ibis.iSDM package, useful remind us term ‘mechanism’ actually means. literature range different definitions, sometimes referring mechanistic SDMs incorporate ecological processes (e.g. demography, dispersal, eco-evolutionary principles). Yet often, correlative SDMs also declared “mechanistic” somehow incorporate specific constrain response function towards environmental variable. example, micro-climatic limits persistence species Briscoe et al. 2023, presence biotic interactions (estimated separate SDM different species) also sometimes referred limiting mechanisms (Ohlmann et al. 2023). latter approaches - largely fine-tuning specific response function - can extent emulated creating specific derivates adding covariate priors (add_priors()) model predictors (add_predictors_model()) SDM. methods added package become available can readily incorporated modelling framework. types integration can also directly modelled integration. details provided vignettes data preparation creating derivates vignette data integration. Users package also directed various add_constraint() functions, many enable corrections projected scenarios.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"adding-ecological-processes-to-correlative-sdms","dir":"Articles","previous_headings":"Mechanistic species distribution modelling","what":"Adding ecological processes to correlative SDMs","title":"Mechanistic species distribution modelling","text":"range wrappers implemented ibis.iSDM allow convenient passing outputs parameters mechanistic modelling packages. wrappers support convenient addition ecological processes dispersal scenarios data integration. enable ibis.iSDM outputs directly become inputs simulations. case key parameters available, package users encouraged check various options add_constraint() function. mechanistic approaches require quite extensive model understanding many cases additional training. Furthermore range parameters usually required outputs meaningful. beyond scope vignette provide introduction various models. Rather, demonstrated linkages ibis.iSDM models can made, reader referred original publication underlying approach (see help page references).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"adding-dispersal-to-scenarios-with-kissmig","dir":"Articles","previous_headings":"Mechanistic species distribution modelling > Adding ecological processes to correlative SDMs","what":"Adding dispersal to scenarios with KISSMig","title":"Mechanistic species distribution modelling","text":"KISSMig model provide simple model estimate limit dispersal species distribution models (Nobis & Normand, 2014). include ecological mechanism related recruitment , instead works simple stochastic migration estimator allows inclusion time-lagged dispersal local neighborhoods. ibis.iSDM package KISSMig simulator can added dispersal constraint (among others) scenario objects. Example:  Now lets add KISSMig dispersal constraints. constrain directly used fitted suitability estimates projected timestep also makes use created thresholded layer. Per time-step dispersal events stochastically simulated constraint range expansions next modelling steps. See ?kissmig::kissmig help-page help explanations parameters.","code":"library(ibis.iSDM) library(terra) #> terra 1.7.65 library(ggplot2) # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE)  # Background and biodiversity data background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM')) virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'points', quiet = TRUE) # Add some pseudo-absence information for later poa <- virtual_points |> add_pseudoabsence(field_occurrence = 'Observed',                                            template = background)  # Note we are loading different predictors than in previous examples # These are in netcdf4 format, a format specific for storing spatial-temporal data including metadata. ll <- list.files(system.file(\"extdata/predictors_presfuture/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.nc\",full.names = TRUE)  # From those list of predictors are first loading the current ones as raster data # We are loading only data from the very first, contemporary time step for model fitting pred_current <- terra::rast() for(i in ll) suppressWarnings( pred_current <- c(pred_current, terra::rast(i, lyrs = 1) ) ) names(pred_current) <- tools::file_path_sans_ext( basename(ll) )  # Get future predictors # These we will load in some time steps using the stars package and ignoring the first time step suppressWarnings( pred_future <- stars::read_stars(ll) |> stars:::slice.stars('Time', seq(2,86,by=10)) ) sf::st_crs(pred_future) <- sf::st_crs(4326) # Set projection # Rename future predictors to those of current names(pred_future) <- names(pred_current)  # ------ # # Fit a model fit <- distribution(background) |>    add_biodiversity_poipa(poa, field_occurrence = 'Observed', name = 'Virtual points') |>    # Note that we scale the predictors here   add_predictors(pred_current, transform = 'scale',derivates = 'none') |>    engine_glmnet(alpha = 0) |>    # Train the model   train(verbose = FALSE) |>    # Add simple percentile thresholds   threshold(method = 'percentile', value = .33)  # Show the threshold fit$plot_threshold() # Create a scenario object sc <- scenario(fit) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from    # the fitted model object.   threshold()     # Add KISSMig constraint sc1 <- sc |>    add_constraint_dispersal(method = \"kissmig\",                            type = \"DIS\", # Final distribution result                            value = 10, # Number of iteration steps                            # These parameters are for KISSMig and get passed on                            # Probablitiy of local extinction between iterations                            pext = 0.5,                            # Probability corner cells are colonized.                            pcor = 0.2                            )  sc2 <- sc |>    add_constraint_dispersal(method = \"kissmig\",                            type = \"DIS\", # Final distribution result                            value = 10, # Number of iteration steps                            # These parameters are for KISSMig and get passed on                            # Probablitiy of local extinction between iterations                            pext = 0.9,                            # Probability corner cells are colonized.                            pcor = 0.1                            )  # Project two scenarios with varying local extinction probability df1 <- project(sc1, verbose = FALSE) |> summary() #> Linking to GEOS 3.10.2, GDAL 3.4.1, PROJ 8.2.1; sf_use_s2() is FALSE df2 <- project(sc2, verbose = FALSE) |> summary() df <- dplyr::bind_rows(df1 |> dplyr::mutate(scenario = \"low\"),                        df2 |> dplyr::mutate(scenario = \"high\") ) # ------ # ggplot(df, aes(x = band, y= area_km2/1e6,                group = scenario, color = scenario)) +   theme_bw(base_size = 16) +   geom_line() +   labs(x = \"Time\", y = \"Occupied area (Million km2)\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"adding-dispersal-to-scenarios-with-migclim","dir":"Articles","previous_headings":"Mechanistic species distribution modelling > Adding ecological processes to correlative SDMs","what":"Adding dispersal to scenarios with MIGCLIM","title":"Mechanistic species distribution modelling","text":"Another dispersal simulator MIGCLIM (Engler et al. 2014), stochastic simulator innovatively allows differentiate short long-distance dispersal events well varying propagule pressure. Unfortunately currently available CRAN anymore (stand September 2023), possibly lack maintenance missing dependency. package can still downloaded github however (https://github.com/robinengler/MigClim/). Assuming user able install MigClim package ’s dependencies (also disappared CRAN), can run ibis.iSDM follows: example updated update current R versions (>3.0) becomes available.","code":"prj <- scenario(fit) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from    # the fitted model object.   threshold() |>  # Check the help files for the function for an explanation of the parameters.   add_constraint_MigClim(rcThresholdMode = 'continuous',                          dispSteps = 1,                          dispKernel = c(1.0, 0.4, 0.16, 0.06, 0.03),                          barrierType = \"strong\",                          lddFreq = 0, lddRange = c(1000, 10000),                          iniMatAge = 1, propaguleProdProb = c(0.2, 0.6,0.8, 0.95),                          replicateNb = 10) |>    # Project the model   project()  # MIGCLIM outputs are provided a single updated layer and can be plotted through # a customized plotting function. prj$plot_migclim()"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"simulating-spatial-explicit-population-abundance-with-steps","dir":"Articles","previous_headings":"Mechanistic species distribution modelling > Adding ecological processes to correlative SDMs","what":"Simulating spatial-explicit population abundance with steps","title":"Mechanistic species distribution modelling","text":"steps package implements spatial-temporal explicit metapopulation simulator (Visintin et al. 2021) able account varying vital rates, dispersal barriers density dependence. steps simulator, thus makes use range parameters critical correlative assumptions estimate example abundance given time step. ibis.iSDM package linkage steps can established directly scenario projections simply adding separate module. added, steps used make spatial-temporal abundance estimates aligned projection time step, eventual specified barriers provided parameters regards vital rates density-dependence. Note: wrapper functionality implemented ibis.iSDM package based assumption higher habitat suitability (estimated correlative SDM) linearly correlated higher population abundance. noted assumptions questioned interpreted caution (Lee-Yaw et al. 2021). Users always clearly understand rationale behind parameter choices!","code":"require(\"steps\") #> Loading required package: steps  # Define some arbitrary vital rates for the transition for this purpose # Define vital rates vt <- matrix(c(0.0,0.52,0.75,               0.52,0.28,0.0,               0.0,0.52,0.75),               nrow = 3, ncol = 3, byrow = TRUE) colnames(vt) <- rownames(vt) <- c('juvenile','subadult','adult')  # We again specify a scenario as before using the fitted model prj <- scenario(fit) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from    # the fitted model object.   threshold() |>    # We then specify that we we    simulate_population_steps(vital_rates = vt)  # Notice how we have added steps as additional simulation outcome prj #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2096-01-01 (79.9 years) #>  ---------  #>   Threshold:      0.519 (percentile) #>   Simulations:    simulation (steps) #>  ---------  #>   Scenarios fitted: None # Now project scenario1 <- project(prj) plot(scenario1, \"population\") # Also see a different one where we add a dispersal constraint and density dependence dispersal <- steps::fast_dispersal(dispersal_kernel = steps::exponential_dispersal_kernel(distance_decay = 1)) scenario2 <- project(prj |>                        simulate_population_steps(vt,                                                  dispersal = dispersal,                                                  density_dependence = steps::ceiling_density(3) ) )  # We can see that the dispersal constraint and higher density dependence cleary # results in a population abundance that tends to be concentrated in central Europe. plot(scenario2, \"population\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/06_engine_comparison.html","id":"capabilities-of-included-engines","dir":"Articles","previous_headings":"","what":"Capabilities of included engines","title":"Comparison of different engines","text":"outlined Fletcher et al. (2019), many different forms integration [ensemble] modelling, adding [offsets], predictors (e.g. [add_predictor_range()] ) [priors] full integration different likelihoods (See (Data integration) ). options available every engine supported ibis.iSDM package table shows currently implemented engines various types integrations supported . Stating name function call engine supported model complexity linear (ln) non-linear (nl) formulations, although noted linear models can approximate non-linearity including transformations (Maxent, e.g. hinge/product/quadratic). every engine supports different types integration via ensembles, offsets, priors, joint likelihood estimation ensemble compositing models using separate datasets species. multiple biodiversity datasets added engine support joint likelihood estimation, parameter method_integration [train()] determines different predictions integrated. Available options integration via predictors, offsets, interactions, priors weights (see help file [train()] information).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/07_package_comparison.html","id":"comparison-with-other-packages","dir":"Articles","previous_headings":"","what":"Comparison with other packages","title":"Capabilities compared to other SDM packages","text":"Species distribution modelling (SDM) approaches around quite result number ecological modelling focused packages developed. general customized towards specific purposes modelling paradigm. isn’t just another SDM package? Indeed , ibis.iSDM number particular features set apart SDM packages: focuses particularly integration guiding principle different ways heterogeneous sources evidence can integrated. puts strong focus biodiversity types, particular Poisson-Process models (PPMs) default way analyzing presence-data. follows object-based modular programming philosophy, taking inspiration tidy programming approaches. supports number Bayesian SDM approaches algorithms, field traditionally less represented owing computational constraints. customized create modify spatio-temporal scenarios, including IIASA integrated land-use assessment model GLOBIOM. Thus overall, idea package part trying bring innovation SDM modelling world, also trying bring together strengths different existing tools. Non exhaustive list acknowledging SDM packages R compare ibis.iSDM provided : hSDM -> Bayesian framework hierachical mixed models. Fast, little flexibility regards weights, offsets different datatypes. multispeciesPP -> Package allows integrated SDMs, however developed since years key gaps remain particular regards different modelling approaches. inlabru -> Package specifically Lox-Gaussian-Cox Process (LGCP) models INLA, now integrated also engine ibis.iSDM pointedSDMs -> Another wrapper INLA allows integrate different datasets SDM. Less focus priors, offsets scenarios. biomod2 -> Popular package ensemble modelling, fixed specific (non-Bayesian) engines data types integration options. sdmTMB -> Package fitting spatial-Temporal SDMs specific biodiversity data. modleR -> similar biomod2 wrapper construct ensembles models. kuenm -> Another wrapper Maxent. flexSDM Similar biomod2 wrapper SDMs, coming several helper functions data preparation cross-validation. Besides SDMs also new packages available spatial integrated species occupancy models, spOccupancy. Occupancy modelling however requires specific biodiversity data information infer detectability species occurrences.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"frequently-asked-questions-faq","dir":"Articles","previous_headings":"","what":"Frequently Asked Questions (FAQ)","title":"Frequently Asked Questions (FAQ)","text":"document contains series frequently asked questions using ibis.iSDM package work progress.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"data-and-model-preparation","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Data and model preparation","title":"Frequently Asked Questions (FAQ)","text":"ibis.iSDM R-package can handle standard spatial formats R (vector raster formats) works predominantly [sf], [SpatRaster] [stars] packages much formatting processing work. adding [biodiversity] [predictor] variables distribution() object number default validity checks alignments commonly conducted, instance ensuring provided points align geographic projection. ease modelling avoid unfortunate errors crashes, ideally ensure following steps taken: 'background' layer describing modelling extent provided directly [sf] 'POLYGON' 'MULTIPOLYGON' object covers biodiversity predictor data. provided data geographic projection. Biodiversity data provided [sf] format covers 'background' bounding box. Furthermore biodiversity dataset set \"field_occurrence\" field numeric values. appropriately formatted (see also ). Important: environmental predictors becomes important ensure nodata values appropriately handled. Unfortunately many implemented [engines] can handle nodata values well, thus necessary pre-processing remove rows covariate extraction least one variable missing data. instance assinging constant NA values: Technically, impossible estimate probability occurrence just presence-data (commonly available databases like GBIF). people normally add called pseudo-absence (often excessive numbers) entire background data, approximating probability occurrence assuming detection probability uniform landscape (see Merow et al. 2013). ibis.iSDM package follows design principle data types (e.g. presence-presence-absence records) modelled least amount assumptions possible. presence-records default way estimating kind responses habitat suitability estimate data following Poisson-Process modelling approach. However, possible add pseudo-absence points presence-dataset follows: Also see add_pseudoabsence() pseudoabs_settings() help pages settings also first article website. example possible define pseudo-absence sampling specific spatial formats, sampling within outside minimum convex polygon (MCP) presence points within certain buffer. Yes, ibis.iSDM package uses range different functionalities , existing packages functions required specific purpose, packages question installed. easy convenience functions install packages ibis_dependencies() installs packages listed getOption(\"ibis.dependencies\").","code":"predictors[is.na(predictors)] <- 0 virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'points',quiet = TRUE) # This takes the default pseudo-absence options created when loading the Ibis package. virtual_points <- add_pseudoabsence(virtual_points, field_occurrence = \"Observed\") # Check that absence points are present unique(virtual_points$Observed)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"model-setup","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Model setup","title":"Frequently Asked Questions (FAQ)","text":"Yes, can desirable outcome modelling. instance one can make - absence better information dispersal constrain (see [add_constrain_dispersal]) - assumption certain species can disperse within given ecoregion beyond. See instance method section Wessels, Merow Trisos (2021). directly ibis.iSDM R-package, one specify limit projection [distribution()] object. context zones extent whole background (extent spatial scale). prediction however limited zones supplied biodiversity observations fall . dedicated function ([create_zonaloccurrence_mask()]) help set zones, either taking existing categorical raster datasets constructing buffers around existing presence records (example reflect assumed maximum dispersal distances). ibis.iSDM R-package allows users add prior information parameters model estimated. priors added engine-specific priors format depends engine question (see specific help pages information). prior can generally define via combination ENGINENAME + Prior wrapped PriorList used estimation. Example: Multiple priors Engine can defined PriorList. Whenever prior variable set , overwrites previous value. great number SDM literature suggests altering background / pseudo-absence points created, can greatly affect model outcomes (see add_pseudoabsence() references). ibis.iSDM R-package options available modify pseudo-absence points created. default package creates least 10 000 points least 25% presence-points (ever larger). change default pseudo-absence sampling settings, two options. Either change global default settings pseudo-absence sampling adding settings add_biodiversity function. overwrite global settings, following: Alternatively one think specifying specific pseudo-absence sampling information one biodiversity dataset specifically: code ibis.iSDM R-package default already parallelized many computationally-intensive operations making use cores (can find example case, please raise issue). number cores generally decided option \"ibis.nthread\" [ibis_options()]. cases, parallelized code run via [parallel] [doParallel] packages, although code infancy support [future] parallelization approaches well, offering greater flexibility. See function [ibis_future] information also use. typical use case thus run separate models (via train()) loop scheduler High-Performance-Computer. Users careful case shared resources, e.g. don’t parallelize operations machine. need parallelize multiple models instance, suggested disable 'ibis.runparallel' option. Yes. add_offset() add_offset_range() functions allows specify spatial explicit offset term added regression model question. offset generally just coefficient set specific value. get one offset, one just needs combine different provided offsets way consistent get fixed value (see reference. can done either summing transformed value (discouraged can errorprone) simply multiplying . Internally provided offsets model object combined via simple addition together. thus requires users transform aprior (instance log transform) adding estimation.","code":"# Where zone is a provided raster mod <- distribution(background, limits = zone) |>     add_biodiversity_poipo(species_data) |>     engine_gdb() |>     train() plot(mod)  # Alternatively one can also create such limits based on a minimum convex polygon # of the provided data. Here we create a non-buffered MCP across all points used # in species_data to constrain the prediction. mod <- distribution(background, limits_method = \"mcp\", mcp_buffer = 0) |>     add_biodiversity_poipo(species_data) |>     engine_gdb() |>     train() plot(mod) # We have prior information that 'Forest' is important for a species # In this case and for the INLA engine we define normal prior on the mean and precision p <- INLAPrior(variable = \"Forest\",type = \"normal\",hyper = c(2, 10)) # This is then wrapped in a PriorList pp <- priors(p) print( pp )  # We can specify multiple priors of course p <- list(   INLAPrior(variable = \"Forest\",type = \"normal\",hyper = c(2, 10)),   INLAPrior(variable = \"Cropland\",type = \"normal\",hyper = c(0, 1)) ) pp <- priors(pp)  # And can now added to the model mod <- distribution(background, limits = zone) |>     add_biodiversity_poipo(species_data) |>     add_predictors(covariates) |>     add_priors(priors = pp)   engine_inlabru() # Define new settings with greater number of background points ss <- pseudoabs_settings(background = NULL, nrpoints =  1e6) # Overwrite the default settings options(\"ibis.pseudoabsence\" = ss) # Define absence layer with biased background to sample from ss <- pseudoabs_settings(background = NULL, bias = bias_layer)  # Assuming background and point data exists x <- distribution(background) |>     add_biodiversity_poipo(points, pseudoabsence_settings = ss) # Check ibis options if set ibis_options() options('ibis.runparallel' = FALSE) # Set to FALSE offset1 <- runif(10) offset2 <- runif(10) # Identical log(offset1) + log(offset2) log(offset1*offset2)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"fitting-and-scenarios","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Fitting and Scenarios","title":"Frequently Asked Questions (FAQ)","text":"two options can enabled reduce number messages: setting parameter verbose train() FALSE messages created respective engine suppressed. Setting parameter ibis.setupmessages FALSE suppresses package related message. can done via Cross-validation deliberatly integrated package. Users like make use cross-validation techniques thus need set external modelling routines. Reason multiple types integration package, construction (independent) testing datasets trivial (considering example offsets, priors multiple datasets). ibis.iSDM R-package two engines makes use INLA framework, namely [engine_inla] [engine_inlabru]. package author started developing package, [engine_inlabru] yet support multiple likelihoods thus implemented directly. Predictions [engine_inla] [engine_inlabru] identical, although latter infer predictions directly, instead simulating posterior. simulation particularly helpful creating (future) projections otherwise new model need fitted every newdata object. creating predictive models SDMs often concern predict variable range outside environmental conditions model trained. ibis.iSDM package supports variable ‘clamping’ predictions similar popular Maxent model, however [engine]. Clamping can enabled setting parameter clamp [train] TRUE. restricts spatial (spatial-temporal) projections combined range predictor variables observed training localities. Similar functionalities also available separately scenario projections setting adaptability constraints (see [add_constraint_adaptability] [add_constraint_boundary]). many predictors SDM can cause substantial -parametrization subsequently overfitting (e.g. model reproducing data trained rather projecting areas unknown). recommended () either use engine strong regularization, example [engine_glmnet] [engine_gdb], (b) train model caution minimum number observations (arbitrary rule thumb, least 10 observations additional predictor included), (c) make use pre-estimation removal predictor, example variable importance criteria colinearity. See code example. distribution model trained inference_only parameter train() set FALSE (Default), outputs prediction found created object SpatRaster. default engines produce SpatRaster object least one band called “mean” average prediction engine. also result returned created model object plotted. addition, Bayesian Engines bands quantifying posterior predictive uncertainty might available can plotted well. raster can also saved spatial GeoTiff given filename using write_output() function. Example: usually due either number rounds estimation low learning_rate high. Try different options parameters engine. good way check performance also plot evaluation log logloss.","code":"options(\"ibis.setupmessages\" = FALSE) # Prior to model fitting, remove highly collinear predictors through a pearson correlation assessment mod <- distribution(background) |>     add_biodiversity_poipo(species_data) |>     engine_glmnet() |>     train(filter_predictors = \"pearson\")  # Alternatively use a RandomForest estimator to remove the least important variables mod <- distribution(background) |>     add_biodiversity_poipo(species_data) |>     engine_glmnet() |>     train(filter_predictors = \"RF\") mod <- distribution(background) |>     add_biodiversity_poipo(species_data) |>     engine_inlabru() |>     train() # To plot  plot(mod, \"mean\") plot(mod, \"sd\")  # To get the layer mod$get_data(\"prediction\")  # To save the output layer as floating point geoTiff write_output(mod, \"myoutput.tif\", type = \"gtif\", dt = \"FLT4S\") # Requires a fitted model plot(fit$get_data(\"fit_best\")$evaluation_log)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"model-troubleshooting","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Model troubleshooting","title":"Frequently Asked Questions (FAQ)","text":"various forms integration simple approach adding [ensembles], [priors] [offsets] fully integrated multiple likelihood models (see Fletcher et al. 2019). Thus, users range possibilities combine different sources evidence modelling. regards different [engines] treat multiple biodiversity datasets. Unfortunately [engine_inla()], [engine_inlabru()] [engine_stan()] support fully integrated multiple likelihood models. full overview can found Engine comparison table. [engines] combine multiple datasets running separate models sequence order determined sequence datasets added model. Within train() function, users option specifying previous predictions handled [method_integration] parameter. example predictions one model added predictors offset next. coefficients one model can used create starting priors next model. default, presence biodiversity data modelled point-process model (PPM, see Renner et al. 2015). Similar Maximum Entropy models models can quite sensitive biased input, common non-structured biodiversity observations presence points tend clustered urban easily accessible areas. avoid predictions biased towards covariates, number things can potentially done . Modify targeted background sampling better control background points. can instance done via add_pseudoabsence() pseudoabs_settings() methods. See respective help files. Make use spatial thinning approaches. See instance Aiello-Lammers et al. 2015 Steen et al. 2021. Note however spatial thinning remove data points, affecting instance poisson distributed models (PPMs) process. Theibis.iSDM package functionality spatial thinning implemented thin_observations() function. Partial biased variable prediction. add_control_bias() function can used specify value needs partialed model. bias_value specified can set instance 0 amount assumed equivalent minimal bias. Consider setting [clamp] parameter train() TRUE. Add spatial offset account bias introduced Merow et al. 2016. can done via add_offset_bias() function requires preparation bias layer advance. Apply rigorous filtering bias control input data. end correction can replace good data preparation cleaning. Remember GIGO principle.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"any-other-questions-and-issues","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Any other questions and issues","title":"Frequently Asked Questions (FAQ)","text":"Often easier communicate index suitability (scale [0-1]) stakeholders policy, can principle derived ibis.iSDM output. Especially using Poisson Process models infer suitability given area, units can hard interpret non-scientists. easy way achieve added function Biodiversity distribution object. See example. feature, bug ;) Many covariates often come unusual characters symbols can readily used equations queries tabular data. sanitize_names() function cleans variable names removes / resets non conform symbols.","code":"# Train a model fit <- distribution(background) |>    # Presence-absence data   add_biodiversity_poipo(my_gbifpoints) |>    add_predictors(predictors) |>    engine_glmnet() |>    train()  # Make a transformed prediction of the suitability layer # The output is a normalized prediction surface  # created via (x - min) / (max - min) or x/sum(x) respectively pred <- fit$calc_suitabilityindex() # It can be disabled by setting the following option to false at the start of the script. options('ibis.cleannames' = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/contributing.html","id":"contributing-to-development-of-the-ibis-isdm-r-package","dir":"Articles","previous_headings":"","what":"Contributing to development of the ibis.iSDM R-package","title":"Contributing to the Package development","text":"welcome contributions ibis.iSDM R-package. contributions simple typo fixes, additions documentation testthat tests, enhancing vignettes provide greater understanding package, completely new functions. latter, please get touch package author one maintainers first. Pull requests master branch require confirmation code review package maintainers.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/contributing.html","id":"development-guidelines","dir":"Articles","previous_headings":"Contributing to development of the ibis.iSDM R-package","what":"Development guidelines","title":"Contributing to the Package development","text":"ibis.iSDM contains primarily functions fitting models. Speed flexibility key Don’t repeat . Create new functions necessary classes. Equally try reuse common names R, e.g. plot, summary Please run code checks tests regularly. Avoid using additional package dependencies possible. Comment code!! Use assertions verify inputs functions. bored, please write unit tests ensure evaluate (CRTL+SHIFT+T)! (also see issues projects) open issues","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Martin Jung. Author, maintainer, copyright holder. Maximilian H.K. Hesselbarth. Contributor.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Jung, M. (2023). integrated species distribution modelling framework heterogeneous biodiversity data. Ecological Informatics, 102127. Jung, M., Hesselbarth, H.K.M. (2023). integrated species distribution modelling framework heterogeneous biodiversity data. R package version 0.0.5","code":"@Article{,   title = {An integrated species distribution modelling framework for heterogeneous biodiversity data},   author = {Martin Jung},   journal = {Ecological Informatics},   volume = {76},   year = {2023},   pages = {102127},   url = {https://doi.org/10.1016/j.ecoinf.2023.102127}, } @Misc{,   title = {An integrated species distribution modelling framework for heterogeneous biodiversity data},   author = {Martin Jung and Maximilian H.K. Hesselbarth},   year = {2023},   version = {0.0.9}, }"},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"the-ibis-framework---an-integrated-model-for-biodiversity-distribution-projections","dir":"","previous_headings":"","what":"A R-package for Integrated Biodiversity distribution modelling","title":"A R-package for Integrated Biodiversity distribution modelling","text":"ibis.iSDM package provides series convenience functions fit integrated Species Distribution Models (iSDMs). integrated models generally refer SDMs incorporate information different biodiversity datasets, external parameters priors offsets respect certain variables regions. See Fletcher et al. (2019) Isaac et al. (2020) introduction iSDMs.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"A R-package for Integrated Biodiversity distribution modelling","text":"latest version can installed GitHub. CRAN release planned, meantime package can found R-universe well.","code":"# For installation (Not yet done) install.packages(\"ibis.iSDM\", repos = \"https://iiasa.r-universe.dev\")  # For Installation directly from github install.packages(\"remotes\") remotes::install_github(\"IIASA/ibis.iSDM\")"},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"basic-usage","dir":"","previous_headings":"","what":"Basic usage","title":"A R-package for Integrated Biodiversity distribution modelling","text":"See relevant reference site articles. Note package active development parameters functions might change. Citation: Jung, Martin. 2023. “Integrated Species Distribution Modelling Framework Heterogeneous Biodiversity Data.” Ecological Informatics, 102127, DOI","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"acknowledgement-","dir":"","previous_headings":"","what":"Acknowledgement","title":"A R-package for Integrated Biodiversity distribution modelling","text":"ibis.iSDM developed maintained Biodiversity, Ecology Conservation group International Institute Applied Systems Analysis (IIASA), Austria.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"contributors","dir":"","previous_headings":"","what":"Contributors","title":"A R-package for Integrated Biodiversity distribution modelling","text":"contributions project gratefully acknowledged using allcontributors package following -contributors specification. Contributions kind welcome!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a tree-based split probability prior for BART — BARTPrior","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"Function include prior information split probability Bayesian additive regression tree model added via engine_bart. Priors engine_bart specified transition probabilities variables internally used generate splits regression tree. Specifying prior can thus help 'enforce' split given variable. can numeric coded values 0 1.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"","code":"BARTPrior(variable, hyper = 0.75, ...)  # S4 method for character BARTPrior(variable, hyper = 0.75, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"variable character matched existing predictors latent effects. hyper numeric object number >0 equal 1. Defaults 0.75. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"Even given variable included split regression classification tree, necessarily mean prediction changes value non-informative (split can occur early ). however affect variable importance estimates calculated model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"Chipman, H., George, E., McCulloch, R. (2009) BART: Bayesian Additive Regression Trees. Chipman, H., George, E., McCulloch R. (2006) Bayesian Ensemble Learning. Advances Neural Information Processing Systems 19, Scholkopf, Platt Hoffman, Eds., MIT Press, Cambridge, MA, 265-272.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","title":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","text":"helper function specify several BARTPrior objects hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","text":"","code":"BARTPriors(variable, hyper = 0.75, ...)  # S4 method for character BARTPriors(variable, hyper = 0.75, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","text":"variable character matched existing predictors latent effects. hyper numeric object number >0 equal 1. Defaults 0.75. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"Function include prior information via Zellner-style spike slab prior generalized linear models used engine_breg. priors similar horseshoe priors used regularized engine_stan models penalize regressions assuming predictors effect 0.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"","code":"BREGPrior(variable, hyper = NULL, ip = NULL)  # S4 method for character BREGPrior(variable, hyper = NULL, ip = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"variable character matched existing predictors. hyper numeric estimate mean regression coefficients. ip numeric estimate 0 1 inclusion probability target variable (Default: NULL).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"Zellner-style spike slab prior generalized linear models specified described Boom R-package. Currently supported two options work models Poisson binomial (Bernoulli) distributed errors. Two types priors can provided variable: \"coefficient\" Allows specify Gaussian priors mean coefficients model. Priors coefficients can provided via \"hyper\" parameter. Note variables prior can still regularized model. \"inclusion.probability\" vector giving prior probability inclusion specified variable. can useful prior information preference known strength . coefficients set, inclusion probability also modified default. However even knowing particular estimate beta coefficients direction, one can still provide estimate inclusion probability. words: hyperparameters 'hyper' 'ip' NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"Hugh Chipman, Edward . George, Robert E. McCulloch, M. Clyde, Dean P. Foster, Robert . Stine (2001), \"Practical Implementation Bayesian Model Selection\" Lecture Notes-Monograph Series, Vol. 38, pp. 65-134. Institute Mathematical Statistics.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"","code":"if (FALSE) { # Positive coefficient p1 <- BREGPrior(variable = \"forest\", hyper = 2, ip = NULL) p1 # Coefficient and direction unknown but variable def. important p2 <- BREGPrior(variable = \"forest\", hyper = NULL, ip = 1) p2 }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","title":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","text":"helper function specify several BREGPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","text":"","code":"BREGPriors(variable, hyper = NULL, ip = NULL)  # S4 method for character BREGPriors(variable, hyper = NULL, ip = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","text":"variable character matched existing predictors. hyper numeric estimate mean regression coefficients. ip numeric estimate 0 1 inclusion probability target variable (Default: NULL).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":null,"dir":"Reference","previous_headings":"","what":"BiodiversityDataset prototype description — BiodiversityDataset-class","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"BiodiversityDataset prototype description","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"name default name dataset character. id character unique id dataset. equation formula object containing equation dataset modelled. family family used dataset character. link link function used data character. type character type character. weight numeric containing custom weights per observation dataset. field_occurrence character name column name containing observations. data Contains observational data sf format. use_intercept logical flag whether intercepts included dataset. pseudoabsence_settings Optionally provided pseudoabsence settings.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"BiodiversityDataset$new() BiodiversityDataset$print() BiodiversityDataset$set_equation() BiodiversityDataset$get_equation() BiodiversityDataset$show_equation() BiodiversityDataset$get_id() BiodiversityDataset$get_type() BiodiversityDataset$get_column_occ() BiodiversityDataset$get_family() BiodiversityDataset$get_link() BiodiversityDataset$get_data() BiodiversityDataset$get_weight() BiodiversityDataset$show() BiodiversityDataset$get_observations() BiodiversityDataset$mask() BiodiversityDataset$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$new(   name,   id,   equation,   family,   link,   type,   weight,   field_occurrence,   data,   use_intercept,   pseudoabsence_settings )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"name default name dataset character. id character unique id dataset. equation formula object containing equation dataset modelled. family family used dataset character. link link function used data character. type character type character. weight numeric containing custom weights per observation dataset. field_occurrence character name column name containing observations. data Contains observational data sf format. use_intercept logical flag whether intercepts included dataset. pseudoabsence_settings Optionally provided pseudoabsence settings.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-set-equation-","dir":"Reference","previous_headings":"","what":"Method set_equation()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Set new equation writes formula","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$set_equation(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"x new formula object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-equation-","dir":"Reference","previous_headings":"","what":"Method get_equation()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get equation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_equation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"placeholder formula object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-show-equation-","dir":"Reference","previous_headings":"","what":"Method show_equation()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Function print equation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$show_equation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"message screen.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-id-","dir":"Reference","previous_headings":"","what":"Method get_id()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get Id within dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-type-","dir":"Reference","previous_headings":"","what":"Method get_type()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get type dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_type(short = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"short logical flag formatted shortform.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character type","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-column-occ-","dir":"Reference","previous_headings":"","what":"Method get_column_occ()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get field occurrence information","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_column_occ()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character occurence field","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-family-","dir":"Reference","previous_headings":"","what":"Method get_family()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get family","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_family()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character family dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-link-","dir":"Reference","previous_headings":"","what":"Method get_link()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get custom link function","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_link()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character family dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get data object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_data()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"sf object data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-weight-","dir":"Reference","previous_headings":"","what":"Method get_weight()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get weight","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_weight()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"numeric weights within dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Print input messages","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"message screen.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-observations-","dir":"Reference","previous_headings":"","what":"Method get_observations()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Collect info statistics number observations","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_observations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"numeric number observations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Convenience function mask input datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed mask","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":null,"dir":"Reference","previous_headings":"","what":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Acts container specified set BiodiversityDataset contained within. Functions provided summarize across BiodiversityDataset-class objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"can likely beautified .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"data list BiodiversityDataset objects. name default name collection character.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"BiodiversityDatasetCollection$new() BiodiversityDatasetCollection$print() BiodiversityDatasetCollection$show() BiodiversityDatasetCollection$get_types() BiodiversityDatasetCollection$get_names() BiodiversityDatasetCollection$set_data() BiodiversityDatasetCollection$get_data_object() BiodiversityDatasetCollection$get_data() BiodiversityDatasetCollection$get_coordinates() BiodiversityDatasetCollection$mask() BiodiversityDatasetCollection$rm_data() BiodiversityDatasetCollection$length() BiodiversityDatasetCollection$get_observations() BiodiversityDatasetCollection$get_equations() BiodiversityDatasetCollection$get_families() BiodiversityDatasetCollection$get_links() BiodiversityDatasetCollection$get_columns_occ() BiodiversityDatasetCollection$get_weights() BiodiversityDatasetCollection$get_ids() BiodiversityDatasetCollection$get_id_byType() BiodiversityDatasetCollection$get_id_byName() BiodiversityDatasetCollection$show_equations() BiodiversityDatasetCollection$plot() BiodiversityDatasetCollection$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$new()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$print(format = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"format logical flag whether message printed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Aliases calls print.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-types-","dir":"Reference","previous_headings":"","what":"Method get_types()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Types biodiversity datasets included ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_types(short = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"short logical flag whether types short format.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-names-","dir":"Reference","previous_headings":"","what":"Method get_names()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get names format necessary","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_names(format = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"format logical flag whether names formatted","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Add new Biodiversity dataset collection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"x character name id dataset. value BiodiversityDataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-data-object-","dir":"Reference","previous_headings":"","what":"Method get_data_object()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get specific Biodiversity dataset id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_data_object(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Returns BiodiversityDataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get biodiversity observations given dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_data(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Returns data set BiodiversityDataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-coordinates-","dir":"Reference","previous_headings":"","what":"Method get_coordinates()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get coordinates given biodiversity dataset. Else return wkt object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_coordinates(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"coordinates given object data.frame.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Convenience function mask input datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$mask(mask, inverse = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-rm-data-","dir":"Reference","previous_headings":"","what":"Method rm_data()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Remove specific biodiversity dataset id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$rm_data(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Number Biodiversity Datasets connection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"numeric number datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-observations-","dir":"Reference","previous_headings":"","what":"Method get_observations()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get number observations datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_observations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"numeric number observations across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-equations-","dir":"Reference","previous_headings":"","what":"Method get_equations()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get equations datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_equations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector equations across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-families-","dir":"Reference","previous_headings":"","what":"Method get_families()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get families datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_families()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector families across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-links-","dir":"Reference","previous_headings":"","what":"Method get_links()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get custom link functions","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_links()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector link functions across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-columns-occ-","dir":"Reference","previous_headings":"","what":"Method get_columns_occ()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get fields observation columns","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_columns_occ()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector names observation columns.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-weights-","dir":"Reference","previous_headings":"","what":"Method get_weights()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get weights across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_weights()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector weights set per dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-ids-","dir":"Reference","previous_headings":"","what":"Method get_ids()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get ids assets collection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_ids()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector ids datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-id-bytype-","dir":"Reference","previous_headings":"","what":"Method get_id_byType()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Search specific biodiversity dataset type","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_id_byType(type)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"type character given data type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character id(s) datasets given type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-id-byname-","dir":"Reference","previous_headings":"","what":"Method get_id_byName()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get id name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_id_byName(name)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"name character given name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character id(s) datasets given name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-show-equations-","dir":"Reference","previous_headings":"","what":"Method show_equations()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Show equations datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$show_equations(msg = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"msg logical whether use print message instead.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Shows equations screen character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Plot whole collection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$plot()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-12","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Biodiversity Distribution master class — BiodiversityDistribution-class","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Base R6 class biodiversity distribution objects. Serves container supplies data functions R6 classes. Generally stores objects parameters added model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Run names() distribution object show available functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"implemented yet. implemented yet.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"background SpatRaster sf object delineating modelling extent. limits optional sf object potential extrapolation limits biodiversity BiodiversityDatasetCollection object. predictors PredictorDataset object. priors optional PriorList object. control optional Control object. latentfactors character whether latentfactors used. offset character whether methods used. log optional Log object. engine Engine object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"BiodiversityDistribution$new() BiodiversityDistribution$print() BiodiversityDistribution$show() BiodiversityDistribution$name() BiodiversityDistribution$show_background_info() BiodiversityDistribution$set_limits() BiodiversityDistribution$get_limits() BiodiversityDistribution$rm_limits() BiodiversityDistribution$get_predictor_names() BiodiversityDistribution$set_latent() BiodiversityDistribution$get_latent() BiodiversityDistribution$rm_latent() BiodiversityDistribution$get_priors() BiodiversityDistribution$set_priors() BiodiversityDistribution$set_biodiversity() BiodiversityDistribution$set_predictors() BiodiversityDistribution$set_engine() BiodiversityDistribution$get_engine() BiodiversityDistribution$rm_engine() BiodiversityDistribution$get_prior_variables() BiodiversityDistribution$set_offset() BiodiversityDistribution$get_offset() BiodiversityDistribution$rm_offset() BiodiversityDistribution$plot_offsets() BiodiversityDistribution$get_offset_type() BiodiversityDistribution$set_control() BiodiversityDistribution$get_control() BiodiversityDistribution$rm_control() BiodiversityDistribution$plot_bias() BiodiversityDistribution$get_log() BiodiversityDistribution$set_log() BiodiversityDistribution$get_extent() BiodiversityDistribution$get_extent_dimensions() BiodiversityDistribution$get_projection() BiodiversityDistribution$get_resolution() BiodiversityDistribution$rm_predictors() BiodiversityDistribution$rm_priors() BiodiversityDistribution$show_biodiversity_length() BiodiversityDistribution$show_biodiversity_equations() BiodiversityDistribution$get_biodiversity_equations() BiodiversityDistribution$get_biodiversity_types() BiodiversityDistribution$get_biodiversity_ids() BiodiversityDistribution$get_biodiversity_names() BiodiversityDistribution$plot() BiodiversityDistribution$summary() BiodiversityDistribution$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Initializes object creates BiodiversityDataset default.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$new(background, limits, biodiversity, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"background SpatRaster sf object delineating modelling extent. limits optional sf object potential extrapolation limits biodiversity BiodiversityDatasetCollection object. ... objects","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Looks returns properties contained objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"alias print","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-name-","dir":"Reference","previous_headings":"","what":"Method name()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Returns self-describing name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-background-info-","dir":"Reference","previous_headings":"","what":"Method show_background_info()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Summarizes extent projection set background","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show_background_info()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-limits-","dir":"Reference","previous_headings":"","what":"Method set_limits()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Specify new limits background","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_limits(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x list object method limit type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-limits-","dir":"Reference","previous_headings":"","what":"Method get_limits()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get provided limits set waiver","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list waiver.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-limits-","dir":"Reference","previous_headings":"","what":"Method rm_limits()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove limits set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-predictor-names-","dir":"Reference","previous_headings":"","what":"Method get_predictor_names()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Function querying predictor names existing","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_predictor_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-latent-","dir":"Reference","previous_headings":"","what":"Method set_latent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Adding latent factors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_latent(type, method = NULL, separate_spde = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"type character given type. method character method. separate_spde logical flag whether duplicate SPDE effects created.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-latent-","dir":"Reference","previous_headings":"","what":"Method get_latent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get latent factors found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_latent()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-latent-","dir":"Reference","previous_headings":"","what":"Method rm_latent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove latent factors found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_latent()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-priors-","dir":"Reference","previous_headings":"","what":"Method get_priors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get prior object found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_priors()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-priors-","dir":"Reference","previous_headings":"","what":"Method set_priors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Specify new prior object. Overwrites existing ones","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_priors(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-biodiversity-","dir":"Reference","previous_headings":"","what":"Method set_biodiversity()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Adds new biodiversity object existing empty collection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_biodiversity(id, p)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"id character id defining object. p BiodiversityDataset object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-predictors-","dir":"Reference","previous_headings":"","what":"Method set_predictors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new Predictor object object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_predictors(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x PredictorDataset predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-engine-","dir":"Reference","previous_headings":"","what":"Method set_engine()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new Engine object object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_engine(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x Engine object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-engine-","dir":"Reference","previous_headings":"","what":"Method get_engine()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Gets name current engine set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_engine()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character engine name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-engine-","dir":"Reference","previous_headings":"","what":"Method rm_engine()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Removes current engine set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_engine()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-prior-variables-","dir":"Reference","previous_headings":"","what":"Method get_prior_variables()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get prior variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_prior_variables()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character variable names priors added.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-offset-","dir":"Reference","previous_headings":"","what":"Method set_offset()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Specify new offsets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_offset(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x new SpatRaster object used offset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-offset-","dir":"Reference","previous_headings":"","what":"Method get_offset()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get offset (print name)","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_offset()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character offsets .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-offset-","dir":"Reference","previous_headings":"","what":"Method rm_offset()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove offsets found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_offset(what = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Optional character specific offsets remove.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-plot-offsets-","dir":"Reference","previous_headings":"","what":"Method plot_offsets()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Plot offset found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$plot_offsets()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-23","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"graphical element.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-offset-type-","dir":"Reference","previous_headings":"","what":"Method get_offset_type()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get offset parameters found","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-24","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_offset_type()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-24","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list offset parameters found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-control-","dir":"Reference","previous_headings":"","what":"Method set_control()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new bias control","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-25","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_control(type = \"bias\", x, method, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"type character type control object. x new bias control object. Expecting SpatRaster object. method method used create object. value bias value numeric.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-25","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-control-","dir":"Reference","previous_headings":"","what":"Method get_control()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get bias control (print name)","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-26","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_control(type = \"bias\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"type character type control object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-26","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character bias object found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-control-","dir":"Reference","previous_headings":"","what":"Method rm_control()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove bias controls found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-27","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_control()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-27","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-plot-bias-","dir":"Reference","previous_headings":"","what":"Method plot_bias()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Plot bias variable set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-28","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$plot_bias()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-28","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"graphical element.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-log-","dir":"Reference","previous_headings":"","what":"Method get_log()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Returns output filename current log object set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-29","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_log()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-29","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character output returned.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-log-","dir":"Reference","previous_headings":"","what":"Method set_log()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new log object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-30","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_log(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x Log object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-30","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-extent-","dir":"Reference","previous_headings":"","what":"Method get_extent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get extent","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-31","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_extent()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-31","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Background extent NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-extent-dimensions-","dir":"Reference","previous_headings":"","what":"Method get_extent_dimensions()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get dimensions extent background","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-32","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_extent_dimensions()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-32","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Background extent NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get projection background crs format.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-33","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-33","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Return resolution background object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-34","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-34","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"vector resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-predictors-","dir":"Reference","previous_headings":"","what":"Method rm_predictors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove predictiors. Either specific ones.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-35","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_predictors(names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-12","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"names character predictors removed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-35","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-priors-","dir":"Reference","previous_headings":"","what":"Method rm_priors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove priors. Either specific ones.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-36","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_priors(names = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-13","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"names character priors removed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-36","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-biodiversity-length-","dir":"Reference","previous_headings":"","what":"Method show_biodiversity_length()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Show number biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-37","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show_biodiversity_length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-37","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"numeric sum biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-biodiversity-equations-","dir":"Reference","previous_headings":"","what":"Method show_biodiversity_equations()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Show Equations biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-38","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show_biodiversity_equations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-38","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message screen.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-equations-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_equations()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get equations biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-39","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_equations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-39","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-types-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_types()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Query biodiversity types object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-40","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_types()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-40","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-ids-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_ids()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Return biodiversity dataset ids object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-41","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_ids()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-41","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list ids biodiversity datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-names-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_names()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Return character names biodiversity datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-42","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-42","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list names biodiversity datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Plots content class.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-43","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$plot()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-43","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Summary function object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-44","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$summary()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-44","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-45","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-14","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"# Query available functions and entries background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM',mustWork = TRUE)) # Define model x <- distribution(background) #> [Setup] 2024-01-25 21:59:49.457332 | Provide a background with a valid projection! #> [Setup] 2024-01-25 21:59:49.476683 | Creating distribution object... names(x) #>  [1] \".__enclos_env__\"             \"engine\"                      #>  [3] \"log\"                         \"offset\"                      #>  [5] \"latentfactors\"               \"control\"                     #>  [7] \"priors\"                      \"predictors\"                  #>  [9] \"biodiversity\"                \"limits\"                      #> [11] \"background\"                  \"clone\"                       #> [13] \"summary\"                     \"plot\"                        #> [15] \"get_biodiversity_names\"      \"get_biodiversity_ids\"        #> [17] \"get_biodiversity_types\"      \"get_biodiversity_equations\"  #> [19] \"show_biodiversity_equations\" \"show_biodiversity_length\"    #> [21] \"rm_priors\"                   \"rm_predictors\"               #> [23] \"get_resolution\"              \"get_projection\"              #> [25] \"get_extent_dimensions\"       \"get_extent\"                  #> [27] \"set_log\"                     \"get_log\"                     #> [29] \"plot_bias\"                   \"rm_control\"                  #> [31] \"get_control\"                 \"set_control\"                 #> [33] \"get_offset_type\"             \"plot_offsets\"                #> [35] \"rm_offset\"                   \"get_offset\"                  #> [37] \"set_offset\"                  \"get_prior_variables\"         #> [39] \"rm_engine\"                   \"get_engine\"                  #> [41] \"set_engine\"                  \"set_predictors\"              #> [43] \"set_biodiversity\"            \"set_priors\"                  #> [45] \"get_priors\"                  \"rm_latent\"                   #> [47] \"get_latent\"                  \"set_latent\"                  #> [49] \"get_predictor_names\"         \"rm_limits\"                   #> [51] \"get_limits\"                  \"set_limits\"                  #> [53] \"show_background_info\"        \"name\"                        #> [55] \"show\"                        \"print\"                       #> [57] \"initialize\""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Base R6 class biodiversity scenario objects. Serves container supplies data functions R6 classes functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"sets threshold method internally 'fixed'. requires \"gganimate\" package. requires set threshold() scenario object. requires set threshold prior projection.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"modelobject name model projection. modelid id model used projection. limits sf object used constraint prediction. predictors predictor object projection. constraints constraints set projection. scenarios resulting stars objects.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"BiodiversityScenario$new() BiodiversityScenario$print() BiodiversityScenario$verify() BiodiversityScenario$show() BiodiversityScenario$get_projection() BiodiversityScenario$get_resolution() BiodiversityScenario$get_model() BiodiversityScenario$get_limits() BiodiversityScenario$get_predictor_names() BiodiversityScenario$get_timeperiod() BiodiversityScenario$get_constraints() BiodiversityScenario$get_threshold() BiodiversityScenario$get_thresholdvalue() BiodiversityScenario$apply_threshold() BiodiversityScenario$set_predictors() BiodiversityScenario$set_constraints() BiodiversityScenario$get_simulation() BiodiversityScenario$set_simulation() BiodiversityScenario$get_predictors() BiodiversityScenario$rm_predictors() BiodiversityScenario$get_data() BiodiversityScenario$set_data() BiodiversityScenario$plot() BiodiversityScenario$plot_threshold() BiodiversityScenario$plot_migclim() BiodiversityScenario$plot_animation() BiodiversityScenario$plot_relative_change() BiodiversityScenario$summary() BiodiversityScenario$summary_beforeafter() BiodiversityScenario$calc_scenarios_slope() BiodiversityScenario$mask() BiodiversityScenario$get_centroid() BiodiversityScenario$save() BiodiversityScenario$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$new()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Print names properties scenarios.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-verify-","dir":"Reference","previous_headings":"","what":"Method verify()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Verify set Model exist check self-validity","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$verify()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Show name Model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Model objectname","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get projection projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"sf object geographic projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get resultion projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"numeric indication resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-model-","dir":"Reference","previous_headings":"","what":"Method get_model()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get actual model used projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_model()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"DistributionModel object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-limits-","dir":"Reference","previous_headings":"","what":"Method get_limits()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get provided projection limits set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"sf object NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-predictor-names-","dir":"Reference","previous_headings":"","what":"Method get_predictor_names()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get names predictors scenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_predictor_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character vector names.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-timeperiod-","dir":"Reference","previous_headings":"","what":"Method get_timeperiod()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get time period projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_timeperiod(what = \"range\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character whether full time period just range returned.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"time period start end.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-constraints-","dir":"Reference","previous_headings":"","what":"Method get_constraints()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get constrains model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_constraints()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list constraints within scenario.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-threshold-","dir":"Reference","previous_headings":"","what":"Method get_threshold()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get thresholds specified.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_threshold()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list method value threshold.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-thresholdvalue-","dir":"Reference","previous_headings":"","what":"Method get_thresholdvalue()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Duplicate function internal consistency return threshold","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_thresholdvalue()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list method value threshold.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-apply-threshold-","dir":"Reference","previous_headings":"","what":"Method apply_threshold()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Apply new threshold projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$apply_threshold(tr = new_waiver())"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"tr numeric value new threshold.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-predictors-","dir":"Reference","previous_headings":"","what":"Method set_predictors()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set new predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_predictors(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x PredictorDataset object supplied.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-constraints-","dir":"Reference","previous_headings":"","what":"Method set_constraints()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set new constrains","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_constraints(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x SpatRaster object added constraint.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-simulation-","dir":"Reference","previous_headings":"","what":"Method get_simulation()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get simulation options parameters gound","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_simulation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-simulation-","dir":"Reference","previous_headings":"","what":"Method set_simulation()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set simulation objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_simulation(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x new simulation entries options list set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-predictors-","dir":"Reference","previous_headings":"","what":"Method get_predictors()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get Predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_predictors()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"predictor dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-rm-predictors-","dir":"Reference","previous_headings":"","what":"Method rm_predictors()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Remove predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$rm_predictors(names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"names character vector names","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get scenario predictions data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_data(what = \"scenarios\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character vector names ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set new data object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_data(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x new data object measuing scenarios.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot predictions made .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot(what = \"suitability\", which = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character describing layers plotted. numeric subset specific time steps. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-threshold-","dir":"Reference","previous_headings":"","what":"Method plot_threshold()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Convenience function plot thresholds set","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_threshold(which = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"numeric subset specific time steps.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-23","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-migclim-","dir":"Reference","previous_headings":"","what":"Method plot_migclim()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot Migclim results existing.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-24","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_migclim()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-24","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-animation-","dir":"Reference","previous_headings":"","what":"Method plot_animation()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot animation scenarios possible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-25","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_animation(what = \"suitability\", fname = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character describing layers plotted. fname optional filename write result.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-25","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-relative-change-","dir":"Reference","previous_headings":"","what":"Method plot_relative_change()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot relative change baseline projected thresholds","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-26","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_relative_change(   position = NULL,   variable = \"mean\",   plot = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"position layer plotted variable character variable plotted plot logical flag whether plot results return object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-26","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation SpatRaster.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarize change layers timesteps","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-27","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$summary(   layer = \"threshold\",   plot = FALSE,   relative = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-12","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"layer character variable plotted plot logical flag whether plot results return coefficients. relative logical coefficients converted relative change.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-27","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarized coefficients data.frame","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-summary-beforeafter-","dir":"Reference","previous_headings":"","what":"Method summary_beforeafter()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarize -change first last layer.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-28","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$summary_beforeafter()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-28","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarized coefficients data.frame","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-calc-scenarios-slope-","dir":"Reference","previous_headings":"","what":"Method calc_scenarios_slope()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Calculate slopes across projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-29","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$calc_scenarios_slope(   what = \"suitability\",   plot = TRUE,   oftype = \"stars\" )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-13","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character layer plotted (default: \"suitability\"). plot logical flag whether plot results return coefficients. oftype character output type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-29","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"SpatRaster layer stars object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Convenience function mask input projections.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-30","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-14","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-30","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-centroid-","dir":"Reference","previous_headings":"","what":"Method get_centroid()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get centroids projection layers","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-31","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_centroid(patch = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-15","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"patch logical centroid calculated weighted values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-31","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Returns sf object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-save-","dir":"Reference","previous_headings":"","what":"Method save()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Save object output somewhere","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-32","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$save(fname, type = \"tif\", dt = \"FLT4S\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-16","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"fname output filename character. type format character. Matched list supported formats. dt datatype used, float64","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-32","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Saved spatial prediction drive.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-33","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-17","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Class for the trained Model object — DistributionModel-class","title":"Class for the trained Model object — DistributionModel-class","text":"trained Models inherit options plus additional ones defined engine inference.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Class for the trained Model object — DistributionModel-class","text":"pretified commands outsourced.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Class for the trained Model object — DistributionModel-class","text":"id character id trained model name description model character. model list containing input datasets parameters model. settings Settings object information inference. fits list containing prediction fitted model.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Class for the trained Model object — DistributionModel-class","text":"DistributionModel$new() DistributionModel$get_name() DistributionModel$print() DistributionModel$show() DistributionModel$plot() DistributionModel$plot_threshold() DistributionModel$show_duration() DistributionModel$summary() DistributionModel$effects() DistributionModel$get_equation() DistributionModel$get_data() DistributionModel$set_data() DistributionModel$get_thresholdvalue() DistributionModel$get_thresholdtype() DistributionModel$show_rasters() DistributionModel$get_projection() DistributionModel$get_resolution() DistributionModel$rm_threshold() DistributionModel$calc_suitabilityindex() DistributionModel$get_centroid() DistributionModel$has_limits() DistributionModel$has_offset() DistributionModel$mask() DistributionModel$save() DistributionModel$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Class for the trained Model object — DistributionModel-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$new(name)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"name description model character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-name-","dir":"Reference","previous_headings":"","what":"Method get_name()","title":"Class for the trained Model object — DistributionModel-class","text":"Return name model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"character model name used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Class for the trained Model object — DistributionModel-class","text":"Print names summarizes model within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Class for the trained Model object — DistributionModel-class","text":"Show name Model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"character run name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"Class for the trained Model object — DistributionModel-class","text":"Plots prediction found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$plot(what = \"mean\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"character specific layer plotted.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"graphical representation prediction","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-plot-threshold-","dir":"Reference","previous_headings":"","what":"Method plot_threshold()","title":"Class for the trained Model object — DistributionModel-class","text":"Plots thresholded prediction found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$plot_threshold(what = 1)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"character numeric layer plotted.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"graphical representation thresholded prediction found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-show-duration-","dir":"Reference","previous_headings":"","what":"Method show_duration()","title":"Class for the trained Model object — DistributionModel-class","text":"Show model run time settings exist","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$show_duration()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"numeric estimate duration took fit models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Class for the trained Model object — DistributionModel-class","text":"Get effects importance tables model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$summary(obj = \"fit_best\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"obj character object return.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"data.frame summarizing model, usually coefficient.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-effects-","dir":"Reference","previous_headings":"","what":"Method effects()","title":"Class for the trained Model object — DistributionModel-class","text":"Generic plotting function effect plots","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$effects(x = \"fit_best\", what = \"fixed\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"x character object question. character type coefficients. ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"graphical representation coefficents.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-equation-","dir":"Reference","previous_headings":"","what":"Method get_equation()","title":"Class for the trained Model object — DistributionModel-class","text":"Get equation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_equation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"formula inferred model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"Class for the trained Model object — DistributionModel-class","text":"Get specific fit Model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_data(x = \"prediction\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"x character stating returned.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"SpatRaster object prediction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"Class for the trained Model object — DistributionModel-class","text":"Set new fit Model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"x name new fit. value SpatRaster layer inserted.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-thresholdvalue-","dir":"Reference","previous_headings":"","what":"Method get_thresholdvalue()","title":"Class for the trained Model object — DistributionModel-class","text":"Get threshold value calculated","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_thresholdvalue()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"numeric threshold value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-thresholdtype-","dir":"Reference","previous_headings":"","what":"Method get_thresholdtype()","title":"Class for the trained Model object — DistributionModel-class","text":"Get threshold type format calculated.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_thresholdtype()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"vector character method numeric threshold value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-show-rasters-","dir":"Reference","previous_headings":"","what":"Method show_rasters()","title":"Class for the trained Model object — DistributionModel-class","text":"List rasters object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$show_rasters()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"vector logical flags various objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"Class for the trained Model object — DistributionModel-class","text":"Get projection background.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"geographic projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"Class for the trained Model object — DistributionModel-class","text":"Get resolution projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"numeric estimates distribution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-rm-threshold-","dir":"Reference","previous_headings":"","what":"Method rm_threshold()","title":"Class for the trained Model object — DistributionModel-class","text":"Remove calculated thresholds","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$rm_threshold()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-calc-suitabilityindex-","dir":"Reference","previous_headings":"","what":"Method calc_suitabilityindex()","title":"Class for the trained Model object — DistributionModel-class","text":"Calculate suitability index given projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$calc_suitabilityindex(method = \"normalize\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"method method used normalization.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Class for the trained Model object — DistributionModel-class","text":"Methods can either normalized minimum maximum. relative total using sumof values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Returns SpatRaster.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-centroid-","dir":"Reference","previous_headings":"","what":"Method get_centroid()","title":"Class for the trained Model object — DistributionModel-class","text":"Get centroids prediction layers","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_centroid(patch = FALSE, layer = \"mean\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"patch logical centroid calculated weighted values. layer character layer use.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Returns sf object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-has-limits-","dir":"Reference","previous_headings":"","what":"Method has_limits()","title":"Class for the trained Model object — DistributionModel-class","text":"Logical indication prediction limited.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$has_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"logical flag.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-has-offset-","dir":"Reference","previous_headings":"","what":"Method has_offset()","title":"Class for the trained Model object — DistributionModel-class","text":"offset used?","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$has_offset()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"logical flag.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"Class for the trained Model object — DistributionModel-class","text":"Convenience function mask input datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed mask","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-save-","dir":"Reference","previous_headings":"","what":"Method save()","title":"Class for the trained Model object — DistributionModel-class","text":"Save prediction output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$save(fname, type = \"gtif\", dt = \"FLT4S\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"fname output filename character. type format character. Matched list supported formats. dt datatype used, float64","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-23","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Saved spatial prediction drive.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Class for the trained Model object — DistributionModel-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-24","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine class description — Engine-class","title":"Engine class description — Engine-class","text":"Basic object engine, engines inherit .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Engine class description — Engine-class","text":"engine class name engine. name name engine data data parameters necessary make engine work.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Engine class description — Engine-class","text":"Engine$new() Engine$print() Engine$show() Engine$get_class() Engine$get_data() Engine$list_data() Engine$set_data() Engine$get_self() Engine$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Engine class description — Engine-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$new(engine, name)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"engine class name engine. name name engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Engine class description — Engine-class","text":"Print Engine name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Engine class description — Engine-class","text":"Aliases calls print.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-get-class-","dir":"Reference","previous_headings":"","what":"Method get_class()","title":"Engine class description — Engine-class","text":"Get class description","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$get_class()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"character class saved engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"Engine class description — Engine-class","text":"Get specific data engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$get_data(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"x respecified data added engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"list data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-list-data-","dir":"Reference","previous_headings":"","what":"Method list_data()","title":"Engine class description — Engine-class","text":"List data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$list_data()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"character vector data entries.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"Engine class description — Engine-class","text":"Set data engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"x character name id dataset. value new list parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-get-self-","dir":"Reference","previous_headings":"","what":"Method get_self()","title":"Engine class description — Engine-class","text":"Dummy function get self object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$get_self()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Engine class description — Engine-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Monotonic constrained priors for boosted regressions — GDBPrior","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"Monotonic constrains gradient descent boosting models work way priors specific coefficient magnitude importance specified. Rather monotonic constraints enforce specific directionality regression coefficients instance coefficient positive negative. Important: Specifying monotonic constrain engine_gdb guarantee variable retained model can still regularized .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"","code":"GDBPrior(variable, hyper = \"increasing\", ...)  # S4 method for character GDBPrior(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"variable character matched existing predictors variables. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'positive', 'negative' 'none'. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"Similar priors can also defined engine_xgboost via XGBPrior().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"Hofner, B., Müller, J., & Hothorn, T. (2011). Monotonicity‐constrained species distribution models. Ecology, 92(10), 1895-1901.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","title":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","text":"helper function specify several GLMNETPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","text":"","code":"GDBPriors(variable, hyper = \"increasing\", ...)  # S4 method for character GDBPriors(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","text":"variable character matched existing predictors variables. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'positive', 'negative' 'none'. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Regression penalty priors for GLMNET — GLMNETPrior","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"engine_glmnet engine support priors typical sense, however possible specify called penalty factors well lower upper limits variables model. default penalty multiplier 1 coefficient X covariate, .e. coefficients penalized equally informed intersection absence information covariates. contrast variable penalty.factor equal 0 penalized . addition, possible specifiy lower upper limit specific coefficients, constrain certain range. default ranges set -Inf Inf respectively, can reset specific value range altering \"lims\" (see examples). regularized regression supports options priors, check Bayesian engine_breg.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"","code":"GLMNETPrior(variable, hyper = 0, lims = c(-Inf, Inf), ...)  # S4 method for character GLMNETPrior(variable, hyper = 0, lims = c(-Inf, Inf), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"variable character variable passed prior object. hyper numeric value 0 1 state penalization factor. default set 0, implying \"variable\" provided regularized . lims numeric vector lower upper limits coefficient (Default: c(-Inf, Inf)). ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"","code":"if (FALSE) { # Retain variable p1 <- GLMNETPrior(variable = \"forest\", hyper = 0) p1 # Smaller chance to be regularized p2 <- GLMNETPrior(variable = \"forest\", hyper = 0.2, lims = c(0, Inf)) p2 }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","title":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","text":"helper function specify several GLMNETPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","text":"","code":"GLMNETPriors(variable, hyper = 0, lims = c(-Inf, Inf))  # S4 method for character GLMNETPriors(variable, hyper = 0, lims = c(-Inf, Inf))"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","text":"variable character variable passed prior object. hyper numeric value 0 1 state penalization factor. default set 0, implying \"variable\" provided regularized . lims numeric vector lower upper limits coefficient (Default: c(-Inf, Inf)).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new INLA prior — INLAPrior","title":"Create a new INLA prior — INLAPrior","text":"fixed random effect INLA supports range different priors exponential distributions. Currently supported INLA ibis.iSDM following priors can specified via \"type\": \"normal\" \"gaussian\": Priors normal distributed set specified variable. Required parameters mean precision estimate provided \"hyper\". Note precision equivalent (rather inverse) typical standard deviation specified Gaussian priors. Defaults set mean 0 precision 0.001. \"clinear\": Prior places constraint linear coefficients model coefficient specified interval \"c(lower,upper)\". Specified hyper values can negative, positive infinite. \"spde\", specifically 'prior.range' 'prior.sigma': Specification penalized complexity priors can added SPDE spatial random effect added via add_latent_spatial(). range penalized complexity prior can specified 'prior.range' uncertainty via 'prior.sigma' supplied options 'type' 'hyper'. priors available INLA  names(INLA::inla.models()$prior) )  might also work, tested!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new INLA prior — INLAPrior","text":"","code":"INLAPrior(variable, type = \"normal\", hyper = c(0, 0.001), ...)  # S4 method for character,character INLAPrior(variable, type = \"normal\", hyper = c(0, 0.001), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new INLA prior — INLAPrior","text":"variable character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper-parameters. See description. default values set mean 0 precision 0.001. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create a new INLA prior — INLAPrior","text":"Compared engines, INLA unfortunately support priors related stringent parameter regularization Laplace Horseshoe priors, limits capability engine_inla regularization. said many default uninformative priors act already regularize coefficients degree.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new INLA prior — INLAPrior","text":"Rue, H., Riebler, ., Sørbye, S. H., Illian, J. B., Simpson, D. P., & Lindgren, F. K. (2017). Bayesian computing INLA: review. Annual Review Statistics Application, 4, 395-421. Simpson, D., Rue, H., Riebler, ., Martins, T. G., & Sørbye, S. H. (2017). Penalising model component complexity: principled, practical approach constructing priors. Statistical science, 32(1), 1-28.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","title":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","text":"helper function specify several INLAPrior objects hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","text":"","code":"INLAPriors(variables, type, hyper = c(0, 0.001), ...)  # S4 method for vector,character INLAPriors(variables, type, hyper = c(0, 0.001), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","text":"variables vector character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper-parameters. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Log prototype. — Log-class","title":"Log prototype. — Log-class","text":"Basic R6 object Log, Log inherit ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Log prototype. — Log-class","text":"filename character log stored. output log content.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Log prototype. — Log-class","text":"Log$new() Log$print() Log$open() Log$close() Log$get_filename() Log$set_filename() Log$delete() Log$open_system() Log$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Log prototype. — Log-class","text":"Initializes object specifies default parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$new(filename, output)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"filename character log stored. output log content.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Log prototype. — Log-class","text":"Print message filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-open-","dir":"Reference","previous_headings":"","what":"Method open()","title":"Log prototype. — Log-class","text":"Opens connection output filename.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$open(type = c(\"output\", \"message\"))"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"type character vector output types.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-close-","dir":"Reference","previous_headings":"","what":"Method close()","title":"Log prototype. — Log-class","text":"Closes connection output file","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$close()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-get-filename-","dir":"Reference","previous_headings":"","what":"Method get_filename()","title":"Log prototype. — Log-class","text":"Get output filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$get_filename()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"character filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-set-filename-","dir":"Reference","previous_headings":"","what":"Method set_filename()","title":"Log prototype. — Log-class","text":"Set new output filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$set_filename(value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"value character new filename.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-delete-","dir":"Reference","previous_headings":"","what":"Method delete()","title":"Log prototype. — Log-class","text":"Delete log file","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$delete()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-open-system-","dir":"Reference","previous_headings":"","what":"Method open_system()","title":"Log prototype. — Log-class","text":"Open log system viewer","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$open_system()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Log prototype. — Log-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":null,"dir":"Reference","previous_headings":"","what":"PredictorDataset class description — PredictorDataset-class","title":"PredictorDataset class description — PredictorDataset-class","text":"class describes PredictorDataset used store covariates within.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"PredictorDataset class description — PredictorDataset-class","text":"id id collection character. data predictor dataset usually SpatRaster. name name object. timeperiod timeperiod field","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"PredictorDataset class description — PredictorDataset-class","text":"PredictorDataset$new() PredictorDataset$print() PredictorDataset$get_name() PredictorDataset$get_id() PredictorDataset$get_names() PredictorDataset$get_predictor_names() PredictorDataset$get_data() PredictorDataset$get_time() PredictorDataset$get_projection() PredictorDataset$get_resolution() PredictorDataset$crop_data() PredictorDataset$mask() PredictorDataset$set_data() PredictorDataset$rm_data() PredictorDataset$show() PredictorDataset$summary() PredictorDataset$has_derivates() PredictorDataset$length() PredictorDataset$plot() PredictorDataset$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"PredictorDataset class description — PredictorDataset-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$new(id, data, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"id id collection character. data predictor dataset usually SpatRaster. ... parameters found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"PredictorDataset class description — PredictorDataset-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$print(format = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"format logical flag whether message printed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-name-","dir":"Reference","previous_headings":"","what":"Method get_name()","title":"PredictorDataset class description — PredictorDataset-class","text":"Return name object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Default character name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-id-","dir":"Reference","previous_headings":"","what":"Method get_id()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get Id object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Default character name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-names-","dir":"Reference","previous_headings":"","what":"Method get_names()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get names data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"character names data value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-predictor-names-","dir":"Reference","previous_headings":"","what":"Method get_predictor_names()","title":"PredictorDataset class description — PredictorDataset-class","text":"Alias get_names","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_predictor_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"character names data value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get specific dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_data(df = FALSE, na.rm = TRUE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"df logical whether data returned data.frame. na.rm logical NA removed data.frame. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"SpatRaster data.frame.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-time-","dir":"Reference","previous_headings":"","what":"Method get_time()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get time dimension object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_time(...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"vector time dimension dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get Projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"vector geographical projection object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get Resolution","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"numeric vector spatial resolution data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-crop-data-","dir":"Reference","previous_headings":"","what":"Method crop_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Utility function clip predictor dataset another dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$crop_data(pol)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"pol sf object used cropping data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisibile TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"PredictorDataset class description — PredictorDataset-class","text":"Utility function mask predictor dataset another dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed masking.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Add new Predictor dataset collection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"x character new name stored. value new SpatRaster object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-rm-data-","dir":"Reference","previous_headings":"","what":"Method rm_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Remove specific Predictor name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$rm_data(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"x character predictor name removed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"PredictorDataset class description — PredictorDataset-class","text":"Alias print method","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"PredictorDataset class description — PredictorDataset-class","text":"Collect info statistics optional decimals","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$summary(digits = 2)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"digits numeric Giving rounding precision","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"data.frame summarizing data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-has-derivates-","dir":"Reference","previous_headings":"","what":"Method has_derivates()","title":"PredictorDataset class description — PredictorDataset-class","text":"Indication predictors derivates outers","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$has_derivates()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"logical flag.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"PredictorDataset class description — PredictorDataset-class","text":"Number Predictors object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"numeric estimate","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"PredictorDataset class description — PredictorDataset-class","text":"Basic Plotting function","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$plot()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"graphical interpretation predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"PredictorDataset class description — PredictorDataset-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Base Prior class — Prior-class","title":"Base Prior class — Prior-class","text":"class sets base class priors inherited priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Base Prior class — Prior-class","text":"Defines Prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Base Prior class — Prior-class","text":"functionality likely deprecated checks superseeded.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Base Prior class — Prior-class","text":"id character id prior. name character name prior. type character type prior. variable character variable name prior. distribution character distribution prior relevant. value numeric character prior value, e.g. hyper-parameters. prob Another numeric entry prior field. inclusion probability. lims limitation lower upper bounds numeric value.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Base Prior class — Prior-class","text":"Prior$new() Prior$print() Prior$validate() Prior$get() Prior$set() Prior$get_id() Prior$get_name() Prior$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Base Prior class — Prior-class","text":"Initializes object prepared various prior variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$new(   id,   name,   variable,   value,   type = NULL,   distribution = NULL,   prob = NULL,   lims = NULL )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"id character id prior. name character name prior. variable character variable name prior. value numeric character prior value, e.g. hyper-parameters. type character type prior. distribution character distribution prior relevant. prob Another numeric entry prior field. inclusion probability. lims limitation lower upper bounds numeric value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Base Prior class — Prior-class","text":"Print prior type variable.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-validate-","dir":"Reference","previous_headings":"","what":"Method validate()","title":"Base Prior class — Prior-class","text":"Generic validation function provided value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$validate(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"x new prior value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-get-","dir":"Reference","previous_headings":"","what":"Method get()","title":"Base Prior class — Prior-class","text":"Get prior values","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$get(what = \"value\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"character entry returned (Default: value).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-set-","dir":"Reference","previous_headings":"","what":"Method set()","title":"Base Prior class — Prior-class","text":"Set prior","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$set(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"x new prior value numeric character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-get-id-","dir":"Reference","previous_headings":"","what":"Method get_id()","title":"Base Prior class — Prior-class","text":"Get specific ID prior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$get_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"character id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-get-name-","dir":"Reference","previous_headings":"","what":"Method get_name()","title":"Base Prior class — Prior-class","text":"Get Name object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$get_name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Returns character class name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Base Prior class — Prior-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":null,"dir":"Reference","previous_headings":"","what":"List of Priors supplied to an class — PriorList-class","title":"List of Priors supplied to an class — PriorList-class","text":"class represents collection Prior objects. provides methods accessing, adding removing priors list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"List of Priors supplied to an class — PriorList-class","text":"PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"List of Priors supplied to an class — PriorList-class","text":"priors list Prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"List of Priors supplied to an class — PriorList-class","text":"PriorList$new() PriorList$print() PriorList$show() PriorList$length() PriorList$ids() PriorList$varnames() PriorList$classes() PriorList$types() PriorList$exists() PriorList$add() PriorList$get() PriorList$collect() PriorList$rm() PriorList$summary() PriorList$combine() PriorList$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"List of Priors supplied to an class — PriorList-class","text":"Initializes object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$new(priors)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"priors list Prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"List of Priors supplied to an class — PriorList-class","text":"Print summary statistics","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"List of Priors supplied to an class — PriorList-class","text":"Aliases calls print.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"List of Priors supplied to an class — PriorList-class","text":"Number priors object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"numeric number priors set","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-ids-","dir":"Reference","previous_headings":"","what":"Method ids()","title":"List of Priors supplied to an class — PriorList-class","text":"Ids prior objects","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$ids()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"list ids priors objects query","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-varnames-","dir":"Reference","previous_headings":"","what":"Method varnames()","title":"List of Priors supplied to an class — PriorList-class","text":"Variable names priors object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$varnames()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character list variable names priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-classes-","dir":"Reference","previous_headings":"","what":"Method classes()","title":"List of Priors supplied to an class — PriorList-class","text":"Function return classes contained priors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$classes()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character list class names priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-types-","dir":"Reference","previous_headings":"","what":"Method types()","title":"List of Priors supplied to an class — PriorList-class","text":"Get types contained priors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$types()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character list type names priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-exists-","dir":"Reference","previous_headings":"","what":"Method exists()","title":"List of Priors supplied to an class — PriorList-class","text":"certain variable type combination exist prior ?","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$exists(variable, type = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"variable character variable name. type character type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-add-","dir":"Reference","previous_headings":"","what":"Method add()","title":"List of Priors supplied to an class — PriorList-class","text":"Add new prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$add(p)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"p Prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-get-","dir":"Reference","previous_headings":"","what":"Method get()","title":"List of Priors supplied to an class — PriorList-class","text":"Get specific prior values list set","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$get(variable, type = NULL, what = \"value\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"variable character variable name. type character type name character specific entry return (Default: prior value).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-collect-","dir":"Reference","previous_headings":"","what":"Method collect()","title":"List of Priors supplied to an class — PriorList-class","text":"Collect priors given id multiple.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$collect(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"id character prior id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-rm-","dir":"Reference","previous_headings":"","what":"Method rm()","title":"List of Priors supplied to an class — PriorList-class","text":"Remove set prior id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$rm(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"id character prior id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"List of Priors supplied to an class — PriorList-class","text":"Summary function lists priors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$summary()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"data.frame summarized priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-combine-","dir":"Reference","previous_headings":"","what":"Method combine()","title":"List of Priors supplied to an class — PriorList-class","text":"Combining function combine PriorList another new one","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$combine(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"x new PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"List of Priors supplied to an class — PriorList-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"if (FALSE) { priors(     INLAPrior('var1','normal',c(0,0.1)),     INLAPrior('var2','normal',c(0,0.1))    ) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new STAN prior — STANPrior","title":"Create a new STAN prior — STANPrior","text":"Function create new prior engine_stan models. Priors currently can set specific environmental predictors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new STAN prior — STANPrior","text":"","code":"STANPrior(variable, type, hyper = c(0, 2), ...)  # S4 method for character,character STANPrior(variable, type, hyper = c(0, 2), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new STAN prior — STANPrior","text":"variable character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper parameters. First entry treated mean (Default: 0), second standard variation (Default: 2) Gaussian distribution respective coefficient. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new STAN prior — STANPrior","text":"Lemoine, N. P. (2019). Moving beyond noninformative priors: choose weakly informative priors Bayesian analyses. Oikos, 128(7), 912-928. Carpenter, B., Gelman, ., Hoffman, M. D., Lee, D., Goodrich, B., Betancourt, M., ... & Riddell, . (2017). Stan: probabilistic programming language. Journal statistical software, 76(1), 1-32.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new STAN prior — STANPrior","text":"","code":"if (FALSE) {  pp <- STANPrior(\"forest\", \"normal\", c(0,1)) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables and types are supplied for STAN — STANPriors","title":"Helper function when multiple variables and types are supplied for STAN — STANPriors","text":"helper function specify several STANPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables and types are supplied for STAN — STANPriors","text":"","code":"STANPriors(variables, type, hyper = c(0, 2), ...)  # S4 method for vector,character STANPriors(variables, type, hyper = c(0, 2), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables and types are supplied for STAN — STANPriors","text":"variables vector character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper-parameters. ... Variables passed prior object","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Prototype for model settings object — Settings-class","title":"Prototype for model settings object — Settings-class","text":"Basic R6 object Settings object, List stores settings used related model training.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Prototype for model settings object — Settings-class","text":"name default name settings character. modelid character model id belongs . data list contained settings.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Prototype for model settings object — Settings-class","text":"Settings$new() Settings$print() Settings$show() Settings$length() Settings$duration() Settings$summary() Settings$get() Settings$set() Settings$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Prototype for model settings object — Settings-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$new()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Prototype for model settings object — Settings-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Prototype for model settings object — Settings-class","text":"Shows name settings","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"character name settings.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"Prototype for model settings object — Settings-class","text":"Number options","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"numeric number options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-duration-","dir":"Reference","previous_headings":"","what":"Method duration()","title":"Prototype for model settings object — Settings-class","text":"Computation duration convenience function","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$duration()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"amount time passed model fitting found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Prototype for model settings object — Settings-class","text":"Summary call contained parameters","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$summary()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"list parameters object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-get-","dir":"Reference","previous_headings":"","what":"Method get()","title":"Prototype for model settings object — Settings-class","text":"Get specific setting","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$get(what)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Prototype for model settings object — Settings-class","text":"character respective setting.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"setting found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-set-","dir":"Reference","previous_headings":"","what":"Method set()","title":"Prototype for model settings object — Settings-class","text":"Set new settings","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$set(what, x, copy = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Prototype for model settings object — Settings-class","text":"character name new settings. x new setting stored. Can object. copy logical whether new settings object created.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"setting found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Prototype for model settings object — Settings-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Prototype for model settings object — Settings-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new monotonic prior for boosted regressions — XGBPrior","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"Function include prior information monotonic constrain extreme gradient descent boosting model engine_xgboost. Monotonic priors enforce directionality direction certain variables, however specifying monotonic constrain guarantee variable regularized model fitting.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"","code":"XGBPrior(variable, hyper = \"increasing\", ...)  # S4 method for character,character XGBPrior(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"variable character matched existing predictors latent effects. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'none'. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"Chen, T., , T., Benesty, M., Khotilovich, V., Tang, Y., & Cho, H. (2015). Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4), 1-4.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"","code":"if (FALSE) {  pp <- XGBPrior(\"forest\", \"increasing\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","title":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","text":"helper function specify several XGBPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","text":"","code":"XGBPriors(variable, hyper = \"increasing\", ...)  # S4 method for character XGBPriors(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","text":"variable character matched existing predictors latent effects. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'none'. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"function adds presence-absence biodiversity dataset distribution object. Opposed presence-data, presence-absence biodiversity records usually originate structured biodiversity surveys absence species given region specifically assessed. analysts choice also possible format presence-biodiversity data presence-absence form, adding pseudo-absence add_pseudoabsence. See help file information.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"","code":"add_biodiversity_poipa(   x,   poipa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_poipa(   x,   poipa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"x distribution() (.e. BiodiversityDistribution) object. poipa data.frame sf object presence-absence point occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records indicating presence/absence. default set \"observed\" error thrown numeric column name exist. formula character formula object passed. Default (NULL) use covariates. family character stating family used  (Default: 'binomial'). link character overwrite default link function (Default: NULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length parameter \"poipa\". separate_intercept logical value stating whether separate intercept added . shared likelihood models engines engine_inla, engine_inlabru engine_stan. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"default, logit link function used logistic regression setting unless specific engine support generalised linear regressions (e.g. engine_bart).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"Renner, . W., J. Elith, . Baddeley, W. Fithian, T. Hastie, S. J. Phillips, G. Popovic, D. . Warton. 2015. Point process models presence-analysis. Methods Ecology Evolution 6:366–379. Guisan . Zimmerman N. 2000. Predictive habitat distribution models ecology. Ecol. Model. 135: 147–186.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"","code":"if (FALSE) { # Define model x <- distribution(background) |> add_biodiversity_poipa(virtual_species) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"function adds presence-biodiversity dataset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"","code":"add_biodiversity_poipo(   x,   poipo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_poipo(   x,   poipo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"x distribution() (.e. BiodiversityDistribution) object. poipo data.frame sf object presence-point occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records. formula character formula object passed. Default use covariates (specified). family character stating family used (Default: 'Poisson'). link character overwrite default link function (Default: codeNULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length \"poipo\". Note: Weights reformated inverse models area offsets (e.g. 5 converted 1/5). separate_intercept logical value stating whether separate intercept added shared likelihood models engines engine_inla, engine_inlabru engine_stan. Otherwise ignored. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). pseudoabsence_settings Either NULL pseudoabs_settings() created settings object. ... parameters passed object. Normally used unless described details.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"function allows add presence-biodiversity records distribution ibis.iSDM Presence-data usually modelled inferential model (see Guisan Zimmerman, 2000) relate occurrence relation environmental covariates selected sample 'background' points. common approach estimation one supported type dataset poisson-process models (PPM) presence-points fitted -weighted Poisson regression. See Renner et al. 2015 overview.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"Guisan . Zimmerman N. 2000. Predictive habitat distribution models ecology. Ecol. Model. 135: 147–186. Renner, . W., J. Elith, . Baddeley, W. Fithian, T. Hastie, S. J. Phillips, G. Popovic, D. . Warton. 2015. Point process models presence-analysis. Methods Ecology Evolution 6:366–379.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"","code":"# Load background background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM',mustWork = TRUE)) # Load virtual species virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM',mustWork = TRUE),'points',quiet = TRUE) # Define model x <- distribution(background) |> add_biodiversity_poipo(virtual_points, field_occurrence = \"Observed\") #> [Setup] 2024-01-25 21:59:54.850886 | Provide a background with a valid projection! #> [Setup] 2024-01-25 21:59:54.874919 | Creating distribution object... #> [Setup] 2024-01-25 21:59:54.875728 | Adding poipo dataset..."},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"function can used add sf polygon dataset existing distribution object. Presence-absence polygon data assumes area within polygon can treated 'presence' species, area outside polygon species absent.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"","code":"add_biodiversity_polpa(   x,   polpa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_polpa(   x,   polpa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"x distribution() (.e. BiodiversityDistribution) object. polpa sf polygon object presence-absence occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records. formula character formula object passed. Default (NULL) use covariates . family character stating family used (Default: binomial). link character overwrite default link function (Default: NULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length \"polpa\". simulate Simulate poipa points within boundaries. Result passed add_biodiversity_poipa (Default: FALSE). simulate_points numeric number points created simulation. simulate_bias SpatRaster layer describing eventual preference simulation (Default: NULL). simulate_strategy character stating strategy sampling. Can set either. 'random' 'regular', latter requiring raster supplied 'simulate_weights' parameter. separate_intercept logical value stating whether separate intercept added shared likelihood models engines engine_inla, engine_inlabru engine_stan. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). pseudoabsence_settings Either NULL pseudoabs_settings() created settings object. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"default approach polygon data sample presence-absence points across region polygons. function thus adds wrapper add_biodiversity_poipa() presence-points created model. Note polygon used directly modelling link covariates polygonal data established regular sampling points within polygon thus equivalent simulating points directly. integration range data predictor offset, see add_predictor_range() add_offset_range() instead.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_biodiversity_polpa(protectedArea) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"function can used add sf polygon dataset existing distribution object. Presence-polygon data treated differential point data engines particular way points generated.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"","code":"add_biodiversity_polpo(   x,   polpo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_polpo(   x,   polpo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"x distribution() (.e. BiodiversityDistribution) object. polpo sf polygon object presence-occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records. formula character formula object passed. Default use covariates (specified). family character stating family used (Default: poisson). link character overwrite default link function (Default: NULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length \"polpo\". simulate Simulate poipo points within boundaries. Result passed add_biodiversity_poipo (Default: FALSE). simulate_points numeric number points created simulation (Default: 100). simulate_bias SpatRaster layer describing eventual preference simulation (Default: NULL). simulate_strategy character stating strategy sampling. Can set either. 'random' 'regular', latter requiring raster supplied 'simulate_weights' parameter. separate_intercept logical value stating whether separate intercept added shared likelihood models engines engine_inla, engine_inlabru engine_stan. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). pseudoabsence_settings Either NULL pseudoabs_settings() created settings object. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"default approach polygon data sample presence-points across region polygons. function thus adds wrapper add_biodiversity_poipo() presence-points created model. points simulated directly (Default) polygon processed train() creating regular point data supplied predictors. Use add_biodiversity_polpa() create binomial distributed inside-outside points given polygon! integration range data predictor offset, see add_predictor_range() add_offset_range() instead.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"","code":"if (FALSE) {  x <- distribution(mod) |>    add_biodiversity_polpo(protectedArea) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a constraint to an existing scenario — add_constraint","title":"Add a constraint to an existing scenario — add_constraint","text":"function adds constrain BiodiversityScenario object constrain (future) projections. constrains can instance constraints possible dispersal distance, connectivity identified patches limitations species adaptability. constrains require pre-calculated thresholds present BiodiversityScenario object!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a constraint to an existing scenario — add_constraint","text":"","code":"add_constraint(mod, method, ...)  # S4 method for BiodiversityScenario add_constraint(mod, method, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a constraint to an existing scenario — add_constraint","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. ... passed parameters. See also specific methods adding constraints.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add a constraint to an existing scenario — add_constraint","text":"Adds constraints data BiodiversityScenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add a constraint to an existing scenario — add_constraint","text":"Constraints can added scenario objects increase decrease suitability given area target feature. function acts wrapper add constraints. Currently supported following options: Dispersal: sdd_fixed - Applies fixed uniform dispersal distance per modelling timestep. sdd_nexpkernel - Applies dispersal distance using negative exponential kernel origin. kissmig - Applies kissmig stochastic dispersal model. Requires `kissmig` package. Applied modelling time step. migclim - Applies dispersal algorithm MigClim modelled objects. Requires \"MigClim\" package. comprehensive overview benefits including dispersal constrains species distribution models can found Bateman et al. (2013). Connectivity: hardbarrier - Defines hard barrier dispersal events. definition sets values larger 0 barrier layer 0 projection. Barrier provided \"resistance\" parameter. resistance - Allows provision static dynamic layer multiplied projection time step. Can example used reduce suitability given area (using pressures included model). respective layer(s) provided \"resistance\" parameter. Provided layers incorporated abs(resistance - 1) multiplied prediction. Adaptability: nichelimit - Specifies limit environmental niche allow modest amount extrapolation beyond known occurrences. can particular useful limit influence increasing marginal responses avoid biologically unrealistic projections. Boundary size: boundary - Applies hard boundary constraint projection, thus disallowing expansion range outside provide layer. Similar specifying projection limits (see distribution), can used specifically constrain projection within certain area (e.g. species range island). minsize - Allows specify certain size must satisfied order thresholded patch occupied. Can thought minimum size requirement. See add_constraint_minsize() required parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a constraint to an existing scenario — add_constraint","text":"Bateman, B. L., Murphy, H. T., Reside, . E., Mokany, K., & VanDerWal, J. (2013). Appropriateness full‐, partial‐‐dispersal scenarios climate change impact modelling. Diversity Distributions, 19(10), 1224-1234. Nobis MP Normand S (2014) KISSMig - simple model R account limited migration analyses species distributions. Ecography 37: 1282-1287. Mendes, P., Velazco, S. J. E., de Andrade, . F. ., & Júnior, P. D. M. (2020). Dealing overprediction species distribution models: adding distance constraints can improve model accuracy. Ecological Modelling, 431, 109180.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a constraint to an existing scenario — add_constraint","text":"","code":"if (FALSE) { # Assumes that a trained 'model' object exists  mod <- scenario(model) |>   add_predictors(env = predictors, transform = 'scale', derivates = \"none\") |>   add_constraint_dispersal(method = \"kissmig\", value = 2, pext = 0.1) |>   project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":null,"dir":"Reference","previous_headings":"","what":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"function adds constrain defined MigClim approach (Engler et al. 2013) BiodiversityScenario object constrain future projections. detailed description MigClim, please respective reference UserGuide. default parameters chosen suggestions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"","code":"add_constraint_MigClim(   mod,   rcThresholdMode = \"continuous\",   dispSteps = 1,   dispKernel = c(1, 0.4, 0.16, 0.06, 0.03),   barrierType = \"strong\",   lddFreq = 0,   lddRange = c(1000, 10000),   iniMatAge = 1,   propaguleProdProb = c(0.2, 0.6, 0.8, 0.95),   replicateNb = 10,   dtmp = terra::terraOptions(print = F)$tempdir )  # S4 method for BiodiversityScenario add_constraint_MigClim(   mod,   rcThresholdMode = \"continuous\",   dispSteps = 1,   dispKernel = c(1, 0.4, 0.16, 0.06, 0.03),   barrierType = \"strong\",   lddFreq = 0,   lddRange = c(1000, 10000),   iniMatAge = 1,   propaguleProdProb = c(0.2, 0.6, 0.8, 0.95),   replicateNb = 10,   dtmp = terra::terraOptions(print = F)$tempdir )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"mod BiodiversityScenario object specified predictors. rcThresholdMode character either binary continuous value (Default: continuous). dispSteps numeric parameters number dispersal steps. Dispersal steps executed timestep (prediction layer). ideally aligned number steps projection. Minimum 1 (Default) maximum 99. dispKernel vector number dispersal Kernel applied. Can set either uniform numeric vector, e.g. c(1,1,1,1) proportional decline (1,0.4,0.16,0.06,0.03) (Default). Depending resolution raster, parameter needs adapted barrierType character indicating whether set barrier set 'strong' 'weak' barriers. Strong barriers prevent dispersal across barrier weak barriers whole \"dispKernel\" length covered barrier (Default: 'strong'). lddFreq numeric parameter indicating frequency long-distance dispersal (LDD) events. Default 0, long-distance dispersal. lddRange numeric value highlighting minimum maximum distance LDD events. Note: units distance cells, thus projection units raster. iniMatAge Initial maturity age. Used together propaguleProd proxy population growth. Must set cell age time units dispersal steps (Default: 1). propaguleProdProb Probability source cell produce propagules function time since colonization. Set probability vector defines probability cell producing propagules. replicateNb Number replicates used analysis (Default: 10). dtmp character folder temporary files created.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"Adds MigClim onstrain BiodiversityScenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"barrier parameter defined \"add_barrier\".","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"Engler R., Hordijk W. Guisan . MIGCLIM R package – seamless integration dispersal constraints projections species distribution models. Ecography, Robin Engler, Wim Hordijk Loic Pellissier (2013). MigClim: Implementing dispersal species distribution models. R package version 1.6.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"","code":"if (FALSE) { # Assumes that a trained 'model' object exists  mod <- scenario(model) |>   add_predictors(env = predictors, transform = 'scale',                  derivates = \"none\") |>   add_constraint_MigClim() |>   project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"Adaptability constraints assume suitable habitat species (future) projections might unsuitable outside range conditions currently observed species. Currently nichelimit implemented, adds simple constrain predictor parameter space, can defined \"value\" parameter. example setting 1 (Default), projections constrained within range maximum 1 standard deviation range covariates used model training.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"","code":"add_constraint_adaptability(   mod,   method = \"nichelimit\",   names = NULL,   value = 1,   increment = 0,   ... )  # S4 method for BiodiversityScenario add_constraint_adaptability(   mod,   method = \"nichelimit\",   names = NULL,   value = 1,   increment = 0,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. names character vector names predictors adaptability threshold set (Default: NULL ). value numeric value units standard deviation (Default: 1). increment numeric constant added value every time step (Default: 0). Allows incremental widening niche space, thus opening constraints. ... passed parameters. See also specific methods adding constraints.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"","code":"if (FALSE) { scenario(fit) |>  add_constraint_adaptability(value = 1) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a boundary constraint to a scenario object — add_constraint_boundary","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"purpose boundary constraints limit future projection within specified area (example range ecoregion). can help limit unreasonable projections geographic space. Similar boundary constraints also possible define \"zone\" scenario projections, similar done model training. difference boundary constraint boundary constraint applied posthoc hard cut projection, zones allow projection (constraints) applied within zone. Note: Setting boundary constraint future projections effectively potentially suitable areas!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"","code":"add_constraint_boundary(mod, layer, ...)  # S4 method for BiodiversityScenario,sf add_constraint_boundary(mod, layer, method = \"boundary\", ...)  # S4 method for BiodiversityScenario,ANY add_constraint_boundary(mod, layer, method = \"boundary\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"mod BiodiversityScenario object specified predictors. layer SpatRaster sf object extent model background. binary used posthoc masking projected grid cells. ... passed parameters. See also specific methods adding constraints. method character indicating type constraints added scenario. See details information.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"","code":"if (FALSE) { # Add scenario constraint scenario(fit) |> add_constraint_boundary(range) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_connectivity.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","title":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","text":"Adds connectivity constraint scenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_connectivity.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","text":"","code":"add_constraint_connectivity(mod, method, value = NULL, resistance = NULL, ...)  # S4 method for BiodiversityScenario add_constraint_connectivity(mod, method, value = NULL, resistance = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_connectivity.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. value many dispersal \"constrain\" set numeric value specifying fixed constrain constant units \"m\" (Default: NULL). kissmig value needs give number iteration steps (within year migration steps). adaptability constraints parameter specifies extent (units standard deviation) extrapolations performed. resistance SpatRaster object describing resistance surface barrier use connectivity constrains (Default: NULL). ... passed parameters. See also specific methods adding constraints.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":null,"dir":"Reference","previous_headings":"","what":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"Add dispersal constraint existing scenario","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"","code":"add_constraint_dispersal(mod, method, value = NULL, type = NULL, ...)  # S4 method for BiodiversityScenario add_constraint_dispersal(mod, method, value = NULL, type = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. value many dispersal \"constrain\" set numeric value specifying fixed constrain constant units \"m\" (Default: NULL). kissmig value needs give number iteration steps (within year migration steps). adaptability constraints parameter specifies extent (units standard deviation) extrapolations performed. type character indicating type used method. See instance `kissmig`. ... passed parameters. See also specific methods adding constraints.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"following additional parameters can bet set: pext: numeric indicator `kissmig` probability colonized cell becomes uncolonised, .e., species gets locally extinct (Default: 0.1). pcor: numeric probability corner cells considered 3x3 neighbourhood (Default: 0.2).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a size constraint on a scenario — add_constraint_minsize","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"function applies minimum size constraint scenario() created object. rationale given species isolated habitat patches smaller given size might viable / unrealistic species establish (long-term) presence. idea thus apply constraint patches bigger certain size retained timesteps. thus potential reduce subsequent colonizations neighbouring patches.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"","code":"add_constraint_minsize(   mod,   value,   unit = \"km2\",   establishment_step = FALSE,   ... )  # S4 method for BiodiversityScenario,numeric add_constraint_minsize(   mod,   value,   unit = \"km2\",   establishment_step = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"mod BiodiversityScenario object specified predictors. value numeric value describing minimum amount area given patch unit character unit area. Options available km2 (Default) ha. establishment_step logical flag indicating whether given patch removed small previous time step (yet implemented!) ... passed parameters. See also specific methods adding constraints.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"Area values specific unit need supplied.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"function requires scenario set threshold()!","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"","code":"if (FALSE) { scenario(fit) |>  add_predictors(future_covariates) |>  threshold() |>  add_constraint_minsize(value = 1000, unit = \"km2\") |>  project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a control to a BiodiversityModel object to control biases — add_control_bias","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Sampling biases pervasive drivers spatial location biodiversity datasets. integration , presumably less biased data can one way controlling sampling biases, another way control directly bias model. Currently supported methods : \"partial\" - approach described Warton et al. (2013) control biases model, including specified variable (\"layer\") model, \"partialling\" projection phase. Specifically variable set specified value (\"bias_value\"), default minimum value observed across background. \"offset\" - Dummy method points add_offset_bias() functionality (see note). Makes use offsets factor specified bias variable. \"proximity\" - Use proximity distance points weight model. option effectively places greater weight points farther away. Note: best case can control spatial bias aggregation, worst case can place lot emphasis points likely outliers misidentification (terms species). See also details explanations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"","code":"add_control_bias(   x,   layer,   method = \"partial\",   bias_value = NULL,   maxdist = NULL,   alpha = 1,   add = TRUE )  # S4 method for BiodiversityDistribution add_control_bias(   x,   layer,   method = \"partial\",   bias_value = NULL,   maxdist = NULL,   alpha = 1,   add = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. Specify variable already added \"x\" avoid issues duplications. method character vector describing method used bias control. Available options \"partial\" (Default), \"offset\" \"proximity\". bias_value numeric value \"layer\". Specifying numeric value sets layer target value projection. default value set minimum value found layer (Default: NULL). maxdist numeric giving maximum distance method \"proximity\" used. unset uses default distance centroid minimum convex polygon encircling points. alpha numeric given initial weight points method \"proximity\" used (Default: 1). example, set values smaller 1 neighbouring points weighted less. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Adds bias control option distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"case \"proximity\" weights assigned point, placing higher weight points away less overlap. Weights assigned maximum distance can provided user (parameter \"maxdist\"). distance ideally informed knowledge species modelled (e.g., maximum dispersal distance). provided, set distance centroid minimum convex polygon encircling observations. parameter \"alpha\" weighting factor can used diminish effect neighboring points.  given observation \\(\\), weight \\(w\\) defined $$w_i = 1 / (1 + \\epsilon)$$ $$\\epsilon = \\sum_{n=1}^{N}((1 - d_n)/d_sac)^\\alpha$$ \\(N\\) total number points closer maximum distance (\\(d_sac\\)) point \\(\\), \\(d_n\\) distance focal point \\(\\) point \\(n\\).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Covariate transformations applied predictors need applied bias . Another option consider biases particular Poisson-point process models remove offset. Functionality available add_offset_bias() method. Setting method \"offset\" automatically point option.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Warton, D.., Renner, .W. Ramp, D., 2013. Model-based control observer bias analysis presence-data ecology. PloS one, 8(11), p.e79168. Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453 Botella, C., Joly, ., Bonnet, P., Munoz, F., & Monestiez, P. (2021). Jointly estimating spatial sampling effort habitat suitability multiple species opportunistic presence‐data. Methods Ecology Evolution, 12(5), 933-945.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_predictors(covariates) |>    add_control_bias(biasvariable, bias_value = NULL) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"One main aims species distribution models (SDMs) project space time. projections common issue extrapolation - unconstrained - SDMs can indicate areas suitable unlikely occupied species habitats (often due historic biotic factors). extent can related insufficient quantification niche (e.g. niche truncation considering subset observations within actual distribution), cases can also general barriers constraints limit projections (e.g. islands). control method adds options model distribution object. Currently supported methods : * \"zones\" - wrapper allow addition zones distribution model object, similar also possible via distribution(). Required spatial layer describes environmental zoning. * \"mcp\" - Rather using external additional layer, option constraints predictions certain distance points vicinity. Buffer distances unit projection used can configured via \"mcp_buffer\". * \"nt2\" - Constraints predictions using multivariate combination novelty index (NT2) following Mesgaran et al. (2014). method also available similarity() function. * \"shape\" - implementation 'shape' method introduced Velazco et al. (2023). user defined threshold effectively limits model extrapolation projections made beyond extent judged defensible informed training observations. See also details explanations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"","code":"add_control_extrapolation(   x,   layer,   method = \"mcp\",   mcp_buffer = 0,   novel = \"within\",   limits_clip = FALSE )  # S4 method for BiodiversityDistribution add_control_extrapolation(   x,   layer,   method = \"mcp\",   mcp_buffer = 0,   novel = \"within\",   limits_clip = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"x distribution() (.e. BiodiversityDistribution) object. layer SpatRaster sf object limits prediction surface intersected input data (Default: NULL). method character vector describing method used controlling extrapolation. Available options \"zones\", \"mcp\" (Default), \"nt2\" \"shape\". mcp_buffer numeric distance buffer mcp (Default 0). used \"mcp\" used. novel conditions masked respectively, either novel conditions within \"within\" (Default) also including outside reference conditions \"outside\". use method = \"nt2\", method = \"mess\" variable always \"within\". limits_clip logical limits clip predictors fitting model (TRUE) just prediction (FALSE, default).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"Adds extrapolation control option distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"method \"zones\" zoning layer can supplied used intersect provided training points . projections made model can constrained project areas consider training points unlikely . Examples zones separation islands mainlands, biomes, lithological soil conditions. layer available, also possible constraint predictions distance minimum convex polygon surrounding training points method \"mcp\" (optionally buffered). can make sense particular rare species fully sampled across niche. \"NT2\" \"MESS\" index possible constrain prediction conditions within (novel = \"within\") also include outside (novel = \"outside\") conditions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"method \"zones\" also possible directly within distribution().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"Randin, C. F., Dirnböck, T., Dullinger, S., Zimmermann, N. E., Zappa, M., & Guisan, . (2006). niche‐based species distribution models transferable space?. Journal biogeography, 33(10), 1689-1703. https://doi.org/10.1111/j.1365-2699.2006.01466.x Chevalier, M., Broennimann, O., Cornuault, J., & Guisan, . (2021). Data integration methods account spatial niche truncation effects regional projections species distribution. Ecological Applications, 31(7), e02427. https://doi.org/10.1002/eap.2427 Velazco, S. J. E., Brooke, M. R., De Marco Jr., P., Regan, H. M., & Franklin, J. (2023). far can extrapolate species distribution model? Exploring Shape, novel method. Ecography, 11, e06992. https://doi.org/10.1111/ecog.06992 Mesgaran, M. B., R. D. Cousens, B. L. Webber, J. Franklin. (2014) dragons: tool quantifying novelty due covariate range correlation change projecting species distribution models. Diversity Distributions 20:1147-1159.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"","code":"if (FALSE) {  # To add a zone layer for extrapolation constraints.  x <- distribution(background) |>    add_predictors(covariates) |>    add_control_extrapolation(method = \"zones\", layer = zones) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":null,"dir":"Reference","previous_headings":"","what":"Add latent spatial effect to the model equation — add_latent_spatial","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"general understand latent spatial effects occurrence spatial dependency observations, might either caused spatial biases, similarities underlying sampling processes unmeasured latent covariates, e.g. quantified. package supports range different spatial effects, however differ another impact estimated prediction. effects simply add spatial dependence covariate, others make use spatial random effects account spatial dependence predictions. default effects added dataset covariate shared spatial field (e.g. SPDE). See details explanation available options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"","code":"add_latent_spatial(   x,   method = \"spde\",   priors = NULL,   separate_spde = FALSE,   ... )  # S4 method for BiodiversityDistribution add_latent_spatial(   x,   method = \"spde\",   priors = NULL,   separate_spde = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"x distribution() (.e. BiodiversityDistribution) object. method character describing kind spatial effect added model. See details. priors \"Prior-List\" object supplied latent effect. Relevant engine_inla NULL equates use default priors. separate_spde logical parameter indicating whether, case SPDE effects, separate effects likelihood fitted. Default (FALSE) uses copy first added likelihood. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"Adds latent spatial effect distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"several different options depend engine used. case unsupported method engine chosen modified next similar method. Available : \"spde\" - stochastic partial differential equation (SPDE) engine_inla engine_inlabru. SPDE effects aim capturing variation response variable space, covariates accounted . Examining spatial distribution spatial error can reveal covariates might missing. example, elevation positively correlated response variable, included model, see higher posterior mean areas higher elevation. Note calculations SPDE's can computationally costly. \"car\" - conditional autocorrelative errors (CAR) engine_inla. yet implemented full. \"kde\" - additional covariate kernel density input point observations. \"poly\" - spatial trend correction adding coordinates polynominal transformation. method assumed transformation spatial coordinates can - included additional predictor - explain variance distribution. method interact species occurrences. \"nnd\" - nearest neighbour distance. function calculates euclidean distance point nearest grid cell known species occurrence. Originally proposed Allouche et al. (2008) can applied across datasets BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"Allouche, O.; Steinitz, O.; Rotem, D.; Rosenfeld, .; Kadmon, R. (2008). Incorporating distance constraints species distribution models. Journal Applied Ecology, 45(2), 599-609. doi:10.1111/j.1365-2664.2007.01445.x Mendes, P., Velazco, S. J. E., de Andrade, . F. ., & Júnior, P. D. M. (2020). Dealing overprediction species distribution models: adding distance constraints can improve model accuracy. Ecological Modelling, 431, 109180.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"","code":"if (FALSE) {  distribution(background) |> add_latent_spatial(method = \"poly\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a log file to distribution object — add_log","title":"Adds a log file to distribution object — add_log","text":"function allows specify file Log file, used save console outputs, prints messages.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a log file to distribution object — add_log","text":"","code":"add_log(x, filename)  # S4 method for BiodiversityDistribution,character add_log(x, filename)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a log file to distribution object — add_log","text":"x distribution() (.e. BiodiversityDistribution) object. filename character object. destination must writeable filename ends 'txt'.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Adds a log file to distribution object — add_log","text":"Adds log file distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds a log file to distribution object — add_log","text":"","code":"if (FALSE) {  x <- distribution(background) |>     add_log()  x }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify a spatial explicit offset — add_offset","title":"Specify a spatial explicit offset — add_offset","text":"Including offsets another option integrate spatial prior information linear additive regression models. Offsets shift intercept regression fit certain amount. Although one offset can added regression model, possible combine several spatial-explicit estimates one offset calculating sum spatial-explicit layers.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify a spatial explicit offset — add_offset","text":"","code":"add_offset(x, layer, add = TRUE)  # S4 method for BiodiversityDistribution,SpatRaster add_offset(x, layer, add = TRUE)  # S4 method for BiodiversityDistribution,sf add_offset(x, layer, add = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify a spatial explicit offset — add_offset","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify a spatial explicit offset — add_offset","text":"Adds offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify a spatial explicit offset — add_offset","text":"function allows set specific offset regression model. offset provided spatial SpatRaster object. function simply adds layer distribution() object. Note transformation offset (log) done externally! layer range requires additional formatting, consider using function add_offset_range() additional functionalities distance transformations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Specify a spatial explicit offset — add_offset","text":"Since offsets make sense linear regressions (instance regression tree based methods engine_bart), work engines. Offsets specified non-supported engines ignored estimation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify a spatial explicit offset — add_offset","text":"Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify a spatial explicit offset — add_offset","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_predictors(covariates) |>    add_offset(nicheEstimate) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify a spatial explicit offset as bias — add_offset_bias","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"Including offsets another option integrate spatial prior information linear additive regression models. Offsets shift intercept regression fit certain amount. Although one offset can added regression model, possible combine several spatial-explicit estimates one offset calculating sum spatial-explicit layers.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"","code":"add_offset_bias(x, layer, add = TRUE, points = NULL)  # S4 method for BiodiversityDistribution,SpatRaster add_offset_bias(x, layer, add = TRUE, points = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE). points optional sf object key points. location points used calculate probability cell sampled accounting area differences. (Default: NULL).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"Adds bias offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"functions emulates use add_offset() function, however applies inverse transformation remove provided layer overall offset. instance offset already specified (area), function removes provided bias.layer via \"offset(log(.area)-log(bias.layer))\" Note transformation offset (log) done externally! generic offset added, consider using add_offset() function. layer expert-based range requires additional parametrization, consider using function add_offset_range() bossMaps R-package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_predictors(covariates) |>    add_offset_bias(samplingBias) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify elevational preferences as offset — add_offset_elevation","title":"Specify elevational preferences as offset — add_offset_elevation","text":"function implements elevation preferences offset defined Ellis‐Soto et al. (2021). code adapted Supporting materials script.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify elevational preferences as offset — add_offset_elevation","text":"","code":"add_offset_elevation(x, elev, pref, rate = 0.0089, add = TRUE)  # S4 method for BiodiversityDistribution,SpatRaster,numeric add_offset_elevation(x, elev, pref, rate = 0.0089, add = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify elevational preferences as offset — add_offset_elevation","text":"x distribution() (.e. BiodiversityDistribution) object. elev SpatRaster elevation given background. pref numeric vector length 2 giving lower upper bound known elevational preferences. Can set Inf unknown. rate numeric rate used offset (Default: .0089). parameter specifies decay near zero probability elevation expert limits. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify elevational preferences as offset — add_offset_elevation","text":"Adds elevational offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify elevational preferences as offset — add_offset_elevation","text":"Specifically functions calculates continuous decay decreasing probability species occur elevation limits. requires SpatRaster elevation information. generalized logistic transform (aka Richard's curve) used calculate decay suitable elevational areas, \"rate\" parameter allowing vary steepness decline. Note offsets created function default log-transformed export. addition function also mean-centers output recommended Ellis-Soto et al.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify elevational preferences as offset — add_offset_elevation","text":"Ellis‐Soto, D., Merow, C., Amatulli, G., Parra, J.L., Jetz, W., 2021. Continental‐scale 1 km hummingbird diversity derived fusing point records lateral elevational expert information. Ecography (Cop.). 44, 640–652. https://doi.org/10.1111/ecog.05119 Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify elevational preferences as offset — add_offset_elevation","text":"","code":"if (FALSE) {  # Adds the offset to a distribution object  distribution(background) |> add_offset_elevation(dem, pref = c(400, 1200)) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify a expert-based species range as offset — add_offset_range","title":"Specify a expert-based species range as offset — add_offset_range","text":"function additional options compared generic add_offset(), allowing customized options specifically expert-based ranges offsets spatialized polygon information species occurrences. even control needed, user informed \"bossMaps\" package Merow et al. (2017). functionalities package emulated \"distance_function\" set \"log\". tries fit 5-parameter logistic function estimate distance range (Merow et al. 2017).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify a expert-based species range as offset — add_offset_range","text":"","code":"add_offset_range(   x,   layer,   distance_max = Inf,   family = \"poisson\",   presence_prop = 0.9,   distance_clip = FALSE,   distance_function = \"negexp\",   field_occurrence = \"observed\",   fraction = NULL,   point = FALSE,   add = TRUE )  # S4 method for BiodiversityDistribution,SpatRaster add_offset_range(x, layer, fraction = NULL, add = TRUE)  # S4 method for BiodiversityDistribution,sf add_offset_range(   x,   layer,   distance_max = Inf,   family = \"poisson\",   presence_prop = 0.9,   distance_clip = FALSE,   distance_function = \"negexp\",   field_occurrence = \"observed\",   fraction = NULL,   point = FALSE,   add = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify a expert-based species range as offset — add_offset_range","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. distance_max numeric threshold maximum distance beyond range considered high likelihood containing species occurrences (Default: Inf \"m\"). Can set NULL 0 indicate distance calculated. family character denoting type model offset added. default assumes 'poisson' distributed model result output created function log-transformed. however 'binomial' distribution chosen, output `logit` transformed. integrated models leave default. presence_prop numeric giving proportion records expected inside range. default set 0.9 indicating 10% records likely outside range. distance_clip logical whether distance clipped maximum distance (Default: FALSE). distance_function character specifying distance function used. Available linear (\"linear\"), negative exponential kernels (\"negexp\", default) five parameters logistic curve (code\"logcurve\") proposed Merow et al. 2017. field_occurrence numeric character location biodiversity point records. fraction optional SpatRaster object multiplied digitized raster layer. Can used example remove reduce expected value (Default: NULL). point optional sf layer points logical argument. case latter point data ignored (Default: FALSE). add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify a expert-based species range as offset — add_offset_range","text":"Adds range offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify a expert-based species range as offset — add_offset_range","text":"output created function creates SpatRaster added provided distribution object. Offsets regression models likelihood specific added directly overall estimate `y^hat`. Note offsets created function default log-transformed export. Background values (e.g. beyond \"distance_max\") set small constant (1e-10).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify a expert-based species range as offset — add_offset_range","text":"Merow, C., Wilson, .M., Jetz, W., 2017. Integrating occurrence data expert maps improved species range predictions. Glob. Ecol. Biogeogr. 26, 243–258. https://doi.org/10.1111/geb.12539 Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify a expert-based species range as offset — add_offset_range","text":"","code":"if (FALSE) {  # Train a presence-only model with a simple offset  fit <- distribution(background) |>  add_biodiversity_poipo(virtual_points, field_occurrence = \"Observed\") |>  add_predictors(predictors) |>  add_offset_range(virtual_range, distance_max = 5,distance_function = \"logcurve\",  distance_clip = TRUE ) |>  engine_glm() |>  train() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":null,"dir":"Reference","previous_headings":"","what":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"Create lower upper limits elevational range add separate predictors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"","code":"add_predictor_elevationpref(x, layer, lower, upper, transform = \"none\")  # S4 method for BiodiversityDistribution,ANY,numeric,numeric add_predictor_elevationpref(x, layer, lower, upper, transform = \"none\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"x distribution() (.e. BiodiversityDistribution) object. layer character stating elevational layer Distribution object SpatRaster object. lower numeric value lower elevational preference species. upper numeric value upper elevational preference species. transform character optional transformation applied. Usually needed (Default: \"none\").","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"","code":"if (FALSE) { distribution(background) |>   add_predictor_elevationpref(elevation, lower = 200, upper = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a range of a species as predictor to a distribution object — add_predictor_range","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"function allows add species range usually drawn experts separate process spatial explicit prior. sf SpatRaster-objects supported input. Users advised look \"bossMaps\" R-package presented part Merow et al. (2017), allows flexible calculation non-linear distance transforms boundary range. Outputs package added directly function. Note function adds range predictor offset. purpose separate function add_offset_range() exists. Additional options allow include range either \"binary\" \"distance\" transformed predictor. difference range either directly included presence-predictor alternatively linear distance transform range boundary. parameter \"distance_max\" can specified constrain distance transform.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"","code":"add_predictor_range(   x,   layer,   method = \"distance\",   distance_max = NULL,   fraction = NULL,   priors = NULL )  # S4 method for BiodiversityDistribution,SpatRaster add_predictor_range(   x,   layer,   method = \"precomputed_range\",   fraction = NULL,   priors = NULL )  # S4 method for BiodiversityDistribution,sf add_predictor_range(   x,   layer,   method = \"distance\",   distance_max = Inf,   fraction = NULL,   priors = NULL )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. method character describing range included (\"binary\" | \"distance\"). distance_max Numeric threshold maximum distance (Default: NULL). fraction optional SpatRaster object multiplied digitized raster layer. Can used example remove reduce expected value (Default: NULL). priors PriorList object. Default set NULL uses default prior assumptions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"Merow, C., Wilson, . M., & Jetz, W. (2017). Integrating occurrence data expert maps improved species range predictions. Global Ecology Biogeography, 26(2), 243–258. https://doi.org/10.1111/geb.12539","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"","code":"if (FALSE) { distribution(background) |>   add_predictor_range(range, method = \"distance\", distance_max = 2) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":null,"dir":"Reference","previous_headings":"","what":"Add predictors to a Biodiversity distribution object — add_predictors","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"function allows add predictors distribution BiodiversityScenario objects. Predictors covariates spatial projection match geographic projection background layer distribution object. function furthermore allows transform create derivates provided predictors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"","code":"add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,SpatRasterCollection add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,SpatRaster add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,stars add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityScenario,SpatRaster add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityScenario,stars add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"x distribution() (.e. BiodiversityDistribution) object. env SpatRaster stars object. names vector character names describing environmental stack case renamed. transform vector stating whether predictors preprocessed way (Options: 'none','pca', 'scale', 'norm') derivates Boolean check whether derivate features considered (Options: 'none', 'thresh', 'hinge', 'quad') ) derivate_knots single numeric vector giving number knots derivate creation relevant (Default: 4). int_variables vector length greater equal 2 specifying covariates (Default: NULL). bgmask Check whether environmental data masked background layer (Default: TRUE). harmonize_na logical value indicating whether NA values harmonized among predictors (Default: FALSE). explode_factors logical whether factor variables split binary variables (one per class). (Default: FALSE). priors PriorList object. Default set NULL uses default prior assumptions. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"transformation takes provided rasters instance rescales transforms principal component analysis (prcomp). contrast, derivates leave original provided predictors alone, instead create new ones, instance transforming values quadratic hinge transformation. Note effectively increases number predictors object, generally requiring stronger regularization used Engine. transformations derivates can also combined. Available options transformation : 'none' - Leaves provided predictors original scale. 'pca' - Converts predictors principal components. Note results renaming variables principal component axes! 'scale' - Transforms predictors applying scale . 'norm' - Normalizes predictors transforming scale 0 1. 'windsor' - Applies windsorization target predictors. default effectively cuts predictors 0.05 0.95, thus helping remove extreme outliers. Available options creating derivates : 'none' - additional predictor derivates created. 'quad' - Adds quadratic transformed predictors. 'interaction' - Add interacting predictors. Interactions need specified (\"int_variables\")! 'thresh' - Add threshold transformed predictors. 'hinge' - Add hinge transformed predictors. 'bin' - Add predictors binned percentiles.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"Important: every Engine supported ibis.iSDM R-package allows missing data points among extracted covariates. Thus observation missing data generally removed prior model fitting. Thus ensure covariates appropriate -data settings (instance setting NA values 0 another range constant). every engine actually need covariates. instance perfectly legit fit model occurrence data spatial latent effect (add_latent_spatial). correspondents spatial kernel density estimate. Certain names \"offset\" forbidden predictor variable names. function return error message used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"","code":"if (FALSE) {  obj <- distribution(background) |>         add_predictors(covariates, transform = 'scale')  obj }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":null,"dir":"Reference","previous_headings":"","what":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"customized function format add downscaled land-use shares Global Biosphere Management Model (GLOBIOM) distribution BiodiversityScenario ibis.iSDM. GLOBIOM partial-equilibrium model developed IIASA represents land-use sectors rich set environmental socio-economic parameters, instance agricultural forestry sector estimated dedicated process-based models. GLOBIOM outputs spatial explicit usually half-degree resolution globally. finer grain analyses GLOBIOM outputs can produced downscaled format customized statistical downscaling module. purpose script format GLOBIOM outputs DownScale use ibis.iSDM package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"","code":"add_predictors_globiom(   x,   fname,   names = NULL,   transform = \"none\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,character add_predictors_globiom(   x,   fname,   names = NULL,   transform = \"none\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityScenario,character add_predictors_globiom(   x,   fname,   names = NULL,   transform = \"none\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   priors = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"x BiodiversityDistribution BiodiversityScenario object. fname character pointing netCDF GLOBIOM data. names vector character names describing environmental stack case renamed (Default: NULL). transform vector stating whether predictors preprocessed way (Options: 'none','pca', 'scale', 'norm') derivates Boolean check whether derivate features considered (Options: 'none', 'thresh', 'hinge', 'quad') ) derivate_knots single numeric vector giving number knots derivate creation relevant (Default: 4). int_variables vector length greater equal 2 specifying covariates (Default: NULL). bgmask Check whether environmental data masked background layer (Default: TRUE) harmonize_na logical value indicating whether NA values harmonized among predictors (Default: FALSE) priors PriorList object. Default set NULL uses default prior assumptions. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"See add_predictors() additional parameters customizations. (manual) control function formatting GLOBIOM data can also called directly via formatGLOBIOM().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"","code":"if (FALSE) {  obj <- distribution(background) |>         add_predictors_globiom(fname = \"\", transform = 'none')  obj }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":null,"dir":"Reference","previous_headings":"","what":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"function convenience wrapper add output previous fitted DistributionModel another BiodiversityDistribution object. Obviously works prediction fitted model. Options instead add thresholds, transform / derivate model outputs also supported.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"","code":"add_predictors_model(   x,   model,   transform = \"scale\",   derivates = \"none\",   threshold_only = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution add_predictors_model(   x,   model,   transform = \"scale\",   derivates = \"none\",   threshold_only = FALSE,   priors = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"x distribution() (.e. BiodiversityDistribution) object. model DistributionModel object. transform vector stating whether predictors preprocessed way (Options: 'none','pca', 'scale', 'norm') derivates Boolean check whether derivate features considered (Options: 'none', 'thresh', 'hinge', 'quad') ) threshold_only logical flag indicating whether add thresholded layers fitted model (existing) instead (Default: FALSE). priors PriorList object. Default set NULL uses default prior assumptions. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"transformation takes provided rasters instance rescales transforms principal component analysis (prcomp). contrast, derivates leave original provided predictors alone, instead create new ones, instance transforming values quadratic hinge transformation. Note effectively increases number predictors object, generally requiring stronger regularization used Engine. transformations derivates can also combined. Available options transformation : 'none' - Leaves provided predictors original scale. 'pca' - Converts predictors principal components. Note results renaming variables principal component axes! 'scale' - Transforms predictors applying scale . 'norm' - Normalizes predictors transforming scale 0 1. 'windsor' - Applies windsorization target predictors. default effectively cuts predictors 0.05 0.95, thus helping remove extreme outliers. Available options creating derivates : 'none' - additional predictor derivates created. 'quad' - Adds quadratic transformed predictors. 'interaction' - Add interacting predictors. Interactions need specified (\"int_variables\")! 'thresh' - Add threshold transformed predictors. 'hinge' - Add hinge transformed predictors. 'bin' - Add predictors binned percentiles.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"","code":"if (FALSE) {  # Fit first model  fit <- distribution(background) |>         add_predictors(covariates) |>         add_biodiversity_poipa(species) |>         engine_glmnet() |>         train()   # New model object  obj <- distribution(background) |>         add_predictors_model(fit)  obj }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Add priors to an existing distribution object — add_priors","title":"Add priors to an existing distribution object — add_priors","text":"function simply allows add priors existing distribution object. supplied priors must PriorList object created calling priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add priors to an existing distribution object — add_priors","text":"","code":"add_priors(x, priors = NULL, ...)  # S4 method for BiodiversityDistribution add_priors(x, priors = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add priors to an existing distribution object — add_priors","text":"x distribution (.e. BiodiversityDistribution) object. priors PriorList object containing multiple priors. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add priors to an existing distribution object — add_priors","text":"Alternatively priors environmental predictors can also directly added parameter via add_predictors","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add priors to an existing distribution object — add_priors","text":"","code":"if (FALSE) {  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":null,"dir":"Reference","previous_headings":"","what":"Add pseudo-absence points to a point data set — add_pseudoabsence","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"engines, background pseudo-absence points necessary. distinction lies absence data handled. poisson distributed responses, absence points considered background points intensity sampling (lambda) integrated (classical Poisson point-process model). contrast binomial distributed responses, absence information assumed adequate representation true absences treated model ... advised specify absence points way represent potential true absence, example targeted background sampling sampling within/outside given range.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"","code":"add_pseudoabsence(   df,   field_occurrence = \"observed\",   template = NULL,   settings = getOption(\"ibis.pseudoabsence\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"df sf, data.frame tibble object containing point data. field_occurrence character name column containing presence information (Default: observed). template SpatRaster object aligned predictors (Default: NULL). set NULL, background pseudoabs_settings() SpatRaster object. settings pseudoabs_settings() objects. Absence settings taken ibis_options otherwise (Default).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"data.frame containing newly created pseudo absence points.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"pseudoabs_settings() object can added setup absence points sampled. bias parameter can set specify bias layer sample , instance layer accessibility. Note modelling several datasets, might make sense check across datasets whether certain areas truly absent. default, pseudo-absence points sampled areas already presence points.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"method removes columns input df object field_occurrence column coordinate columns (created already present).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"Stolar, J., & Nielsen, S. E. (2015). Accounting spatially biased sampling effort presence‐species distribution modelling. Diversity Distributions, 21(5), 595-608. Bird, T.J., Bates, .E., Lefcheck, J.S., Hill, N.., Thomson, R.J., Edgar, G.J., Stuart-Smith, R.D., Wotherspoon, S., Krkosek, M., Stuart-Smith, J.F. Pecl, G.T., 2014. Statistical solutions error bias global citizen science datasets. Biological Conservation, 173, pp.144-154.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":null,"dir":"Reference","previous_headings":"","what":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"data projection template, alignment computed reprojection . data already projection, data set cropped aggregated prior resampling order reduce computation time.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"","code":"alignRasters(data, template, method = \"bilinear\", func = mean, cl = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"data SpatRaster object resampled. template SpatRaster sf object geometry can extracted. method method resampling (Options: \"near\" \"bilinear\"). func function resampling (Default: mean). cl logical value multicore computation used (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"New SpatRaster object aligned supplied template layer.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"Nearest Neighbour resampling (near) recommended discrete bilinear resampling recommended continuous data. See also help terra::resample options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"","code":"if (FALSE) {  # Align one raster to another  ras1 <- alignRasters( ras1, ras2, method = \"near\", cl = FALSE) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/as.Id.html","id":null,"dir":"Reference","previous_headings":"","what":"As Id — as.Id","title":"As Id — as.Id","text":"Id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/as.Id.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"As Id — as.Id","text":"","code":"as.Id(x, ...)  # S3 method for character as.Id(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/as.Id.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"As Id — as.Id","text":"x character converted id. ... arguements","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":null,"dir":"Reference","previous_headings":"","what":"Bivariate plot wrapper for distribution objects — bivplot","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"Often intention display predictions made SDM, also uncertainty prediction. Uncertainty estimated either directly model calculating variation prediction values among set models. particular Bayesian engines can produce mean estimates fitted responses, also pixel-based estimates uncertainty posterior standard deviation (SD) coefficient variation given prediction. function makes use \"biscale\" R-package create bivariate plots fitted distribution object, allowing visualize two variables . mostly thought convenience function create bivariate plots quick visualization. Supported Inputs either single trained Bayesian DistributionModel uncertainty output ensemble() call. cases, users make sure \"xvar\" \"yvar\" set accordingly.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"","code":"bivplot(   mod,   xvar = \"mean\",   yvar = \"sd\",   plot = TRUE,   fname = NULL,   title = NULL,   col = \"BlueGold\",   ... )  # S4 method for ANY bivplot(   mod,   xvar = \"mean\",   yvar = \"sd\",   plot = TRUE,   fname = NULL,   title = NULL,   col = \"BlueGold\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"mod trained DistributionModel alternatively SpatRaster object prediction model within. xvar character denoting value x-axis (Default: 'mean'). yvar character denoting value y-axis (Default: 'sd'). plot logical indication whether result plotted (Default: TRUE)? fname character specifying output filename created figure written . title Allows respecify title character (Default:NULL). col character stating colour palette use. either predefined value vector colours. See \"biscale::bi_pal_manual\". Default: \"BlueGold\". ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"Saved bivariate plot 'fname' specified, otherwise plot.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"function requires biscale package installed. Although work around without package developed, deemed necessary point. See also gist.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":null,"dir":"Reference","previous_headings":"","what":"Check objects in the package for common errors or issues — check","title":"Check objects in the package for common errors or issues — check","text":"always enough data sufficient information robustly infer suitable habitat niche species. many SDM algorithms essentially regression models, similar assumptions model convergence, homogeneity residuals inferrence usually apply (although often ignored). function simply checks respective input object common issues mistakes.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Check objects in the package for common errors or issues — check","text":"","code":"check(obj, stoponwarning = FALSE)  # S4 method for ANY check(obj, stoponwarning = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Check objects in the package for common errors or issues — check","text":"obj BiodiversityDistribution, DistributionModel BiodiversityScenario object. stoponwarning logical check return stop warning raised? (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Check objects in the package for common errors or issues — check","text":"Message outputs","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Check objects in the package for common errors or issues — check","text":"Different checks implemented depending supplied object BiodiversityDistribution Checks less 200 observations TODO: Add rm_insufficient_covs link DistributionModel Check model convergence Check model found Check coefficients exist Check unusal outliers prediction (using 10median absolute deviation) Check threshold larger layer BiodiversityScenario","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Check objects in the package for common errors or issues — check","text":"function likely expanded additional checks future. ideas, please let know per issue.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Check objects in the package for common errors or issues — check","text":"","code":"if (FALSE) {  # Where mod is an estimated DistributionModel  check(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":null,"dir":"Reference","previous_headings":"","what":"Obtains the coefficients of a trained model — coef","title":"Obtains the coefficients of a trained model — coef","text":"Similar summary, helper function obtains coefficients given DistributionModel object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Obtains the coefficients of a trained model — coef","text":"","code":"# S3 method for DistributionModel coef(object, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Obtains the coefficients of a trained model — coef","text":"object prepared object. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Obtains the coefficients of a trained model — coef","text":"models trained machine-learning approaches (e.g. engine_bart etc) function return variable importance estimates rather linear coefficients. Similar can said trained non-linear models.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":null,"dir":"Reference","previous_headings":"","what":"Create distribution modelling procedure — distribution","title":"Create distribution modelling procedure — distribution","text":"function creates object contains data, parameters settings building (integrated) species distribution model. Key functions add data add_biodiversity_poipo like, add_predictors, add_latent_spatial, engine_glmnet similar, add_priors add_offset. creates prototype BiodiversityDistribution object functions. setting input data parameters, model predictions can created via train function predictions created. Additionally, possible specify \"limit\" predictions conducted background. can instance buffered layer certain dispersal distance (Cooper Soberon, 2018) categorical layer representing biomes soil conditions. Another option create constraint constructing minimum convex polygon (MCP) using supplied biodiversity data. option can enabled setting \"limits_method\" \"mcp\". also possible provide small buffer constructed MCP way. See frequently asked question (FAQ) section homepage information. See Details description internal functions available modify summarize data within created object. Note model requires minimum single added biodiversity dataset well specified engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create distribution modelling procedure — distribution","text":"","code":"distribution(   background,   limits = NULL,   limits_method = \"none\",   mcp_buffer = 0,   limits_clip = FALSE )  # S4 method for SpatRaster distribution(   background,   limits = NULL,   limits_method = \"none\",   mcp_buffer = 0,   limits_clip = FALSE )  # S4 method for sf distribution(   background,   limits = NULL,   limits_method = \"none\",   mcp_buffer = 0,   limits_clip = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create distribution modelling procedure — distribution","text":"background Specification modelling background. Must SpatRaster sf object. limits SpatRaster sf object limits prediction surface intersected input data (Default: NULL). limits_method character method used hard limiting projection. Available options \"none\" (Default), \"zones\" \"mcp\". mcp_buffer numeric distance buffer mcp (Default 0). used \"mcp\" used. limits_clip logical limits clip predictors fitting model (TRUE) just prediction (FALSE, default).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create distribution modelling procedure — distribution","text":"BiodiversityDistribution object containing data building biodiversity distribution modelling problem.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create distribution modelling procedure — distribution","text":"function creates BiodiversityDistribution object contains functions stores parameters (pre-)processed data. full list functions available can queried via \"names(object)\". functions intended manipulated directly, rather convenience functions (e.g. \"object$set_predictors()\"). Similarly objects stored BiodiversityDistribution object functions well can queried (e.g. \"names(object)\"). list functions see reference documentation. default, datasets set, \"Waiver\" object returned instead. following objects can stored: object$biodiversity BiodiversityDatasetCollection object added biodiversity data. object$engine \"engine\" object (e.g. engine_inlabru()) function depended added engine. object$predictors PredictorDataset object set predictions. object$priors PriorList object specified priors. object$log Log object captures. Useful high-level functions address objects instance: object$show() generic summary BiodiversityDistribution object contents. Can also called via print. object$get_biodiversity_equations() Lists equations used biodiversity dataset given id. Defaults predictors. object$get_biodiversity_types() Lists type specified biodiversity dataset given id. object$get_extent() Outputs terra::ext modelling region. object$show_background_info() Returns list terra::ext terra::crs. object$get_extent_dimensions() Outputs terra::ext dimension calling \"extent_dimensions()\" function. object$get_predictor_names() Returns character vector names added predictors. object$get_prior_variables() Returns description priors added. functions well better accessed respective wrapper functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create distribution modelling procedure — distribution","text":"Fletcher, R.J., Hefley, T.J., Robertson, E.P., Zuckerberg, B., McCleery, R.., Dorazio, R.M., (2019) practical guide combining data model species distributions. Ecology 100, e02710. https://doi.org/10.1002/ecy.2710 Cooper, Jacob C., Jorge Soberón. \"Creating individual accessible area hypotheses improves stacked species distribution model performance.\" Global Ecology Biogeography 27, . 1 (2018): 156-165.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create distribution modelling procedure — distribution","text":"","code":"# Load background raster background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\")) # Define model x <- distribution(background) #> [Setup] 2024-01-25 21:59:59.645498 | Provide a background with a valid projection! #> [Setup] 2024-01-25 21:59:59.656606 | Creating distribution object... x #>  #> Background extent:  #>      xmin: -16.064, xmax: 36.322, #>      ymin: 34.95, ymax: 71.535 #>    projection: +proj=longlat +datum=WGS84 +no_defs #>  ---------  #> Biodiversity data: #>    None #>  ---------  #>   predictors:     None #>   priors:          #>   latent:         None #>   log:             #>   engine:         "},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":null,"dir":"Reference","previous_headings":"","what":"Plot effects of trained model — effects","title":"Plot effects of trained model — effects","text":"functions handy wrapper calls default plotting functions model specific engine. Equivalent calling effects fitted distribution function.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Plot effects of trained model — effects","text":"","code":"# S3 method for DistributionModel effects(object, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Plot effects of trained model — effects","text":"object fitted distribution object. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Plot effects of trained model — effects","text":"None.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Plot effects of trained model — effects","text":"models, default coefficients plots available, function attempt generate partial dependency plots instead.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Plot effects of trained model — effects","text":"","code":"if (FALSE) { # Where mod is an estimated distribution model mod$effects() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":null,"dir":"Reference","previous_headings":"","what":"Create an empty SpatRaster based on a template — emptyraster","title":"Create an empty SpatRaster based on a template — emptyraster","text":"function creates empty copy provided SpatRaster object. primarily used package create outputs predictions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create an empty SpatRaster based on a template — emptyraster","text":"","code":"emptyraster(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create an empty SpatRaster based on a template — emptyraster","text":"x SpatRaster* object corresponding. ... arguments can passed terra","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create an empty SpatRaster based on a template — emptyraster","text":"empty SpatRaster, .e. cells NA.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create an empty SpatRaster based on a template — emptyraster","text":"","code":"require(terra) #> Loading required package: terra #> terra 1.7.65 r <- rast(matrix(1:100, 5, 20)) emptyraster(r) #> class       : SpatRaster  #> dimensions  : 5, 20, 1  (nrow, ncol, nlyr) #> resolution  : 1, 1  (x, y) #> extent      : 0, 20, 0, 5  (xmin, xmax, ymin, ymax) #> coord. ref. :"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Bayesian regression approach sum complementary trees shrink said fit tree regularization prior. BART models provide non-linear highly flexible estimation shown compare favourable among machine learning algorithms (Dorie et al. 2019). Default prior preference trees small (terminal nodes) shrinkage towards 0. package requires \"dbarts\" R-package installed. Many functionalities engine inspired \"embarcadero\" R-package. Users therefore advised cite make heavy use BART.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"","code":"engine_bart(x, iter = 1000, nburn = 250, chains = 4, type = \"response\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"x distribution() (.e. BiodiversityDistribution) object. iter numeric estimate number trees used sum--trees formulation (Default: 1000). nburn numeric estimate burn samples (Default: 250). chains number number chains used (Default: 4). type mode used creating posterior predictions. Either \"link\" \"response\" (Default: \"response\"). ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Prior distributions can furthermore set : probability tree stops node given depth (yet implemented) probability given variable chosen splitting rule probability splitting variable particular value (yet implemented)","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Carlson, CJ. embarcadero: Species distribution modelling Bayesian additive regression trees r. Methods Ecol Evol. 2020; 11: 850– 858. https://doi.org/10.1111/2041-210X.13389 Dorie, V., Hill, J., Shalit, U., Scott, M., & Cervone, D. (2019). Automated versus --methods causal inference: Lessons learned data analysis competition. Statistical Science, 34(1), 43-68. Vincent Dorie (2020). dbarts: Discrete Bayesian Additive Regression Trees Sampler. R package version 0.9-19. https://CRAN.R-project.org/package=dbarts","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"","code":"if (FALSE) { # Add BART as an engine x <- distribution(background) |> engine_bart(iter = 100) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for Bayesian regularized regression models — engine_breg","title":"Engine for Bayesian regularized regression models — engine_breg","text":"Efficient MCMC algorithm linear regression models makes use 'spike--slab' priors modest regularization amount posterior probability subset coefficients.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for Bayesian regularized regression models — engine_breg","text":"","code":"engine_breg(   x,   iter = 10000,   nthread = getOption(\"ibis.nthread\"),   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for Bayesian regularized regression models — engine_breg","text":"x distribution() (.e. BiodiversityDistribution) object. iter numeric number MCMC iterations run (Default: 10000). nthread numeric number CPU-threads use data augmentation. type mode used creating posterior predictions. Either making \"link\" \"response\" (Default: \"response\"). ... none specified parameters passed model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for Bayesian regularized regression models — engine_breg","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for Bayesian regularized regression models — engine_breg","text":"engine provides efficient Bayesian predictions Boom R-package. However note link models functions supported certain functionalities offsets generally available. engines allows estimation linear non-linear effects via \"only_linear\" option specified train.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for Bayesian regularized regression models — engine_breg","text":"Nguyen, K., Le, T., Nguyen, V., Nguyen, T., & Phung, D. (2016, November). Multiple kernel learning data augmentation. Asian Conference Machine Learning (pp. 49-64). PMLR. Steven L. Scott (2021). BoomSpikeSlab: MCMC Spike Slab Regression. R package version 1.2.4. https://CRAN.R-project.org/package=BoomSpikeSlab","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for Bayesian regularized regression models — engine_breg","text":"","code":"if (FALSE) { # Add BREG as an engine x <- distribution(background) |> engine_breg(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":null,"dir":"Reference","previous_headings":"","what":"Use of Gradient Descent Boosting for model estimation — engine_gdb","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"Gradient descent boosting efficient way optimize loss function generalized linear additive model (GAMs available \"mgcv\" R-package). furthermore automatically regularizes fit, thus resulting model contains covariates whose baselearners influence response. Depending type add_biodiversity data, either poisson process models logistic regressions estimated. \"only_linear\" term train set FALSE, splines added estimation, thus providing non-linear additive inference.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"","code":"engine_gdb(   x,   iter = 2000,   learning_rate = 0.1,   empirical_risk = \"inbag\",   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"x distribution() (.e. BiodiversityDistribution) object. iter integer giving number boosting iterations (Default: 2e3L). learning_rate bounded numeric value 0 1 defining shrinkage parameter. empirical_risk method empirical risk calculation. Available options 'inbag', 'oobag' 'none'. (Default: 'inbag'). type mode used creating posterior predictions. Either making \"link\", \"response\" \"class\" (Default: \"response\"). ... variables control parameters","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":": package requires \"mboost\" R-package installed. philosophy somewhat related engine_xgboost \"XGBoost\" R-package, however providing additional desirable features make estimation quicker particularly useful spatial projections. instance ability specifically add spatial baselearners via add_latent_spatial specification monotonically constrained priors via GDBPrior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"Hofner, B., Mayr, ., Robinzonov, N., & Schmid, M. (2014). Model-based boosting R: hands-tutorial using R package mboost. Computational statistics, 29(1-2), 3-35. Hofner, B., Müller, J., Hothorn, T., (2011). Monotonicity-constrained species distribution models. Ecology 92, 1895–901. Mayr, ., Hofner, B. Schmid, M. (2012). importance knowing stop - sequential stopping rule component-wise gradient boosting. Methods Information Medicine, 51, 178–186.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"","code":"if (FALSE) { # Add GDB as an engine x <- distribution(background) |> engine_gdb(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for Generalized linear models (GLM) — engine_glm","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"engine implements basic generalized linear modle (GLM) creating species distribution models. main purpose engine support basic, dependency-free method inference projection can used within package examples vignettes. said, engine fully functional engine. basic implementation GLMs part general class oflinear models - exception offsets - minimal options integrate sources information priors joint integration. general recommendation engine_glmnet() instead regularization support. However basic GLMs can cases useful quick projections ensemble() small models (practice common rare species).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"","code":"engine_glm(x, control = NULL, type = \"response\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"x distribution() (.e. BiodiversityDistribution) object. control list containing parameters controlling fitting process (Default: NULL). type mode used creating posterior predictions. Either making \"link\" \"response\" (Default: \"response\"). ... parameters passed stats::glm().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"engine essentially wrapper stats::glm.fit(), however customized settings support offsets weights.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"Hastie, T. J. Pregibon, D. (1992) Generalized linear models. Chapter 6 Statistical Models S eds J. M. Chambers T. J. Hastie, Wadsworth & Brooks/Cole.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"","code":"# Load background background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM',mustWork = TRUE))  # Add GLM as an engine x <- distribution(background) |> engine_glm() #> [Setup] 2024-01-25 22:00:00.59482 | Provide a background with a valid projection! #> [Setup] 2024-01-25 22:00:00.605784 | Creating distribution object..."},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for regularized regression models — engine_glmnet","title":"Engine for regularized regression models — engine_glmnet","text":"engine allows estimation linear coefficients using either ridge, lasso elastic net regressions techniques. Backbone engine glmnet R-package commonly used SDMs, including popular 'maxnet' (e.g. Maxent) package. Ultimately engine equivalent engine_breg, \"frequentist\" setting. user aim emulate model closely resembles maxent within ibis.iSDM modelling framework, package best way . Compared 'maxnet' R-package, number efficiency settings implemented particular cross-validation alpha lambda values. Limited amount prior information can specified engine, specifically via offsets GLMNETPrior, allow specify priors regularization constants.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for regularized regression models — engine_glmnet","text":"","code":"engine_glmnet(   x,   alpha = 0,   nlambda = 100,   lambda = NULL,   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for regularized regression models — engine_glmnet","text":"x distribution() (.e. BiodiversityDistribution) object. alpha numeric giving elasticnet mixing parameter, 0 1. alpha=1 lasso penalty, alpha=0 ridge penalty (Default: 0). nlambda numeric giving number lambda values used (Default: 100). lambda numeric user supplied estimate lambda. Usually best let parameter determined deterministically (Default: NULL). type mode used creating posterior predictions. Either making \"link\" \"response\" (Default: \"response\"). ... parameters passed glmnet.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for regularized regression models — engine_glmnet","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for regularized regression models — engine_glmnet","text":"Regularized regressions effectively GLMs fitted ridge, lasso elastic-net regularization. chosen critical dependent alpha value: * alpha equal 0 ridge regularization used. Ridge regularization property remove variables entirely, instead sets coefficients 0. * alpha equal 1 lasso regularization used. Lassos tend remove coefficients fully final model improve loss function. * alpha values 0 1 elastic-net regularization used, essentially combination two. optimal lambda parameter can determined via cross-validation. option set \"varsel\" train() \"reg\".","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for regularized regression models — engine_glmnet","text":"Jerome Friedman, Trevor Hastie, Robert Tibshirani (2010). Regularization Paths Generalized Linear Models via Coordinate Descent. Journal Statistical Software, 33(1), 1-22. URL https://www.jstatsoft.org/v33/i01/. Renner, .W., Elith, J., Baddeley, ., Fithian, W., Hastie, T., Phillips, S.J., Popovic, G. Warton, D.., 2015. Point process models presence‐analysis. Methods Ecology Evolution, 6(4), pp.366-379. Fithian, W. & Hastie, T. (2013) Finite-sample equivalence statistical models presence-data. Annals Applied Statistics 7, 1917–1939","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for regularized regression models — engine_glmnet","text":"","code":"if (FALSE) { # Add GLMNET as an engine x <- distribution(background) |> engine_glmnet(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":null,"dir":"Reference","previous_headings":"","what":"Use INLA as engine — engine_inla","title":"Use INLA as engine — engine_inla","text":"Allows full Bayesian analysis linear additive models using Integrated Nested Laplace approximation. Engine largely superceded engine_inlabru package users advised us one, unless specific options required.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use INLA as engine — engine_inla","text":"","code":"engine_inla(   x,   optional_mesh = NULL,   optional_projstk = NULL,   max.edge = NULL,   offset = NULL,   cutoff = NULL,   proj_stepsize = NULL,   timeout = NULL,   strategy = \"auto\",   int.strategy = \"eb\",   barrier = FALSE,   type = \"response\",   area = \"gpc2\",   nonconvex.bdry = FALSE,   nonconvex.convex = -0.15,   nonconvex.concave = -0.05,   nonconvex.res = 40,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use INLA as engine — engine_inla","text":"x distribution() (.e. BiodiversityDistribution) object. optional_mesh directly supplied \"INLA\" mesh (Default: NULL) optional_projstk directly supplied projection stack. Useful projection stack identical multiple species (Default: NULL) max.edge largest allowed triangle edge length, must scale units coordinates. Default educated guess (Default: NULL). offset interpreted numeric factor relative approximate data diameter. Default educated guess (Default: NULL). cutoff minimum allowed distance points mesh. Default educated guess (Default: NULL). proj_stepsize stepsize coordinate units cells projection grid (Default: NULL). timeout Specify timeout INLA models sec. Afterwards passed. strategy approximation use joint posterior. Options \"auto\" (\"default\"), \"adaptative\", \"gaussian\", \"simplified.laplace\" & \"laplace\". int.strategy Integration strategy. Options \"auto\",\"grid\", \"eb\" (\"default\") & \"ccd\". See also https://groups.google.com/g/r-inla-discussion-group/c/hDboQsJ1Mls barrier barrier model added model? type mode used creating posterior predictions. Either summarizing linear \"predictor\" \"response\" (Default: \"response\"). area Accepts character denoting type area calculation done mesh (Default: 'gpc2'). nonconvex.bdry Create non-convex boundary hulls instead (Default: FALSE) yet implemented nonconvex.convex Non-convex minimal extension radius convex curvature yet implemented nonconvex.concave Non-convex minimal extension radius concave curvature yet implemented nonconvex.res Computation resolution nonconvex.hulls yet implemented ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use INLA as engine — engine_inla","text":"engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use INLA as engine — engine_inla","text":"INLA engines require specification mesh needs provided \"optional_mesh\" parameter. Otherwise mesh created based best guesses data spread. good mesh needs triangles regular possible size shape: equilateral. * \"max.edge\": largest allowed triangle edge length, must scale units coordinates Lower bounds affect density triangles * \"offset\": automatic extension distance mesh positive: scale units. negative, interpreted factor relative approximate data diameter .e., value -0.10 add 10% data diameter outer extension. * \"cutoff\": minimum allowed distance points, means points closer distance supplied value replaced single vertex. critical points close , either point locations domain boundary. * \"proj_stepsize\": stepsize spatial predictions, affects spatial grain outputs created. Priors can set via INLAPrior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Use INLA as engine — engine_inla","text":"INLA Meshes generated, substantially influences prediction outcomes. See Dambly et al. (2023).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use INLA as engine — engine_inla","text":"Havard Rue, Sara Martino, Nicholas Chopin (2009), Approximate Bayesian Inference Latent Gaussian Models Using Integrated Nested Laplace Approximations (discussion), Journal Royal Statistical Society B, 71, 319-392. Finn Lindgren, Havard Rue, Johan Lindstrom (2011). Explicit Link Gaussian Fields Gaussian Markov Random Fields: Stochastic Partial Differential Equation Approach (discussion), Journal Royal Statistical Society B, 73(4), 423-498. Simpson, Daniel, Janine B. Illian, S. H. Sørbye, Håvard Rue. 2016. “Going Grid: Computationally Efficient Inference Log-Gaussian Cox Processes.” Biometrika 1 (103): 49–70. Dambly, L. ., Isaac, N. J., Jones, K. E., Boughey, K. L., & O'Hara, R. B. (2023). Integrated species distribution models fitted INLA sensitive mesh parameterisation. Ecography, e06391.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use INLA as engine — engine_inla","text":"","code":"if (FALSE) { # Add INLA as an engine (with a custom mesh) x <- distribution(background) |> engine_inla(mesh = my_mesh) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":null,"dir":"Reference","previous_headings":"","what":"Use inlabru as engine — engine_inlabru","title":"Use inlabru as engine — engine_inlabru","text":"Model components specified general inputs mapping methods latent variables, predictors specified via general R expressions, separate expressions observation likelihood model multi-likelihood models. inlabru engine - similar engine_inla function acts wrapper INLA, albeit \"inlabru\" number convenience functions implemented make particular predictions new data much straight forward (e.g. via posterior simulation instead fitting). Since recent versions \"inlabru\" also supports addition multiple likelihoods, therefore allowing full integrated inference.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use inlabru as engine — engine_inlabru","text":"","code":"engine_inlabru(   x,   optional_mesh = NULL,   max.edge = NULL,   offset = NULL,   cutoff = NULL,   proj_stepsize = NULL,   strategy = \"auto\",   int.strategy = \"eb\",   area = \"gpc2\",   timeout = NULL,   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"source","dir":"Reference","previous_headings":"","what":"Source","title":"Use inlabru as engine — engine_inlabru","text":"https://inlabru-org.github.io/inlabru/articles/","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use inlabru as engine — engine_inlabru","text":"x distribution() (.e. BiodiversityDistribution) object. optional_mesh directly supplied \"INLA\" mesh (Default: NULL) max.edge largest allowed triangle edge length, must scale units coordinates. Default educated guess (Default: NULL). offset interpreted numeric factor relative approximate data diameter. Default educated guess (Default: NULL). cutoff minimum allowed distance points mesh. Default educated guess (Default: NULL). proj_stepsize stepsize coordinate units cells projection grid (Default: NULL) strategy approximation use joint posterior. Options \"auto\" (\"default\"), \"adaptative\", \"gaussian\", \"simplified.laplace\" & \"laplace\". int.strategy Integration strategy. Options \"auto\", \"grid\", \"eb\" (\"default\") & \"ccd\". area Accepts character denoting type area calculation done mesh (Default: 'gpc2'). timeout Specify timeout INLA models sec. Afterwards passed. type mode used creating posterior predictions. Either summarizing linear \"predictor\" \"response\" (Default:\"response\"). ... variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use inlabru as engine — engine_inlabru","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use inlabru as engine — engine_inlabru","text":"INLA engines require specification mesh needs provided \"optional_mesh\" parameter. Otherwise mesh created based best guesses data spread. good mesh needs triangles regular possible size shape: equilateral. * \"max.edge\": largest allowed triangle edge length, must scale units coordinates Lower bounds affect density triangles * \"offset\": automatic extension distance mesh positive: scale units. negative, interpreted factor relative approximate data diameter .e., value -0.10 add 10% data diameter outer extension. * \"cutoff\": minimum allowed distance points, means points closer distance supplied value replaced single vertex. critical points close , either point locations domain boundary. * \"proj_stepsize\": stepsize spatial predictions, affects spatial grain outputs created. Priors can set via INLAPrior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Use inlabru as engine — engine_inlabru","text":"INLA Meshes generated, substantially influences prediction outcomes. See Dambly et al. (2023).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use inlabru as engine — engine_inlabru","text":"Bachl, F. E., Lindgren, F., Borchers, D. L., & Illian, J. B. (2019). inlabru: R package Bayesian spatial modelling ecological survey data. Methods Ecology Evolution, 10(6), 760-766. Simpson, Daniel, Janine B. Illian, S. H. Sørbye, Håvard Rue. 2016. “Going Grid: Computationally Efficient Inference Log-Gaussian Cox Processes.” Biometrika 1 (103): 49–70. Dambly, L. ., Isaac, N. J., Jones, K. E., Boughey, K. L., & O'Hara, R. B. (2023). Integrated species distribution models fitted INLA sensitive mesh parameterisation. Ecography, e06391.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use inlabru as engine — engine_inlabru","text":"","code":"if (FALSE) { # Add inlabru as an engine x <- distribution(background) |> engine_inlabru() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":null,"dir":"Reference","previous_headings":"","what":"Use Stan as engine — engine_stan","title":"Use Stan as engine — engine_stan","text":"Stan probabilistic programming language can used specify types statistical linear non-linear regression models. Stan provides full Bayesian inference continuous-variable models Markov chain Monte Carlo methods -U-Turn sampler, adaptive form Hamiltonian Monte Carlo sampling. Stan code written separately function acts compiler build stan-model. Requires \"cmdstanr\" package installed!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use Stan as engine — engine_stan","text":"","code":"engine_stan(   x,   chains = 4,   iter = 2000,   warmup = floor(iter/2),   init = \"random\",   cores = getOption(\"ibis.nthread\"),   algorithm = \"sampling\",   control = list(adapt_delta = 0.95),   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use Stan as engine — engine_stan","text":"x distribution() (.e. BiodiversityDistribution) object. chains positive integer specifying number Markov chains (Default: 4 chains). iter positive integer specifying number iterations chain (including warmup). (Default: 2000). warmup positive integer specifying number warmup (aka burnin) iterations per chain. step-size adaptation (Default: TRUE), also controls number iterations adaptation run (hence warmup samples used inference). number warmup iterations smaller iter default iter/2. init Initial values parameters (Default: 'random'). Can also specified list (see: \"rstan::stan\") cores set NULL take values specified ibis option getOption('ibis.nthread'). algorithm Mode used sample posterior. Available options \"sampling\", \"optimize\", \"variational\". See \"cmdstanr\" package details. (Default: \"sampling\"). control See \"rstan::stan\" details specifying controls. type mode used creating posterior predictions. Either summarizing linear \"predictor\" \"response\" (Default: \"response\"). ... variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use Stan as engine — engine_stan","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use Stan as engine — engine_stan","text":"default posterior obtained sampling, however stan also supports approximate inference forms penalized maximum likelihood estimation (see Carpenter et al. 2017).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Use Stan as engine — engine_stan","text":"function obj$stancode() can used print stancode model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use Stan as engine — engine_stan","text":"Jonah Gabry Rok Češnovar (2021). cmdstanr: R Interface 'CmdStan'. https://mc-stan.org/cmdstanr, https://discourse.mc-stan.org. Carpenter, B., Gelman, ., Hoffman, M. D., Lee, D., Goodrich, B., Betancourt, M., ... & Riddell, . (2017). Stan: probabilistic programming language. Journal statistical software, 76(1), 1-32. Piironen, J., & Vehtari, . (2017). Sparsity information regularization horseshoe shrinkage priors. Electronic Journal Statistics, 11(2), 5018-5051.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use Stan as engine — engine_stan","text":"","code":"if (FALSE) { # Add Stan as an engine x <- distribution(background) |> engine_stan(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"Allows estimate eXtreme gradient descent boosting tree-based linear boosting regressions. XGBoost engine flexible, yet powerful engine many customization options, supporting multiple options perform single multi-class regression classification tasks. full list options users advised look xgboost::xgb.train help file https://xgboost.readthedocs.io.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"","code":"engine_xgboost(   x,   booster = \"gbtree\",   iter = 8000L,   learning_rate = 0.001,   gamma = 6,   reg_lambda = 0,   reg_alpha = 0,   max_depth = 2,   subsample = 0.75,   colsample_bytree = 0.4,   min_child_weight = 3,   nthread = getOption(\"ibis.nthread\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"x distribution() (.e. BiodiversityDistribution) object. booster character booster use. Either \"gbtree\" \"gblinear\" (Default: gblinear) iter numeric value giving maximum number boosting iterations cross-validation (Default: 8e3L). learning_rate numeric value indicating learning rate (eta). Lower values generally better also computationally costly. (Default: 1e-3) gamma numeric regularization parameter model. Lower values better estimates (Default: 3). Also see \"reg_lambda\" parameter L2 regularization weights reg_lambda numeric L2 regularization term weights (Default: 0). reg_alpha numeric L1 regularization term weights (Default: 0). max_depth numeric Maximum depth tree (Default: 3). subsample numeric ratio used subsampling prevent overfitting. Also used creating random tresting dataset (Default: 0.75). colsample_bytree numeric Sub-sample ratio columns constructing tree (Default: 0.4). min_child_weight numeric Broadly related number instances necessary node (Default: 3). nthread numeric number CPU-threads use. ... none specified parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"default parameters set relatively conservative reduce overfitting. XGBoost supports specification monotonic constraints certain variables. Within ibis possible via XGBPrior. However constraints available \"gbtree\" baselearners.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"'Machine learning statistics minus checking models assumptions‘ ~ Brian D. Ripley, useR! 2004, Vienna","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"Tianqi Chen Carlos Guestrin, \"XGBoost: Scalable Tree Boosting System\", 22nd SIGKDD Conference Knowledge Discovery Data Mining, 2016, https://arxiv.org/abs/1603.02754","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"","code":"if (FALSE) { # Add xgboost as an engine x <- distribution(background) |> engine_xgboost(iter = 4000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to create an ensemble of multiple fitted models — ensemble","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"Ensemble models calculated multiple models often shown outcompete single model comparative assessments (Valavi et al. 2022). function creates ensemble multiple provided distribution models fitted ibis.iSDM-package. model estimated predictions given method optional uncertainty form standard deviation similar. layer parameter can specified part prediction averaged ensemble. can instance mean prediction /standard deviation sd. See Details overview different methods. Also returns coefficient variation (cv) output ensemble, note interpreted measure model uncertainty capture parameter uncertainty individual models; rather reflects variation among predictions can due many factors including simply differences model complexity.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"","code":"ensemble(   ...,   method = \"mean\",   weights = NULL,   min.value = NULL,   layer = \"mean\",   normalize = FALSE,   uncertainty = \"cv\",   apply_threshold = TRUE )  # S4 method for ANY ensemble(   ...,   method = \"mean\",   weights = NULL,   min.value = NULL,   layer = \"mean\",   normalize = FALSE,   uncertainty = \"cv\",   apply_threshold = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"... Provided DistributionModel SpatRaster objects. method Approach ensemble created. See details available options (Default: 'mean'). weights (Optional) weights provided ensemble function weighted means constructed (Default: NULL). min.value optional numeric stating minimum value needs surpassed layer calculating ensemble (Default: NULL). layer character layer taken prediction (Default: 'mean'). set NULL ignore layer names ensembles SpatRaster objects. normalize logical whether inputs ensemble normalized scale 0-1 (Default: FALSE). uncertainty character indicating uncertainty among models calculated. Available options include \"none\", standard deviation (\"sd\"), average PCA axes except first \"pca\", coefficient variation (\"cv\", Default) range lowest highest value (\"range\"). apply_threshold logical flag (Default: TRUE) specifying whether threshold values also created via \"method\". applies works DistributionModel thresholds found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"SpatRaster object containing ensemble provided predictions specified method coefficient variation across models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"Possible options creating ensemble includes: 'mean' - Calculates mean several predictions. 'median' - Calculates median several predictions. 'max' - maximum value across predictions. 'min' - minimum value across predictions. 'weighted.mean' - Calculates weighted mean. Weights supplied separately (e.g. TSS). 'min.sd' - Ensemble created minimizing uncertainty among predictions. 'threshold.frequency' - Returns ensemble based threshold frequency (simple count). Requires thresholds computed. 'pca' - Calculates PCA predictions algorithm extract first axis (one explaining variation). addition different ensemble methods, minimal threshold (min.value) can set needs surpassed averaging. default option used (Default: NULL). Note default band layer parameter composited. supported model summary statistics posterior (e.g. 'sd') can specified.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"list supplied, assumed entry list fitted DistributionModel object. Take care create ensemble models constructed different link functions, e.g. logistic vs log. case \"normalize\" parameter set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"Valavi, R., Guillera‐Arroita, G., Lahoz‐Monfort, J. J., & Elith, J. (2022). Predictive performance presence‐species distribution models: benchmark study reproducible code. Ecological Monographs, 92(1), e01486.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"","code":"# Method works for fitted models as well as as rasters r1 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,  xmax = 1.5, ymin = -1.5, ymax = 1.5, vals = rnorm(3600,mean = .5,sd = .1)) r2 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,  xmax = 1.5, ymin = -1.5, ymax = 1.5, vals = rnorm(3600,mean = .5,sd = .5)) names(r1) <- names(r2) <- \"mean\"  # Assumes previously computed predictions ex <- ensemble(r1, r2, method = \"mean\")  terra::plot(ex)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"Similar ensemble() function, function creates ensemble partial responses provided distribution models fitted ibis.iSDM-package. layer parameter can specified part partial prediction averaged ensemble (given). can instance mean prediction /standard deviation sd. Ensemble partial also called one input DistributionModel object provided partial. default ensemble partial responses created average across models uncertainty standard deviation responses.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"","code":"ensemble_partial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   normalize = TRUE )  # S4 method for ANY ensemble_partial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   normalize = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"... Provided DistributionModel objects partial responses can called. future provided data.frames might supported well. x.var character variable ensemble created. method Approach ensemble created. See details options (Default: 'mean'). layer character layer taken prediction (Default: 'mean'). set NULL ignore layer names ensembles SpatRaster objects. newdata optional data.frame SpatRaster object supplied model (DefaultL NULL). object needs identical names original predictors. normalize logical whether inputs ensemble normalized scale 0-1 (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"data.frame combined partial effects supplied models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"Possible options creating ensemble includes: 'mean' - Calculates mean several predictions. 'median' - Calculates median several predictions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"list supplied, assumed entry list fitted DistributionModel object. Take care create ensemble models constructed different link functions, e.g. logistic vs log. default response functions model normalized.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"","code":"if (FALSE) {  # Assumes previously computed models  ex <- ensemble_partial(mod1, mod2, mod3, method = \"mean\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"Similar ensemble() function, function creates ensemble partial responses provided distribution models fitted ibis.iSDM-package. layer parameter can specified part partial prediction averaged ensemble (given). can instance mean prediction /standard deviation sd. Ensemble partial also called one input DistributionModel object provided partial. default ensemble partial responses created average across models uncertainty standard deviation responses.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"","code":"ensemble_spartial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   min.value = NULL,   normalize = TRUE )  # S4 method for ANY ensemble_spartial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   min.value = NULL,   normalize = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"... Provided DistributionModel objects partial responses can called. future provided data.frames might supported well. x.var character variable ensemble created. method Approach ensemble created. See details options (Default: 'mean'). layer character layer taken prediction (Default: 'mean'). set NULL ignore layer names ensembles SpatRaster objects. newdata optional data.frame SpatRaster object supplied model (DefaultL NULL). object needs identical names original predictors. min.value optional numeric stating minimum value needs surpassed layer calculating ensemble (Default: NULL). normalize logical whether inputs ensemble normalized scale 0-1 (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"SpatRaster object combined partial effects supplied models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"Possible options creating ensemble includes: 'mean' - Calculates mean several predictions. 'median' - Calculates median several predictions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"list supplied, assumed entry list fitted DistributionModel object. Take care create ensemble models constructed different link functions, e.g. logistic vs log. default response functions model normalized.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"","code":"if (FALSE) {  # Assumes previously computed models  ex <- ensemble_spartial(mod1, mod2, mod3, method = \"mean\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"function expects downscaled GLOBIOM output created BIOCLIMA project. Likely little use anyone outside IIASA.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"","code":"formatGLOBIOM(   fname,   oftype = \"raster\",   ignore = NULL,   period = \"all\",   template = NULL,   shares_to_area = FALSE,   use_gdalutils = FALSE,   verbose = getOption(\"ibis.setupmessages\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"fname filename character pointing GLOBIOM output netCDF format. oftype character denoting output type (Default: 'raster'). ignore vector variables ignored (Default: NULL). period character limiting period returned formatted data. Options include \"reference\" first entry, \"projection\" entries first, \"\" entries (Default: \"reference\"). template optional SpatRaster object towards projects transformed. shares_to_area logical whether shares corrected areas (identified). use_gdalutils (Deprecated) logical use gdalutils hack-around. verbose logical whether chatty.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"SpatRaster stack formatted GLOBIOM predictors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"","code":"if (FALSE) { # Expects a filename pointing to a netCDF file. covariates <- formatGLOBIOM(fname) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":null,"dir":"Reference","previous_headings":"","what":"Small helper function to obtain predictions from an object — get_data","title":"Small helper function to obtain predictions from an object — get_data","text":"function short helper function return fitted data DistributionModel BiodiversityScenario object. can used easily obtain example estimated prediction model projected scenario scenario() object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Small helper function to obtain predictions from an object — get_data","text":"","code":"get_data(obj, what = NULL)  # S4 method for ANY get_data(obj, what = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Small helper function to obtain predictions from an object — get_data","text":"obj Provided DistributionModel BiodiversityScenario object. character specific layer returned existing (Default: NULL).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Small helper function to obtain predictions from an object — get_data","text":"SpatRaster \"stars\" object depending input.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Small helper function to obtain predictions from an object — get_data","text":"function essentially identical querying internal function x$get_data() object. However attempt lazy character matching supplied.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Small helper function to obtain predictions from an object — get_data","text":"","code":"if (FALSE) {  # Assumes previously computed model  get_data(fit) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"function performs nearest neighbour matching biodiversity observations independent predictors, operates directly provided data.frames. Note despite parallized function can rather slow large data volumes data!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"","code":"get_ngbvalue(   coords,   env,   longlat = TRUE,   field_space = c(\"x\", \"y\"),   cheap = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"coords matrix, data.frame sf object. env data.frame object predictors. longlat logical variable indicating whether projection long-lat. field_space vector highlight columns coordinates extracted (Default: c('x','y')). cheap logical variable whether dataset considered large faster computation help. ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"data.frame extracted covariate data provided data point.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"Nearest neighbour matching done via geodist R-package (geodist::geodist).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"multiple values equal distance nearest neighbour check, results default averaged.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"Mark Padgham Michael D. Sumner (2021). geodist: Fast, Dependency-Free Geodesic Distance Calculations. R package version 0.0.7. https://CRAN.R-project.org/package=geodist","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"","code":"if (FALSE) {  # Create matchup table tab <- get_ngbvalue( coords = coords, # Coordinates                      env = env # Data.frame with covariates and coordinates                   ) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Create priors from an existing distribution model — get_priors","title":"Create priors from an existing distribution model — get_priors","text":"Often can make sense fit additional model get grasp range values \"beta\" parameters can take. function takes existing BiodiversityDistribution object creates PriorList object . resulting object can used add instance priors new model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create priors from an existing distribution model — get_priors","text":"","code":"get_priors(mod, target_engine, ...)  # S4 method for ANY,character get_priors(mod, target_engine, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create priors from an existing distribution model — get_priors","text":"mod fitted DistributionModel object. instead BiodiversityDistribution object passed function, simply returns contained priors used estimation (). target_engine character priors created. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create priors from an existing distribution model — get_priors","text":"engines support priors similar ways. See vignettes help pages topic!","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create priors from an existing distribution model — get_priors","text":"","code":"if (FALSE) {  mod <- distribution(background) |>     add_predictors(covariates) |>     add_biodiversity_poipo(points) |>     engine_inlabru() |>     train()  get_priors(mod, target_engine = \"BART\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to extract directly the raster value of provided points — get_rastervalue","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"function simply extracts values provided SpatRaster, SpatRasterDataset SpatRasterCollection object. points NA values extracted small buffer applied try obtain remaining values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"","code":"get_rastervalue(coords, env, ngb_fill = TRUE, rm.na = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"coords data.frame, matrix sf object. env SpatRaster object provided predictors. ngb_fill logical whether cells interpolated neighbouring values. rm.na logical parameter - set - removes rows missing data point (NA) result.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"data.frame extracted covariate data provided data point.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"essentially wrapper terra::extract.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"","code":"if (FALSE) { # Extract values vals <- get_rastervalue(coords, env) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis.iSDM.html","id":null,"dir":"Reference","previous_headings":"","what":"ibis.iSDM — ibis.iSDM","title":"ibis.iSDM — ibis.iSDM","text":"Integrated framework modelling distribution species ecosystems suitability framing. package allows estimation integrated species distribution models (iSDM) based several sources evidence provided presence-presence-absence datasets. makes heavy use point-process models estimating habitat suitability allows include spatial latent effects priors estimation. 'ibis.iSDM' supports number engines Bayesian non-parametric machine learning estimation. , 'ibis.iSDM' specifically customized support spatial-temporal projections habitat suitability future.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis.iSDM.html","id":"author","dir":"Reference","previous_headings":"","what":"Author","title":"ibis.iSDM — ibis.iSDM","text":"Maintainer: Martin Jung jung@iiasa.ac.(ORCID) [copyright holder] contributors: Maximilian H.K. Hesselbarth hesselbarth@iiasa.ac.(ORCID) [contributor]","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":null,"dir":"Reference","previous_headings":"","what":"Install ibis dependencies — ibis_dependencies","title":"Install ibis dependencies — ibis_dependencies","text":"dependencies (R-Packages) ibis.iSDM relies intention added Description file keep number mandatory dependencies small enable package run even systems might libraries pre-installed. function provides convenience wrapper install missing dependencies needed. furthermore checks packages require updating updates needed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Install ibis dependencies — ibis_dependencies","text":"","code":"ibis_dependencies(deps = getOption(\"ibis.dependencies\"), update = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Install ibis dependencies — ibis_dependencies","text":"deps vector names packages installed (Default: \"ibis.dependencies\" ibis_options). update logical flag whether (installed) packages also checked updates (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Install ibis dependencies — ibis_dependencies","text":"Nothing. Packages installed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Install ibis dependencies — ibis_dependencies","text":"INLA handled special way available via cran.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Install ibis dependencies — ibis_dependencies","text":"","code":"if (FALSE) {   # Install and update all dependencies   ibis_dependencies() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":null,"dir":"Reference","previous_headings":"","what":"Options to set up ibis for parallel processing with future — ibis_future","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"Options set ibis parallel processing future","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"","code":"ibis_future(   cores = getOption(\"ibis.nthread\"),   strategy = getOption(\"ibis.futurestrategy\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"cores numeric number stating number cores use. strategy character denoting strategy used future. See help future options. (Default: \"multisession\").","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"None","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"","code":"if (FALSE) { # Starts future job ibis_future(cores = 4) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":null,"dir":"Reference","previous_headings":"","what":"Print ibis options — ibis_options","title":"Print ibis options — ibis_options","text":"number hidden options can specified ibis.iSDM. Currently supported : 'ibis.runparallel' : logical value whether processing run parallel. 'ibis.nthread' : numeric value many cores used default. 'ibis.setupmessages' : logical value indicating whether message object creation shown. 'ibis.engines' : Returns vector valid engines. 'ibis.use_future' : logical whether future package used parallel computing.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Print ibis options — ibis_options","text":"","code":"ibis_options()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Print ibis options — ibis_options","text":"output getOptions ibis related variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Print ibis options — ibis_options","text":"","code":"ibis_options() #> $ibis.cleannames #> [1] TRUE #>  #> $ibis.corPred #> [1] 0.7 #>  #> $ibis.dependencies #>  [1] \"pdp\"           \"scales\"        \"biscale\"       \"modEvA\"        #>  [5] \"dplyr\"         \"geodist\"       \"geosphere\"     \"progress\"      #>  [9] \"glmnet\"        \"glmnetUtils\"   \"xgboost\"       \"BoomSpikeSlab\" #> [13] \"INLA\"          \"inlabru\"       \"gnlm\"          \"cubelyr\"       #> [17] \"matrixStats\"   \"Boruta\"        \"abess\"         \"gdalUtilities\" #> [21] \"dbarts\"        \"mboost\"        \"rstan\"         \"cmdstanr\"      #> [25] \"biscale\"       \"poems\"         \"BiocManager\"   #>  #> $ibis.engines #> [1] \"GDB-Model\"     \"BART-Model\"    \"INLABRU-Model\" \"BREG-Model\"    #> [5] \"GLMNET-Model\"  \"GLM-Model\"     \"INLA-Model\"    \"STAN-Model\"    #> [9] \"XGBOOST-Model\" #>  #> $ibis.futurestrategy #> [1] \"multisession\" #>  #> $ibis.nthread #> [1] 3 #>  #> $ibis.priors #> [1] \"INLAPrior\"   \"BARTPrior\"   \"GDBPrior\"    \"GLMNETPrior\" \"XGBPrior\"    #> [6] \"BREGPrior\"   \"STANPrior\"   #>  #> $ibis.pseudoabsence #> Background Settings: 5 parameters #>  #> $ibis.runparallel #> [1] FALSE #>  #> $ibis.seed #> [1] 8459 #>  #> $ibis.setupmessages #> [1] TRUE #>"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":null,"dir":"Reference","previous_headings":"","what":"Approximate missing time steps between dates — interpolate_gaps","title":"Approximate missing time steps between dates — interpolate_gaps","text":"function linearly approximates shares time steps, gaps instance 2010 2020 filled data 2010, 2011, 2012, etc.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Approximate missing time steps between dates — interpolate_gaps","text":"","code":"interpolate_gaps(env, date_interpolation = \"annual\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Approximate missing time steps between dates — interpolate_gaps","text":"env stars object. date_interpolation character missing dates events interpolated. See project().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Approximate missing time steps between dates — interpolate_gaps","text":"logical indicating two SpatRaster objects ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Approximate missing time steps between dates — interpolate_gaps","text":"","code":"if (FALSE) {   # Interpolate stars stack   sc <- interpolate_gaps( stack, \"annual\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":null,"dir":"Reference","previous_headings":"","what":"Check whether a provided object is truly of a specific type — is.Id","title":"Check whether a provided object is truly of a specific type — is.Id","text":"Check whether provided object truly specific type","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Check whether a provided object is truly of a specific type — is.Id","text":"","code":"is.Id(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Check whether a provided object is truly of a specific type — is.Id","text":"x provided Id object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Check whether a provided object is truly of a specific type — is.Id","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":null,"dir":"Reference","previous_headings":"","what":"Tests if an input is a SpatRaster object. — is.Raster","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"Tests input SpatRaster object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"","code":"is.Raster(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"x R Object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":null,"dir":"Reference","previous_headings":"","what":"Is the provided object of type waiver? — is.Waiver","title":"Is the provided object of type waiver? — is.Waiver","text":"provided object type waiver?","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Is the provided object of type waiver? — is.Waiver","text":"","code":"is.Waiver(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Is the provided object of type waiver? — is.Waiver","text":"x provided Waiver object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Is the provided object of type waiver? — is.Waiver","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":null,"dir":"Reference","previous_headings":"","what":"Check whether a formula is valid — is.formula","title":"Check whether a formula is valid — is.formula","text":"Check whether formula valid","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Check whether a formula is valid — is.formula","text":"","code":"is.formula(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Check whether a formula is valid — is.formula","text":"x character object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Check whether a formula is valid — is.formula","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":null,"dir":"Reference","previous_headings":"","what":"Tests if an input is a stars object. — is.stars","title":"Tests if an input is a stars object. — is.stars","text":"Tests input stars object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Tests if an input is a stars object. — is.stars","text":"","code":"is.stars(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Tests if an input is a stars object. — is.stars","text":"x R Object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Tests if an input is a stars object. — is.stars","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":null,"dir":"Reference","previous_headings":"","what":"Identify local limiting factor — limiting","title":"Identify local limiting factor — limiting","text":"Calculates SpatRaster locally limiting factors given projected model. calculate first spartial effect individual covariate model calculated. effect estimated variable responsible decreasing suitability cell. decrease suitability calculated, predictor turn, relative thesuitability achieved predictor took value equal mean predictor associated largest decrease suitability limiting factor.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Identify local limiting factor — limiting","text":"","code":"limiting(mod, plot = TRUE)  # S4 method for ANY limiting(mod, plot = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Identify local limiting factor — limiting","text":"mod fitted 'DistributionModel' object limited factors identified. plot result plotted? (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Identify local limiting factor — limiting","text":"terra object important variable given grid cell.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Identify local limiting factor — limiting","text":"Elith, J., Kearney, M. Phillips, S. (2010), art modelling range-shifting species. Methods Ecology Evolution, 1: 330-342. doi: 10.1111/j.2041-210X.2010.00036.x","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Identify local limiting factor — limiting","text":"","code":"if (FALSE) { o <- limiting(fit) plot(o) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":null,"dir":"Reference","previous_headings":"","what":"Load a pre-computed model — load_model","title":"Load a pre-computed model — load_model","text":"load_model function (opposed write_model) loads previous saved DistributionModel. essentially wrapper readRDS. models loaded, briefly checked validity presence necessary components.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Load a pre-computed model — load_model","text":"","code":"load_model(fname, verbose = getOption(\"ibis.setupmessages\"))  # S4 method for character load_model(fname, verbose = getOption(\"ibis.setupmessages\"))"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Load a pre-computed model — load_model","text":"fname character depicting output filename. verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Load a pre-computed model — load_model","text":"DistributionModel object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Load a pre-computed model — load_model","text":"","code":"if (FALSE) { # Load model mod <- load_model(\"testmodel.rds\")  summary(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":null,"dir":"Reference","previous_headings":"","what":"Mask data with an external layer — mask","title":"Mask data with an external layer — mask","text":"helper function takes existing object created ibis.iSDM package external layer, intersects . currently takes either DistributionModel, BiodiversityDatasetCollection, PredictorDataset BiodiversityScenario input. mask either sf SpatRaster object can chosen. mask converted internally depending object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Mask data with an external layer — mask","text":"","code":"mask.DistributionModel(x, mask, inverse = FALSE, ...)  mask.BiodiversityDatasetCollection(x, mask, inverse = FALSE, ...)  mask.PredictorDataset(x, mask, inverse = FALSE, ...)  mask.BiodiversityScenario(x, mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Mask data with an external layer — mask","text":"x object belonging DistributionModel, BiodiversityDatasetCollection, PredictorDataset BiodiversityScenario. mask sf SpatRaster object. inverse logical flag whether take inverse mask instead (Default: FALSE). ... Passed arguments","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Mask data with an external layer — mask","text":"respective object input type.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Mask data with an external layer — mask","text":"","code":"if (FALSE) { # Build and train a model mod <- distribution(background) |>   add_biodiversity_poipo(species) |>   add_predictors(predictors) |>   engine_glmnet() |>   train()  # Constrain the prediction by another object mod <- mask(mod, speciesrange)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":null,"dir":"Reference","previous_headings":"","what":"Custom messaging function for scripts — myLog","title":"Custom messaging function for scripts — myLog","text":"functions prints message custom header colour.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Custom messaging function for scripts — myLog","text":"","code":"myLog(title = \"[Processing]\", col = \"green\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Custom messaging function for scripts — myLog","text":"title title log output col character indicating text colour used. Supported 'green' / 'yellow' / 'red' ... additional outputs words display","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Custom messaging function for scripts — myLog","text":"","code":"if (FALSE) { myLog(\"[Setup]\", \"red\", \"Some error occurred during data preparation.\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":null,"dir":"Reference","previous_headings":"","what":"Identifier — new_id","title":"Identifier — new_id","text":"Generate new unique identifier.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Identifier — new_id","text":"","code":"new_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Identifier — new_id","text":"\"Id\" object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Identifier — new_id","text":"Identifiers made using uuid::UUIDgenerate().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Identifier — new_id","text":"","code":"# create new id i <- new_id()  # print id print(i) #> id: c4c1b581-e3a3-4f31-9edb-42b13c778037  # convert to character as.character(i) #> [1] \"c4c1b581-e3a3-4f31-9edb-42b13c778037\"  # check if it is an Id object is.Id(i) #> [1] TRUE"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":null,"dir":"Reference","previous_headings":"","what":"Waiver — new_waiver","title":"Waiver — new_waiver","text":"Create waiver object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Waiver — new_waiver","text":"","code":"new_waiver()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Waiver — new_waiver","text":"Object class Waiver.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Waiver — new_waiver","text":"object used represent user manually specified setting, defaults used. explicitly using new_waiver(), means NULL objects can valid setting. use \"waiver\" object inspired ggplot2 prioritizr package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Waiver — new_waiver","text":"","code":"# create new waiver object w <- new_waiver()  # print object print(w) #> list() #> attr(,\"class\") #> [1] \"Waiver\"  # is it a waiver object? is.Waiver(w) #> [1] TRUE"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":null,"dir":"Reference","previous_headings":"","what":"Obtain partial effects of trained model — partial","title":"Obtain partial effects of trained model — partial","text":"Create partial response effect plot trained model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Obtain partial effects of trained model — partial","text":"","code":"partial(   mod,   x.var = NULL,   constant = NULL,   variable_length = 100,   values = NULL,   newdata = NULL,   plot = FALSE,   type = \"response\",   ... )  # S4 method for ANY partial(   mod,   x.var = NULL,   constant = NULL,   variable_length = 100,   values = NULL,   newdata = NULL,   plot = FALSE,   type = \"response\",   ... )  partial.DistributionModel(mod, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Obtain partial effects of trained model — partial","text":"mod trained DistributionModel object fit_best model within. x.var character indicating variable partial effect calculated. constant numeric constant inserted variables. Default calculates mean per variable. variable_length numeric interpolation depth (nr. points) used (Default: 100). values numeric Directly specified values compute partial effects . parameter set anything NULL, parameter \"variable_length\" ignored (Default: NULL). newdata optional data.frame provided data partial estimation (Default: NULL). plot logical indication whether result plotted? type specified type, either 'response' 'predictor'. Can missing. ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Obtain partial effects of trained model — partial","text":"data.frame created partial response.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Obtain partial effects of trained model — partial","text":"default mean calculated across parameters x.var. Instead constant can set (instance 0) applied output.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Obtain partial effects of trained model — partial","text":"","code":"if (FALSE) {  # Do a partial calculation of a trained model  partial(fit, x.var = \"Forest.cover\", plot = TRUE) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":null,"dir":"Reference","previous_headings":"","what":"Visualize the density of the data over the environmental data — partial_density","title":"Visualize the density of the data over the environmental data — partial_density","text":"Based fitted model, plot density observations estimated variable environmental space. Opposed partial spartial functions, rather low-level interfaces, function provides detail light data. also able contrast different variables show used data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Visualize the density of the data over the environmental data — partial_density","text":"","code":"partial_density(mod, x.var, df = FALSE, ...)  # S4 method for ANY,character partial_density(mod, x.var, df = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Visualize the density of the data over the environmental data — partial_density","text":"mod trained DistributionModel object. Requires fitted model inferred prediction. x.var character indicating variable investigated. Can vector length 1 2. df logical plotting data returned instead (Default: FALSE). ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Visualize the density of the data over the environmental data — partial_density","text":"ggplot2 object showing marginal response light data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Visualize the density of the data over the environmental data — partial_density","text":"functions calculates observed density presence absence points whole surface specific variable. can used visually inspect fit model data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Visualize the density of the data over the environmental data — partial_density","text":"default variables x.var hold constant mean.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Visualize the density of the data over the environmental data — partial_density","text":"Warren, D.L., Matzke, N.J., Cardillo, M., Baumgartner, J.B., Beaumont, L.J., Turelli, M., Glor, R.E., Huron, N.., Simões, M., Iglesias, T.L. Piquet, J.C., Dinnage, R. 2021. ENMTools 1.0: R package comparative ecological biogeography. Ecography, 44(4), pp.504-511.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Visualize the density of the data over the environmental data — partial_density","text":"","code":"if (FALSE) {  # Do a partial calculation of a trained model  partial_density(fit, x.var = \"Forest.cover\")  # Or with two variables  partial_density(fit, x.var = c(\"Forest.cover\", \"bio01\")) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":null,"dir":"Reference","previous_headings":"","what":"Plot wrappers — plot","title":"Plot wrappers — plot","text":"Plots information given object plotting object available.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Plot wrappers — plot","text":"","code":"# S3 method for DistributionModel plot(x, what = \"mean\", ...)  # S3 method for BiodiversityDatasetCollection plot(x, ...)  # S3 method for PredictorDataset plot(x, ...)  # S3 method for Engine plot(x, ...)  # S3 method for BiodiversityScenario plot(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Plot wrappers — plot","text":"x object belonging DistributionModel, BiodiversityDatasetCollection, PredictorDataset BiodiversityScenario. case SpatRaster supplied, parameter specifies layer shown (Default: \"mean\"). ... arguments passed x$plot.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Plot wrappers — plot","text":"Graphical output","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Plot wrappers — plot","text":"plotted outputs vary depending object plotted. example fitted DistributionModel output usually fitted spatial prediction (Default: 'mean').","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Plot wrappers — plot","text":"","code":"if (FALSE) { # Build and train a model mod <- distribution(background) |>   add_biodiversity_poipo(species) |>   add_predictors(predictors) |>   engine_glmnet() |>   train() # Plot the resulting model plot(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"function simulates posterior created stan model, therefore providing fast efficient way project coefficients obtained Bayesian models new/novel contexts.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"","code":"posterior_predict_stanfit(   obj,   form,   newdata,   mode = \"predictor\",   family = NULL,   offset = NULL,   draws = NULL )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"obj \"stanfit\" object (used rstan). form formula object created DistributionModel. newdata data.frame new data used prediction. mode character whether linear predictor response summarized. family character giving family simulating linear response values (Default: NULL) offset vector optionally specified offset. draws numeric indicating whether specific number draws taken.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"https://medium.com/@alex.pavlakis/making-predictions--stan-models--r-3e349dfac1ed. brms R-package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":null,"dir":"Reference","previous_headings":"","what":"Create spatial derivative of raster stacks — predictor_derivate","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"function creates derivatives existing covariates returns Raster format. Derivative variables can machine learning literature commonly understood one aspect feature engineering. can particularly powerful introducing non-linearities otherwise linear models, example often done popular Maxent framework.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"","code":"predictor_derivate(   env,   option,   nknots = 4,   deriv = NULL,   int_variables = NULL,   method = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"env SpatRaster object. option vector stating whether predictors preprocessed way (Options: 'none', 'quadratic', 'hinge', 'thresh', 'bin'). nknots number knots used transformation (Default: 4). deriv vector character specific derivates create (Default: NULL). int_variables vector length greater equal 2 specifying covariates  (Default: NULL). method 'option' intuitive method setting. Can left empty (case option set). ... options (Non specified).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"Returns derived adjusted SpatRaster objects identical resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"Available options : 'none' - original layer(s) returned. 'quadratic' - quadratic transformation (\\(x^{2}\\)) created provided layers. 'hinge' - Creates hinge transformation covariates, set values lower set threshold 0 others range \\([0,1]\\). number thresholds thus new derivates specified via parameter 'nknots' (Default: 4). 'interaction' - Creates interactions variables. Target variables specified via \"int_variables\". 'thresh' - threshold transformation covariates, sets values lower set threshold 0 larger 1. number thresholds thus new derivates specified via parameter 'nknots' (Default: 4). 'bin' - Creates factor representation covariates cutting range covariates percentiles. number percentile cuts thus new derivates specified via parameter 'nknots' (Default: 4).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"","code":"if (FALSE) { # Create a hinge transformation of one or multiple SpatRaster. predictor_derivate(covs, option = \"hinge\", knots = 4) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":null,"dir":"Reference","previous_headings":"","what":"Filter a set of correlated predictors to fewer ones — predictor_filter","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"function helps remove highly correlated variables set predictors. supports multiple options require environmental predictors observations, others predictors. options require different packages pre-installed, ranger Boruta.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"","code":"predictor_filter(env, keep = NULL, method = \"pearson\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"env data.frame matrix extracted environmental covariates given species. keep vector variables keep regardless. usually variables prior information known. method method use constructing correlation matrix (Options: 'pearson' (Default), 'spearman'| 'kendal'), \"abess\", \"boruta\". ... options specific method","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"character  vector variable names excluded. function fails due reason return NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"Available options : \"none\" prior variable removal performed (Default). \"pearson\", \"spearman\" \"kendall\" Makes use pairwise comparisons identify remove highly collinear predictors (Pearson's r >= 0.7). \"abess\" -priori adaptive best subset selection covariates via abess package (see References). Note effectively fits separate generalized linear model reduce number covariates. \"boruta\" Uses Boruta package identify non-informative features.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"Using function predictors effectively means separate model fitted data assumptions come (e.g. linearity, appropriateness response, normality, etc).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"","code":"if (FALSE) {  # Remove highly correlated predictors  env <- predictor_filter( env, option = \"pearson\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":null,"dir":"Reference","previous_headings":"","what":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"method allows homogenization missing data across set environmental predictors. default called predictors added BiodiversityDistribution object. grid cells NAs contain values raster layers homogenized. Additional parameters allow instead homogenization fill missing data neighbouring values","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"","code":"predictor_homogenize_na(   env,   fill = FALSE,   fill_method = \"ngb\",   return_na_cells = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"env SpatRaster object predictors. fill logical value indicating whether missing data filled (Default: FALSE). fill_method character method filling gaps used (Default: 'ngb'). return_na_cells logical value whether ids grid cells NA values returned instead (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"SpatRaster object number layers input.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"","code":"if (FALSE) {  # Harmonize predictors  env <- predictor_homogenize_na(env) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":null,"dir":"Reference","previous_headings":"","what":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"function allows transformation provided environmental predictors (SpatRaster format). common use case instance standardization (scaling) predictors prior model fitting. function works SpatRaster well stars objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"","code":"predictor_transform(   env,   option,   windsor_props = c(0.05, 0.95),   pca.var = 0.8,   method = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"env SpatRaster object. option vector stating whether predictors preprocessed way (Options: 'none', 'scale', 'norm', 'windsor', 'windsor_thresh', 'percentile' 'pca', 'revjack'). See Details. windsor_props numeric vector specifying proportions clipped windsorization (Default: c(.05,.95)). pca.var numeric value >0 1 stating minimum amount variance covered (Default: 0.8). method 'option' intuitive method setting. Can left empty (case option set). ... options (Non specified).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"Returns adjusted SpatRaster object identical resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"Available options : 'none' original layer(s) returned. 'scale' run scale() function default settings (1 Standard deviation) across predictors. sensible default model fitting. 'norm' normalizes predictors range 0-1. 'windsor' applies 'windsorization' existing raster layer setting lowest, respectively largest values value certain percentage level (e.g. 95%). can set via parameter \"windsor_props\". 'windsor_thresh' option 'windsor', however case values clamped thresholds rather certain percentages calculated data. 'percentile' converts bins values percentiles, e.g. top 10% lowest 10% values . 'pca' option runs principal component decomposition predictors (via prcomp()). returns new predictors resembling components order important ones. Can useful reduce collinearity, however note changes predictor names 'PCX', X number component. parameter 'pca.var' can modified specify minimum variance covered axes. 'revjack' Removes outliers supplied stack via reverse jackknife procedure. Identified outliers default set NA.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"","code":"if (FALSE) { # Where x is a SpatRaster new_x <- predictor_transform(x, option = 'scale') }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":null,"dir":"Reference","previous_headings":"","what":"Print — print","title":"Print — print","text":"Display information object created ibis.iSDM R-package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Print — print","text":"","code":"# S3 method for distribution print(x, ...)  # S3 method for BiodiversityDistribution print(x, ...)  # S3 method for BiodiversityDatasetCollection print(x, ...)  # S3 method for BiodiversityDataset print(x, ...)  # S3 method for PredictorDataset print(x, ...)  # S3 method for DistributionModel print(x, ...)  # S3 method for BiodiversityScenario print(x, ...)  # S3 method for Prior print(x, ...)  # S3 method for PriorList print(x, ...)  # S3 method for Engine print(x, ...)  # S3 method for Settings print(x, ...)  # S3 method for Log print(x, ...)  # S3 method for Id print(x, ...)  # S4 method for Id print(x, ...)  # S4 method for tbl_df print(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Print — print","text":"x object created package. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Print — print","text":"Object specific.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Print — print","text":"","code":"if (FALSE) { # Where mod is fitted object mod print(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Creates a new PriorList object — priors","title":"Creates a new PriorList object — priors","text":"PriorList object essentially list contains individual Prior objects. order use priors engines, respective Prior identified (e.g. INLAPrior) embedded PriorList object. Afterwards objects can added distribution object add_priors function. PriorList object essentially list contains individual Prior objects. order use priors engines, respective Prior identified (e.g. INLAPrior) embedded PriorList object. Afterwards objects can added distribution object add_priors function.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Creates a new PriorList object — priors","text":"","code":"priors(x, ...)  # S4 method for ANY priors(x, ...)  priors(x, ...)  # S4 method for ANY priors(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Creates a new PriorList object — priors","text":"x Prior object added list. ... One multiple additional Prior object added list.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Creates a new PriorList object — priors","text":"PriorList object. PriorList object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Creates a new PriorList object — priors","text":"","code":"p1 <- GDBPrior(variable = \"Forest\", hyper = \"positive\") p2 <- GDBPrior(variable = \"Urban\", hyper = \"decreasing\") priors(p1, p2) #> Set priors: 2  if (FALSE) { p1 <- INLAPrior(variable = \"Forest\",type = \"normal\", hyper = c(1,1e4)) p2 <- INLAPrior(variable = \"Urban\",type = \"normal\", hyper = c(0,1e-2)) priors(p1, p2) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":null,"dir":"Reference","previous_headings":"","what":"Project a fitted model to a new environment and covariates — project","title":"Project a fitted model to a new environment and covariates — project","text":"Equivalent train, function acts wrapper project model stored BiodiversityScenario object newly supplied (future) covariates. Supplied predictors usually spatial-temporal predictors prepared via add_predictors() (e.g. transformations derivates) way initial modelling distribution(). constrains specified scenario object applied projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Project a fitted model to a new environment and covariates — project","text":"","code":"project.BiodiversityScenario(x, ...)  # S4 method for BiodiversityScenario project(   x,   date_interpolation = \"none\",   stabilize = FALSE,   stabilize_method = \"loess\",   layer = \"mean\",   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Project a fitted model to a new environment and covariates — project","text":"x BiodiversityScenario object set predictors. Note constrains MigClim can still simulate future change without projections. ... passed parameters. date_interpolation character whether dates interpolated. Options include \"none\" (Default), \"annual\", \"monthly\", \"daily\". stabilize logical value indicating whether suitability projection stabilized (Default: FALSE). stabilize_method character stating stabilization method applied. Currently supported `loess`. layer character specifying layer projected (Default: \"mean\"). verbose Setting logical value TRUE prints information model fitting (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Project a fitted model to a new environment and covariates — project","text":"Saves stars objects obtained predictions mod.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Project a fitted model to a new environment and covariates — project","text":"background function x$project() respective model object called, x fitted model object. specifics constraints, see relevant constrain functions, respectively: add_constraint() generic wrapper add available constrains. add_constraint_dispersal() specifying dispersal constraint temporal projections step. add_constraint_MigClim() Using MigClim R-package simulate dispersal projections. add_constraint_connectivity() Apply connectivity constraint projection, instance adding barrier prevents migration. add_constraint_minsize() Adds constraint minimum area given thresholded patch , assuming smaller areas fact suitable. add_constraint_adaptability() Apply adaptability constraint projection, instance constraining speed species able adapt new conditions. add_constraint_boundary() artificially limit distribution change. Similar specifying projection limits, can used specifically constrain projection within certain area (e.g. species range island). Many constrains also requires thresholds calculated. Adding threshold() BiodiversityScenario object enables computation thresholds every step based threshold used main model (threshold values taken ). also possible make complementary simulation steps package, can provided via simulate_population_steps() BiodiversityScenario object. Similar thresholds, estimates values added outputs. Finally function also allows temporal stabilization across prediction steps via enabling parameter stabilize checking stablize_method argument. Stabilization can instance helpful situations environmental variables quite dynamic, changes projected suitability expected abruptly increase decrease. thus way smoothen outliers projection. Options far instance 'loess' fits loess() model per pixel time step. conducted processing steps thresholds recalculated afterwards.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Project a fitted model to a new environment and covariates — project","text":"","code":"if (FALSE) { # Fit a model fit <- distribution(background) |>         add_biodiversity_poipa(surveydata) |>         add_predictors(env = predictors) |>         engine_breg() |>         train()  # Fit a scenario sc <- scenario(fit) |>         add_predictors(env = future_predictors) |>         project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":null,"dir":"Reference","previous_headings":"","what":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"function defines settings pseudo-absence sampling background. many engines points necessary model Poisson (Binomial) distributed point process data. Specifically call absence points Binomial (Bernoulli really) distributed responses 'pseudo-absence' absence data Poisson responses 'background' points. details read Renner et al. (2015). function 'add_pseudoabsence' allows add absence points sf object. See Details additional parameter description examples 'turn' presence-dataset presence-(pseudo-)absence.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"","code":"pseudoabs_settings(   background = NULL,   nrpoints = 10000,   min_ratio = 0.25,   method = \"random\",   buffer_distance = 10000,   inside = FALSE,   layer = NULL,   bias = NULL,   ... )  # S4 method for ANY pseudoabs_settings(   background = NULL,   nrpoints = 10000,   min_ratio = 0.25,   method = \"random\",   buffer_distance = 10000,   inside = FALSE,   layer = NULL,   bias = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"background SpatRaster sf object background points can sampled. Default NULL (Default) background added sampling first called. nrpoints numeric given number absence points created. larger 0 normally points created excess number cells background (Default: 10000). min_ratio numeric minimum ratio background points relative presence points. Setting value 1 generates equal amount absence points relative presence points. Usually ignored unless ratio exceeds nrpoints parameters (Default: 0.25). method character denoting sampling done. See details options (Default: \"random\"). buffer_distance numeric distance observations pseudo-absence points generated. Note units follow units projection (e.g. m °). used method = \"buffer\". inside logical value whether absence points sampled outside (Default) inside minimum convex polygon range provided respective method chosen (parameter method = \"mcp\" method = \"range\"). layer sf SpatRaster (case method 'zones') object indicating range species. used method = \"range\" method = \"zones\" (Default: NULL). bias SpatRaster extent projection background. Absence points preferentially sampled areas higher (!) bias. (Default: NULL). ... settings added pseudoabs settings.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"multiple methods available sampling biased background layer. Possible parameters method : 'random' Absence points generated randomly background (Default), 'buffer' Absence points generated within buffered distance existing points. option requires specification parameter buffer_distance. 'mcp' Can used generate absence points within outside minimum convex polygon presence points. parameter inside specifies whether points sampled inside outside (Default) minimum convex polygon. 'range' Absence points created either inside outside provided additional layer indicates example range species (controlled parameter inside). 'zones' ratified (e.g. type factor) SpatRaster layer depicting zones absence points sampled. method checks points fall within zones samples absence points either within outside zones exclusively. 'layer' 'inside' set option. 'target' Make use target background sampling absence points. SpatRaster object provided parameter 'layer'. Absence points sampled exclusively within target areas grid cells non-zero values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"Renner IW, Elith J, Baddeley , Fithian W, Hastie T, Phillips SJ, Popovic G, Warton DI. 2015. Point process models presence-analysis. Methods Ecology Evolution 6:366–379. DOI: 10.1111/2041-210X.12352. Renner, . W., & Warton, D. . (2013). Equivalence MAXENT Poisson point process models species distribution modeling ecology. Biometrics, 69(1), 274-281.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"","code":"if (FALSE) { # This setting generates 10000 pseudo-absence points outside the # minimum convex polygon of presence points ass1 <- pseudoabs_settings(nrpoints = 10000, method = 'mcp', inside = FALSE)  # This setting would match the number of presence-absence points directly. ass2 <- pseudoabs_settings(nrpoints = 0, min_ratio = 1)  # These settings can then be used to add pseudo-absence data to a # presence-only dataset. This effectively adds these simulated absence # points to the resulting model all_my_points <- add_pseudoabsence(                      df = virtual_points,                       field_occurrence = 'observed',                       template = background,                       settings = ass1) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":null,"dir":"Reference","previous_headings":"","what":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"Remove particular dataset () distribution object BiodiversityDatasetCollection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"","code":"rm_biodiversity(x, name, id)  # S4 method for BiodiversityDistribution rm_biodiversity(x, name, id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"x distribution() (.e. BiodiversityDistribution) object. name character name biodiversity dataset. id character id biodiversity dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"","code":"if (FALSE) { distribution(background) |>  add_biodiversity_poipa(species, \"Duckus communus\")  rm_biodiversity(names = \"Duckus communus\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to remove a latent effect — rm_latent","title":"Function to remove a latent effect — rm_latent","text":"just wrapper function removing specified offsets BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to remove a latent effect — rm_latent","text":"","code":"rm_latent(x)  # S4 method for BiodiversityDistribution rm_latent(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to remove a latent effect — rm_latent","text":"x distribution() (.e. BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to remove a latent effect — rm_latent","text":"Removes latent spatial effect distribution object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to remove a latent effect — rm_latent","text":"","code":"if (FALSE) {  rm_latent(model) -> model }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to remove an offset — rm_offset","title":"Function to remove an offset — rm_offset","text":"just wrapper function removing specified offsets BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to remove an offset — rm_offset","text":"","code":"rm_offset(x, layer = NULL)  # S4 method for BiodiversityDistribution rm_offset(x, layer = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to remove an offset — rm_offset","text":"x distribution() (.e. BiodiversityDistribution) object. layer character pointing specific layer removed. set NULL, offsets removed object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to remove an offset — rm_offset","text":"Removes offset distribution object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to remove an offset — rm_offset","text":"","code":"if (FALSE) {  rm_offset(model) -> model }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":null,"dir":"Reference","previous_headings":"","what":"Remove specific predictors from a distribution object — rm_predictors","title":"Remove specific predictors from a distribution object — rm_predictors","text":"Remove particular variable distribution object PredictorDataset. See Examples.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Remove specific predictors from a distribution object — rm_predictors","text":"","code":"rm_predictors(x, names)  # S4 method for BiodiversityDistribution,character rm_predictors(x, names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Remove specific predictors from a distribution object — rm_predictors","text":"x distribution() (.e. BiodiversityDistribution) object. names vector Vector character names describing environmental stack.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Remove specific predictors from a distribution object — rm_predictors","text":"","code":"if (FALSE) { distribution(background) |>  add_predictors(my_covariates) |>  rm_predictors(names = \"Urban\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Remove existing priors from an existing distribution object — rm_priors","title":"Remove existing priors from an existing distribution object — rm_priors","text":"function allows remove priors existing distribution object. order remove set prior, name prior specified.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Remove existing priors from an existing distribution object — rm_priors","text":"","code":"rm_priors(x, names = NULL, ...)  # S4 method for BiodiversityDistribution rm_priors(x, names = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Remove existing priors from an existing distribution object — rm_priors","text":"x distribution (.e. BiodiversityDistribution) object. names vector character object priors removed. ... parameters passed ","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Remove existing priors from an existing distribution object — rm_priors","text":"","code":"if (FALSE) {  # Add prior  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  # Remove again  x <- x |> rm_priors(\"forest\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":null,"dir":"Reference","previous_headings":"","what":"Fit cmdstanr model and convert to rstan object — run_stan","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"function fits stan model using light-weight interface provided cmdstanr. code adapted McElreath rethinking package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"","code":"run_stan(   model_code,   data = list(),   algorithm = \"sampling\",   chains = 4,   cores = getOption(\"ibis.nthread\"),   threads = 1,   iter = 1000,   warmup = floor(iter/2),   control = list(adapt_delta = 0.95),   cpp_options = list(),   force = FALSE,   path = base::getwd(),   save_warmup = TRUE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"model_code character pointing stan modelling code. data list parameters required run model_code stan. algorithm character giving algorithm use. Either 'sampling' (Default), 'optimize' 'variational' penalized likelihood estimation. chains numeric indicating number chains use estimation. cores Number threads sampling. Default set 'getOption(\"ibis.nthread\")'. See ibis_options(). threads numeric giving number threads run per chain. specified accordance cores. iter numeric value giving number MCMC samples generate. warmup numeric number warm-samples MCMC. Default set 1/2 iter. control list control options stan. cpp_options list options Cpp compiling. force logical indication whether force recompile model (Default: FALSE). path character indicating path made available stan compiler. save_warmup logical flag whether save warmup samples. ... non-specified parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"rstan object","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":null,"dir":"Reference","previous_headings":"","what":"Sanitize variable names — sanitize_names","title":"Sanitize variable names — sanitize_names","text":"Prepared covariates often special characters variable names can can used formulas cause errors certain engines. function converts special characters variable names format","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Sanitize variable names — sanitize_names","text":"","code":"sanitize_names(names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Sanitize variable names — sanitize_names","text":"names vector character vectors sanitized.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Sanitize variable names — sanitize_names","text":"vector sanitized character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Sanitize variable names — sanitize_names","text":"","code":"# Correct variable names vars <- c(\"Climate-temperature2015\", \"Elevation__sealevel\", \"Landuse.forest..meanshare\") sanitize_names(vars) #> [1] \"Climate_temperature2015\"   \"Elevation_sealevel\"        #> [3] \"Landuse.forest..meanshare\""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new scenario based on trained model parameters — scenario","title":"Create a new scenario based on trained model parameters — scenario","text":"function creates new BiodiversityScenario object contains projections model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new scenario based on trained model parameters — scenario","text":"","code":"scenario(fit, limits = NULL, reuse_limits = FALSE, copy_model = FALSE)  # S4 method for ANY scenario(fit, limits = NULL, reuse_limits = FALSE, copy_model = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new scenario based on trained model parameters — scenario","text":"fit BiodiversityDistribution object containing trained model. limits SpatRaster sf object limits projection surface intersected prediction data (Default: NULL). can instance set expert-delineated constrain limit spatial projections. reuse_limits logical whether reuse limits found trained BiodiversityDistribution object (Default: FALSE). See also notes! copy_model logical whether model object copied scenario object. Note setting option TRUE can increase required amount memory (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create a new scenario based on trained model parameters — scenario","text":"limit defined already train(), example adding extrapolation limit add_control_extrapolation(), zonal layer can reused projections. Note: effectively fixes projections certain areas.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new scenario based on trained model parameters — scenario","text":"","code":"if (FALSE) {   scenario(fit, limits = island_area) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":null,"dir":"Reference","previous_headings":"","what":"Select specific predictors from a distribution object — sel_predictors","title":"Select specific predictors from a distribution object — sel_predictors","text":"function allows - character vector names already added PredictorDataset object - select particular set predictors. See Examples.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Select specific predictors from a distribution object — sel_predictors","text":"","code":"sel_predictors(x, names)  # S4 method for BiodiversityDistribution,character sel_predictors(x, names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Select specific predictors from a distribution object — sel_predictors","text":"x distribution() (.e. BiodiversityDistribution) object. names vector Vector character names describing environmental stack.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Select specific predictors from a distribution object — sel_predictors","text":"","code":"if (FALSE) { distribution(background) |>  add_predictors(my_covariates) |>  sel_predictors(names = c(\"Forest\", \"Elevation\")) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":null,"dir":"Reference","previous_headings":"","what":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"function simply allows add priors existing distribution object. supplied priors must PriorList object created calling priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"","code":"# S4 method for BiodiversityDistribution set_priors(x, priors = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"x distribution (.e. BiodiversityDistribution) object. priors PriorList object containing multiple priors. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"Alternatively priors environmental predictors can also directly added parameter via add_predictors","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"","code":"if (FALSE) {  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Add priors to an existing distribution object — set_priors","title":"Add priors to an existing distribution object — set_priors","text":"function simply allows add priors existing distribution object. supplied priors must PriorList object created calling priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add priors to an existing distribution object — set_priors","text":"","code":"set_priors(x, priors = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add priors to an existing distribution object — set_priors","text":"x distribution (.e. BiodiversityDistribution) object. priors PriorList object containing multiple priors. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add priors to an existing distribution object — set_priors","text":"Alternatively priors environmental predictors can also directly added parameter via add_predictors","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add priors to an existing distribution object — set_priors","text":"","code":"if (FALSE) {  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":null,"dir":"Reference","previous_headings":"","what":"Calculate environmental similarity of reference datasets to predictors. — similarity","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"Calculate environmental similarity provided covariates respect reference dataset. Currently supported Multivariate Environmental Similarity index multivariate combination novelty index (NT2) based Mahalanobis divergence (see references).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"","code":"similarity(   obj,   ref,   ref_type = \"poipo\",   method = \"mess\",   predictor_names = NULL,   full = FALSE,   plot = TRUE,   ... )  # S4 method for BiodiversityDistribution similarity(   obj,   ref,   ref_type = \"poipo\",   method = \"mess\",   predictor_names = NULL,   full = FALSE,   plot = TRUE,   ... )  # S4 method for SpatRaster similarity(   obj,   ref,   ref_type = \"poipo\",   method = \"mess\",   predictor_names = NULL,   full = FALSE,   plot = TRUE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"obj BiodiversityDistribution, DistributionModel alternatively SpatRaster object. ref BiodiversityDistribution, DistributionModel alternatively data.frame extracted values (corresponding given obj). ref_type character specifying type biodiversity use obj BiodiversityDistribution. method specifc method similarity calculation. Currently supported: 'mess', 'nt'. predictor_names optional character specifying covariates used (Default: NULL). full similarity values returned variables (Default:FALSE)? plot result plotted? Otherwise return output list (Default: TRUE). ... options (Non specified).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"function returns list containing: similarity: SpatRaster object multiple layers giving environmental similarities variable x (included \"full=TRUE\"); mis: SpatRaster layer giving minimum similarity value across variables location (.e. MESS); exip: SpatRaster layer indicating whether model interpolate extrapolate location based environmental surface; mod: factor SpatRaster layer indicating variable dissimilar reference range (.e. MoD map, Elith et al. 2010); mos: factor SpatRaster layer indicating variable similar reference range.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"similarity implements MESS algorithm described Appendix S3 Elith et al. (2010) well Mahalanobis dissimilarity described Mesgaran et al. (2014).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"Elith, J., Kearney, M., Phillips, S. (2010) \"art modelling range-shifting species\". Methods Ecology Evolution, 1: 330-342. https://doi.org/10.1111/j.2041-210X.2010.00036.x Mesgaran, M.B., Cousens, R.D. Webber, B.L. (2014) \"dragons: tool quantifying novelty due covariate range correlation change projecting species distribution models\". Diversity Distributions, 20: 1147-1159. https://doi.org/10.1111/ddi.12209","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"","code":"if (FALSE) { plot(   similarity(x) # Where x is a distribution or Raster object )  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":null,"dir":"Reference","previous_headings":"","what":"Simulate population dynamics following the steps approach — simulate_population_steps","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"function adds flag BiodiversityScenario object indicate species abundances simulated based expected habitat suitability, well demography, density-dependence dispersal information. simulation done using steps package (Visintin et al. 2020) conducted habitat suitability projection created. steps spatially explicit population models coded mostly R. detailed description steps parameters, please see respective reference help files. Default assumptions underlying wrapper presented details","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"","code":"simulate_population_steps(   mod,   vital_rates,   replicates = 1,   carrying_capacity = NULL,   initial = NULL,   dispersal = NULL,   density_dependence = NULL,   include_suitability = TRUE )  # S4 method for BiodiversityScenario,matrix simulate_population_steps(   mod,   vital_rates,   replicates = 1,   carrying_capacity = NULL,   initial = NULL,   dispersal = NULL,   density_dependence = NULL,   include_suitability = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"mod BiodiversityScenario object specified predictors. vital_rates symmetrical demographic matrix. column row names equivalent vital stages estimated. replicates numeric vector number replicates (Default: 1). carrying_capacity Either SpatRaster numeric estimate maximum carrying capacity, e.g. many adult individual likely occur per grid cell. set numeric, carrying capacity estimated maximum set (Note: clever way use species-area relationship scaling. yet implemented). initial SpatRaster giving initial population size. provided, initial populations guessed (see details) projected suitability rasters (Default: NULL). dispersal dispersal object defined steps package (Default: NULL). density_dependence Specification density dependence defined steps package (Default: NULL). include_suitability logical flag whether projected suitability estimates used (Default: TRUE) initial conditions set first time step.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"Adds flag BiodiversityScenario object indicate simulations added projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"order function work steps package installed separately. Instructions can found github. initial population lifestages provided, estimated assuming linear scaling suitability, 50:50 split sexes 1:3 ratio adults juveniles. provision different parameters highly encouraged!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"steps package multiple options simulating species population possible options represented wrapper. Furthermore, package still makes use raster package much internal data processing. Since ibis.iSDM switched terra ago, can efficiency problems layers need translated packages.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"Visintin, C., Briscoe, N. J., Woolley, S. N., Lentini, P. E., Tingley, R., Wintle, B. ., & Golding, N. (2020). steps: Software spatially temporally explicit population simulations. Methods Ecology Evolution, 11(4), 596-603. https://doi.org/10.1111/2041-210X.13354","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"","code":"if (FALSE) { # Define vital rates vt <- matrix(c(0.0,0.5,0.75,                0.5,0.2,0.0,                0.0,0.5,0.9),                nrow = 3, ncol = 3, byrow = TRUE) colnames(vt) <- rownames(vt) <- c('juvenile','subadult','adult')  # Assumes that a trained 'model' object exists  mod <- scenario(model) |>   add_predictors(env = predictors, transform = 'scale',                  derivates = \"none\") |>   # Use Vital rates here, but note the other parameters!   simulate_population_steps(vital_rates = vt) |>   project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":null,"dir":"Reference","previous_headings":"","what":"Obtain spatial partial effects of trained model — spartial","title":"Obtain spatial partial effects of trained model — spartial","text":"Similar partial function calculates partial response trained model given variable. Differently partial space. However result SpatRaster showing spatial magnitude partial response.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Obtain spatial partial effects of trained model — spartial","text":"","code":"spartial(mod, x.var, constant = NULL, newdata = NULL, plot = FALSE, ...)  # S4 method for ANY,character spartial(mod, x.var, constant = NULL, newdata = NULL, plot = FALSE, ...)  spartial.DistributionModel(mod, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Obtain spatial partial effects of trained model — spartial","text":"mod DistributionModel object trained model. x.var character indicating variable partial effect calculated. constant numeric constant inserted variables. Default calculates mean per variable. newdata data.frame calculate spartial . Can example created raster file (Default: NULL). plot logical indication whether result plotted? ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Obtain spatial partial effects of trained model — spartial","text":"SpatRaster containing mapped partial response variable.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Obtain spatial partial effects of trained model — spartial","text":"default mean calculated across parameters x.var. Instead constant can set (instance 0) applied output.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Obtain spatial partial effects of trained model — spartial","text":"","code":"if (FALSE) {  # Create and visualize the spartial effect  spartial(fit, x.var = \"Forest.cover\", plot = TRUE) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":null,"dir":"Reference","previous_headings":"","what":"Show the stan code from a trained model — stancode","title":"Show the stan code from a trained model — stancode","text":"helper function shows code trained DistributionModel using engine_stan. function emulated similar functionality brms R-package. works models inferred stan!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Show the stan code from a trained model — stancode","text":"","code":"stancode(obj, ...)  stancode.DistributionModel(obj, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Show the stan code from a trained model — stancode","text":"obj prepared object. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Show the stan code from a trained model — stancode","text":"None.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":null,"dir":"Reference","previous_headings":"","what":"Summarises a trained model or predictor object — summary","title":"Summarises a trained model or predictor object — summary","text":"helper function summarizes given object, including DistributionModel, PredictorDataset PriorList objects others. can helpful way summarize contained within values specified models objects. unsure, usually good strategy run summary object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Summarises a trained model or predictor object — summary","text":"","code":"# S3 method for distribution summary(object, ...)  # S3 method for DistributionModel summary(object, ...)  # S3 method for PredictorDataset summary(object, ...)  # S3 method for BiodiversityScenario summary(object, ...)  # S3 method for PriorList summary(object, ...)  # S3 method for Settings summary(object, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Summarises a trained model or predictor object — summary","text":"object prepared object. ... used.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Summarises a trained model or predictor object — summary","text":"","code":"if (FALSE) { # Example with a trained model x <- distribution(background) |>         # Presence-absence data         add_biodiversity_poipa(surveydata) |>         # Add predictors and scale them         add_predictors(env = predictors) |>         # Use glmnet and lasso regression for estimation         engine_glmnet(alpha = 1)  # Train the model  mod <- train(x)  summary(mod)   # Example with a prior object  p1 <- BREGPrior(variable = \"forest\", hyper = 2, ip = NULL)  p2 <- BREGPrior(variable = \"cropland\", hyper = NULL, ip = 1)  pp <- priors(p1,p2)  summary(pp) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":null,"dir":"Reference","previous_headings":"","what":"Functionality for geographic and environmental thinning — thin_observations","title":"Functionality for geographic and environmental thinning — thin_observations","text":"species distribution modelling approaches assumed occurrence records unbiased, rarely case. model-based control can alleviate effects sampling bias, can often desirable account sampling biases spatial thinning (Aiello‐Lammens et al. 2015). approach based assumption -sampled grid cells contribute little bias, rather strengthening environmental responses. function provides methods apply spatial thinning approaches. Note effectively removes data prior estimation use considered care (see also Steen et al. 2021).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Functionality for geographic and environmental thinning — thin_observations","text":"","code":"thin_observations(   data,   background,   env = NULL,   method = \"random\",   remainpoints = 10,   mindistance = NULL,   zones = NULL,   probs = 0.75,   global = TRUE,   centers = NULL,   verbose = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Functionality for geographic and environmental thinning — thin_observations","text":"data sf object observed occurrence points. methods threat presence-presence-absence occurrence points equally. background SpatRaster object background study region. Use assessing point density. env SpatRaster object environmental covariates. Needed method set \"environmental\" \"bias\" (Default: NULL). method character method applied (Default: \"random\"). remainpoints numeric giving number data points minimum remain (Default: 10). mindistance numeric minimum distance neighbouring observations (Default: NULL). zones SpatRaster supplied option \"zones\" chosen (Default: NULL). probs numeric used quantile threshold \"bias\" method. (Default: 0.75). global logical \"bias\" method global (entire env raster) local (extracted point locations) bias values used quantile threshold. (Default: TRUE). centers numeric used number centers \"environmental\" method. (Default: NULL). set, automatically set three nlayers - 1 (whatever bigger). verbose logical whether print statistics thinning outcome (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Functionality for geographic and environmental thinning — thin_observations","text":"methods remove points \"-sampled\" grid cells/areas. defined cells/areas either points remainpoints points global minimum point count per cell/area (whichever larger). Currently implemented thinning methods: \"random\": Samples random across -sampled grid cells returning \"remainpoints\" -sampled cells. account spatial environmental distance observations. \"bias\": option removes explicitly points considered biased (based \"env\"). Points thinned grid cells bias quantile (larger values equals greater bias). Thins observations returning \"remainpoints\" -sampled biased cell. \"zones\": Thins observations zone -sampled threshold returns  \"remainpoints\" zone. Careful: zones relatively wide can remove quite observations. \"environmental\": approach creates observation-wide clustering (k-means) assumption full environmental niche comprehensively sampled covered provided covariates env. -sampled cluster, obtain (\"remainpoints\") thinning points. \"spatial\": Calculates spatial distance observations. points removed iteratively minimum distance points crossed. \"mindistance\" parameter set function work.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Functionality for geographic and environmental thinning — thin_observations","text":"Aiello‐Lammens, M. E., Boria, R. ., Radosavljevic, ., Vilela, B., & Anderson, R. P. (2015). spThin: R package spatial thinning species occurrence records use ecological niche models. Ecography, 38(5), 541-545. Steen, V. ., Tingley, M. W., Paton, P. W., & Elphick, C. S. (2021). Spatial thinning class balancing: Key choices lead variation performance species distribution models citizen science data. Methods Ecology Evolution, 12(2), 216-226.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Functionality for geographic and environmental thinning — thin_observations","text":"","code":"if (FALSE) {  # Thin a certain number of observations  # At random  thin_points <- thin_observations(points, background, method = \"random\")  # using a bias layer  thin_points <- thin_observations(points, background, method = \"bias\", env = bias) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":null,"dir":"Reference","previous_headings":"","what":"Threshold a continuous prediction to a categorical layer — threshold","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"common many applications species distribution modelling estimated continuous suitability surfaces converted discrete representations suitable habitat might might exist. called threshold'ing can done various ways described details. case SpatRaster provided input function obj, furthermore necessary provide sf object validation DistributionModel read information . Note: course also allows estimate threshold based withheld data, instance created -priori cross-validation procedure. BiodiversityScenario objects, adding function processing pipeline stores threshold attribute created scenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"","code":"threshold(   obj,   method = \"mtp\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE,   ... )  # S4 method for ANY threshold(   obj,   method = \"mtp\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE,   ... )  # S4 method for SpatRaster threshold(   obj,   method = \"fixed\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE )  # S4 method for BiodiversityScenario threshold(   obj,   method = \"mtp\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"obj BiodiversityScenario object existing threshold added. method specifc method thresholding. See details available options. value numeric value specifying specific threshold scenarios (Default: NULL Grab object). point sf object containing observational data used model training. field_occurrence character location biodiversity point records. format character indication whether \"binary\", \"normalize\" \"percentile\" formatted thresholds created (Default: \"binary\"). Also see Muscatello et al. (2021). return_threshold threshold value returned instead (Default: FALSE) ... parameter. Used fetch value set somehow.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"SpatRaster SpatRaster object input. Otherwise threshold added respective DistributionModel BiodiversityScenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"following options currently implemented: 'fixed' = applies single pre-determined threshold. Requires value set. 'mtp' = minimum training presence used find set lowest predicted suitability occurrence point. 'percentile' = percentile threshold. value parameter set . 'min.cv' = Threshold raster minimize coefficient variation (cv) posterior. Uses lowest tercile cv space. feasible Bayesian engines. 'TSS' = Determines optimal TSS (True Skill Statistic). Requires \"modEvA\" package installed. 'kappa' = Determines optimal kappa value (Kappa). Requires \"modEvA\" package installed. 'F1score' = Determines optimal F1score (also known Sorensen similarity). Requires \"modEvA\" package installed. 'F1score' = Determines optimal sensitivity presence records. Requires \"modEvA\" package installed. 'Sensitivity' = Determines optimal sensitivity presence records. Requires \"modEvA\" package installed. 'Specificity' = Determines optimal sensitivity presence records. Requires \"modEvA\" package installed. 'AUC' = Determines optimal AUC presence records. Requires \"modEvA\" package installed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"Lawson, C.R., Hodgson, J.., Wilson, R.J., Richards, S.., 2014. Prevalence, thresholds performance presence-absence models. Methods Ecol. Evol. 5, 54–64. https://doi.org/10.1111/2041-210X.12123 Liu, C., White, M., Newell, G., 2013. Selecting thresholds prediction species occurrence presence-data. J. Biogeogr. 40, 778–789. https://doi.org/10.1111/jbi.12058 Muscatello, ., Elith, J., Kujala, H., 2021. decisions fitting species distribution models affect conservation outcomes. Conserv. Biol. 35, 1309–1320. https://doi.org/10.1111/cobi.13669","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"","code":"if (FALSE) {  # Where mod is an estimated DistributionModel  tr <- threshold(mod)  tr$plot_threshold() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":null,"dir":"Reference","previous_headings":"","what":"Train the model from a given engine — train","title":"Train the model from a given engine — train","text":"function trains distribution() model specified engine furthermore generic options apply engines (regardless type). See Details regards options. Users advised check help files individual engines advice estimation done.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Train the model from a given engine — train","text":"","code":"train(   x,   runname,   filter_predictors = \"none\",   optim_hyperparam = FALSE,   inference_only = FALSE,   only_linear = TRUE,   method_integration = \"predictor\",   aggregate_observations = TRUE,   clamp = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for BiodiversityDistribution train(   x,   runname,   filter_predictors = \"none\",   optim_hyperparam = FALSE,   inference_only = FALSE,   only_linear = TRUE,   method_integration = \"predictor\",   aggregate_observations = TRUE,   clamp = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Train the model from a given engine — train","text":"x distribution() (.e. BiodiversityDistribution) object). runname character name trained run. filter_predictors character defining highly correlated predictors removed prior model estimation. Available options : \"none\" prior variable removal performed (Default). \"pearson\", \"spearman\" \"kendall\" Makes use pairwise comparisons identify remove highly collinear predictors (Pearson's r >= 0.7). \"abess\" -priori adaptive best subset selection covariates via \"abess\" package (see References). Note effectively fits separate generalized linear model reduce number covariates. \"boruta\" Uses \"Boruta\" package identify non-informative features. optim_hyperparam Parameter tune model iterating input parameters selection predictors included iteration. Can set TRUE extra precision needed (Default: FALSE). inference_only default engine used create spatial prediction suitability surface, can take time. inferences strength relationship covariates observations required, parameter can set TRUE ignore spatial projection (Default: FALSE). only_linear Fit model linear baselearners functions. Depending engine setting option FALSE result non-linear relationships observations covariates, often increasing processing time (Default: TRUE). non-linearity captured depends used engine. method_integration character type integration applied one BiodiversityDataset object provided x. Particular relevant engines support integration one dataset. Integration methods generally sensitive order added BiodiversityDistribution object. Available options : \"predictor\" predicted output first (previously fitted) models added predictor stack thus predictors subsequent models (Default). \"offset\" predicted output first (previously fitted) models added spatial offsets subsequent models. Offsets back-transformed depending model family. option might supported every Engine. \"interaction\" Instead fitting several separate models, observations dataset combined incorporated prediction factor interaction \"weaker\" data source partialed prediction. first dataset added determines reference level (see Leung et al. 2019 description). \"prior\" option make use coefficients previous model define priors used next model. Might work engine! \"weight\" option works multiple biodiversity datasets type (e.g. \"poipo\"). Individual weight multipliers can determined setting model (Note: Default 1). Datasets combined estimation weighted respectively, thus giving example presence-records less weight survey records. Note parameter ignored engines support joint likelihood estimation. aggregate_observations logical whether observations covering grid cell aggregated (Default: TRUE). clamp logical whether predictions clamped range predictor values observed model fitting (Default: FALSE). verbose Setting logical value TRUE prints information model fitting (Default: FALSE). ... arguments passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Train the model from a given engine — train","text":"DistributionModel object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Train the model from a given engine — train","text":"function acts generic training function - based provided BiodiversityDistribution object creates new distribution model. resulting object contains \"fit_best\" object estimated model , inference_only FALSE SpatRaster object named \"prediction\" contains spatial prediction model. objects can requested via object$get_data(\"fit_best\"). parameters function: \"filter_predictors\" parameter can set various options remove highly correlated variables little additional information gain model prior estimation. Available options \"none\" (Default) \"pearson\" applying 0.7 correlation cutoff, \"abess\" regularization framework Zhu et al. (2020), \"RF\" \"randomforest\" removing least important variables according randomForest model. Note: function applied predictors prior provided (e.g. potentially non-informative ones). \"optim_hyperparam\" option allows make use hyper-parameter search several models, can improve prediction accuracy although substantial increase computational cost. \"method_integration\" relevant one BiodiversityDataset supplied engine support joint integration likelihoods. See also Miller et al. (2019) references details different types integration. course, users want control aspect, another option fit separate models make use add_offset, add_offset_range ensemble functionalities. \"clamp\" Boolean parameter support clamping projection predictors range values observed model training.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Train the model from a given engine — train","text":"silver bullets (correlative) species distribution modelling model analyst understand objective, workflow parameters can used modify outcomes. Different predictions can obtained data parameters necessarily make sense useful.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Train the model from a given engine — train","text":"Miller, D..W., Pacifici, K., Sanderlin, J.S., Reich, B.J., 2019. recent past promising future data integration methods estimate species’ distributions. Methods Ecol. Evol. 10, 22–37. https://doi.org/10.1111/2041-210X.13110 Zhu, J., Wen, C., Zhu, J., Zhang, H., & Wang, X. (2020). polynomial algorithm best-subset selection problem. Proceedings National Academy Sciences, 117(52), 33117-33123. Leung, B., Hudgins, E. J., Potapova, . & Ruiz‐Jaen, M. C. new baseline countrywide α‐diversity species distributions: illustration using >6,000 plant species Panama. Ecol. Appl. 29, 1–13 (2019).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Train the model from a given engine — train","text":"","code":"# Load example data  background <- terra::rast(system.file('extdata/europegrid_50km.tif',  package='ibis.iSDM',mustWork = TRUE))  # Get test species  virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg',  package='ibis.iSDM',mustWork = TRUE),'points',quiet = TRUE)   # Get list of test predictors  ll <- list.files(system.file('extdata/predictors/', package = 'ibis.iSDM',  mustWork = TRUE),full.names = TRUE)  # Load them as rasters  predictors <- terra::rast(ll);names(predictors) <- tools::file_path_sans_ext(basename(ll))   # Use a basic GLM to fit a SDM  x <- distribution(background) |>         # Presence-only data         add_biodiversity_poipo(virtual_points, field_occurrence = \"Observed\") |>         # Add predictors and scale them         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>         # Use GLM as engine         engine_glm() #> [Setup] 2024-01-25 22:00:11.717918 | Provide a background with a valid projection! #> [Setup] 2024-01-25 22:00:11.72865 | Creating distribution object... #> [Setup] 2024-01-25 22:00:11.72943 | Adding poipo dataset... #> [Setup] 2024-01-25 22:00:11.801099 | Adding predictors... #> [Setup] 2024-01-25 22:00:11.879135 | Transforming predictors...   # Train the model, Also filter out co-linear predictors using a pearson threshold  mod <- train(x, only_linear = TRUE, filter_predictors = 'pearson') #> [Estimation] 2024-01-25 22:00:11.99227 | Collecting input parameters. #> [Estimation] 2024-01-25 22:00:12.05278 | Filtering predictors via pearson... #> [Estimation] 2024-01-25 22:00:12.059666 | Adding engine-specific parameters. #> [Estimation] 2024-01-25 22:00:12.060823 | Engine setup. #> [Estimation] 2024-01-25 22:00:12.251369 | Starting fitting: Species:  #> [Estimation] 2024-01-25 22:00:12.293568 | Starting prediction... #> [Done] 2024-01-25 22:00:12.417486 | Completed after 0.42 secs  mod #> Trained GLM-Model (Unnamed run) #>   Strongest summary effects: #>      Positive: CLC3_112_mean_50km, CLC3_132_mean_50km, CLC3_211_mean_50km, ... (7) #>      Negative: aspect_mean_50km, bio03_mean_50km, slope_mean_50km (3) #>   Prediction fitted: yes"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":null,"dir":"Reference","previous_headings":"","what":"Validation of a fitted distribution object — validate","title":"Validation of a fitted distribution object — validate","text":"function conducts model evaluation based either fitted point data supplied independent. Currently supporting point datasets. validation integrated models work needed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Validation of a fitted distribution object — validate","text":"","code":"validate(   mod,   method = \"continuous\",   layer = \"mean\",   point = NULL,   point_column = \"observed\",   ... )  # S4 method for ANY validate(   mod,   method = \"continuous\",   layer = \"mean\",   point = NULL,   point_column = \"observed\",   ... )  # S4 method for SpatRaster validate(   mod,   method = \"continuous\",   layer = NULL,   point = NULL,   point_column = \"observed\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Validation of a fitted distribution object — validate","text":"mod fitted BiodiversityDistribution object set predictors. Alternatively one can also provide directly SpatRaster, however case point layer also needs provided. method validation conducted continious prediction (previously calculated) thresholded layer binary format? Note depending method different metrics can computed. See Details. layer case multiple layers exist, one use? (Default: 'mean'). point sf object type POINT MULTIPOINT. point_column character vector name column containing independent observations. (Default: 'observed'). ... parameters passed . Currently unused.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Validation of a fitted distribution object — validate","text":"Return tidy tibble validation results.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Validation of a fitted distribution object — validate","text":"'validate' function calculates different validation metrics depending output type. output metrics type defined follows: Continuous: 'n' = Number observations. 'rmse' = Root Mean Square Error, $$ \\sqrt {\\frac{1}{N} \\sum_{=1}^{N} (\\hat{y_{}} - y_{})^2} $$ 'mae' = Mean Absolute Error, $$ \\frac{ \\sum_{=1}^{N} y_{} - x_{} }{n} $$ 'logloss' = Log loss, TBD 'normgini' = Normalized Gini index, TBD 'cont.boyce' = Continuous Boyce index, TBD Discrete: 'n' = Number observations. 'auc' = Area curve, TBD 'overall.accuracy' = Overall Accuracy, TBD 'true.presence.ratio' = True presence ratio Jaccard index, TBD 'precision' = Precision, TBD 'sensitivity' = Sensitivity, TBD 'specificity' = Specifivity, TBD 'tss' = True Skill Statistics, TBD 'f1' = F1 Score Positive predictive value, $$ \\frac{2TP}{2TP + FP + FN} $$ 'logloss' = Log loss, TBD 'expected.accuracy' = Expected Accuracy, $$ \\frac{TP + FP}{N} x \\frac{TP + FN}{N} + \\frac{TN + FN}{N} x \\frac{TN + FP}{N} $$ 'kappa' = Kappa value, $$ \\frac{2 (TP x TN - FN x FP)}{(TP + FP) x (FP + TN) + (TP + FN) x (FN + TN) } $$, 'brier.score' = Brier score, $$ \\frac{ \\sum_{=1}^{N} (y_{} - x_{})^{2} }{n} $$, $y_i$ predicted presence absence $x_i$ observed. TP true positive, TN true negative, FP false positive FN false negative.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Validation of a fitted distribution object — validate","text":"use Boyce Index, please cite original Hirzel et al. (2006) paper.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Validation of a fitted distribution object — validate","text":"Liu, C., White, M., Newell, G., 2013. Selecting thresholds prediction species occurrence presence-data. J. Biogeogr. 40, 778–789. https://doi.org/10.1111/jbi.12058 Hirzel, . H., Le Lay, G., Helfer, V., Randin, C., & Guisan, . (2006). Evaluating ability habitat suitability models predict species presences. Ecological modelling, 199(2), 142-152.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Validation of a fitted distribution object — validate","text":"","code":"if (FALSE) {  # Assuming that mod is a distribution object and has a thresholded layer  mod <- threshold(mod, method = \"TSS\")  validate(mod, method = \"discrete\")  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":null,"dir":"Reference","previous_headings":"","what":"Wrap a list with stan model code — wrap_stanmodel","title":"Wrap a list with stan model code — wrap_stanmodel","text":"engine_stan builds list stan model code. function concatenates together.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Wrap a list with stan model code — wrap_stanmodel","text":"","code":"wrap_stanmodel(sm_code)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Wrap a list with stan model code — wrap_stanmodel","text":"sm_code list object exactly 7 entries.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Wrap a list with stan model code — wrap_stanmodel","text":"character object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":null,"dir":"Reference","previous_headings":"","what":"Save a model for later use — write_model","title":"Save a model for later use — write_model","text":"write_model function (opposed write_output) generic wrapper writing DistributionModel disk. essentially wrapper saveRDS. Models can loaded via load_model function.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Save a model for later use — write_model","text":"","code":"write_model(   mod,   fname,   slim = FALSE,   verbose = getOption(\"ibis.setupmessages\") )  # S4 method for ANY write_model(   mod,   fname,   slim = FALSE,   verbose = getOption(\"ibis.setupmessages\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Save a model for later use — write_model","text":"mod Provided DistributionModel object. fname character depicting output filename. slim logical option whether unnecessary entries model object deleted. deletes example predictions non-model content object (Default: FALSE). verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Save a model for later use — write_model","text":"R-output created. file written target direction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Save a model for later use — write_model","text":"default output files overwritten already existing!","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Save a model for later use — write_model","text":"","code":"if (FALSE) { x <- distribution(background) |>  add_biodiversity_poipo(virtual_points, field_occurrence = 'observed', name = 'Virtual points') |>  add_predictors(pred_current, transform = 'scale',derivates = 'none') |>  engine_xgboost(nrounds = 2000) |> train(varsel = FALSE, only_linear = TRUE) write_model(x, \"testmodel.rds\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":null,"dir":"Reference","previous_headings":"","what":"Generic function to write spatial outputs — write_output","title":"Generic function to write spatial outputs — write_output","text":"write_output function generic wrapper writing output files (e.g. projections) created ibis.iSDM-package. possible write outputs fitted DistributionModel, BiodiversityScenario individual terra stars objects. case data.frame supplied, output written csv file. creating summaries distribution scenario parameters performance, see write_summary()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Generic function to write spatial outputs — write_output","text":"","code":"write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for ANY,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for BiodiversityScenario,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for SpatRaster,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for data.frame,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for stars,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Generic function to write spatial outputs — write_output","text":"mod Provided DistributionModel, BiodiversityScenario, terra stars object. fname character depicting output filename. dt character output datatype. Following terra::writeRaster options (Default: 'FLT4S'). verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE). ... arguments passed individual functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Generic function to write spatial outputs — write_output","text":"R-output created. file written target direction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Generic function to write spatial outputs — write_output","text":"default output files overwritten already existing!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Generic function to write spatial outputs — write_output","text":"","code":"if (FALSE) { x <- distribution(background)  |>  add_biodiversity_poipo(virtual_points, field_occurrence = 'observed', name = 'Virtual points') |>  add_predictors(pred_current, transform = 'scale',derivates = 'none') |>  engine_xgboost(nrounds = 2000) |> train(varsel = FALSE, only_linear = TRUE) write_output(x, \"testmodel.tif\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":null,"dir":"Reference","previous_headings":"","what":"Generic function to write summary outputs from created models. — write_summary","title":"Generic function to write summary outputs from created models. — write_summary","text":"write_summary function wrapper function create summaries fitted DistributionModel BiodiversityScenario objects. function extract parameters statistics used data input object writes output either 'rds' 'rdata' file. Alternative, open file formats consideration.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Generic function to write summary outputs from created models. — write_summary","text":"","code":"write_summary(   mod,   fname,   partial = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for ANY,character write_summary(   mod,   fname,   partial = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Generic function to write summary outputs from created models. — write_summary","text":"mod Provided DistributionModel BiodiversityScenario object. fname character depicting output filename. suffix determines file type output (Options: 'rds', 'rdata'). partial logical value determining whether partial variable contributions calculated added model summary. Note can rather slow (Default: FALSE). verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE). ... arguments passed individual functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Generic function to write summary outputs from created models. — write_summary","text":"R-output created. file written target direction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Generic function to write summary outputs from created models. — write_summary","text":"predictions tabular data saved function. Use write_output() save .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Generic function to write summary outputs from created models. — write_summary","text":"","code":"if (FALSE) { x <- distribution(background) |>  add_biodiversity_poipo(virtual_points, field_occurrence = 'observed', name = 'Virtual points')  |>  add_predictors(pred_current, transform = 'scale',derivates = 'none') |>  engine_xgboost(nrounds = 2000) |> train(varsel = FALSE, only_linear = TRUE) write_summary(x, \"testmodel.rds\") }"},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-1-2","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.1.2 (current dev branch)","text":"Switched object structure R6 throughout improved data memory handling #44 Implemented convenience function ro remove biodiversity datasets (rm_biodiversity()).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-1-2","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.1.2 (current dev branch)","text":"Added logical parameter ensemble() enabling compositing thresholds set #84 Support multi-band rasters ensemble() convenience. Fix bug threshold() supplied point data improved error messages. Cleaner docs structure","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-1-1","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.1.1","text":"Added default engine_glm() dependency-free inference projection. Harmonized controls settings added option contrain extrapolation add_control_extrapolation() Adding function temporal interpolation predictors #52","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-1-1","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.1.1","text":"Minor corrective fixes additions add_offset(). Switch engine_glm() many unittests better coverage. Several bug fixes improvements thin_observations() global, probs, centers argument better control thin_observations() Harmonization parameters spartial() addressing #80","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-1-0","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.1.0","text":"Added small convenience wrapper add model outputs another model add_predictors_model() Started adding mechanistic SDM vignette #67 Wrapper steps implemented via simulate_population_steps() #68","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-1-0","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.1.0","text":"Added R-universe installation option alternative github #38 Minor bug fixes scenario() object, MigClim Kissmig wrappers. Bug fix related CRS classes sp sf Bug fix related blas.num.threads Bug fix crashed write_summary() outputs prediction made. Bug fix related CRS engine_inla() Bug fix engine_stan() related background layer Class biodiversity data identical PO PA Bug fix built_formula_glmnet() response Bug fix built_formula_gdb() response model$biodiversity stores predictors current ID Bug fix built_formula_inla() INLABRU","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-9","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.9","text":"Added new vignette available functions data preparation #67 Addition small mask() function emulates terra.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-9","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.9","text":"Small fix ensemble() ensembles future scenarios use correct standardization. Small fix threshold() now returning threshold values correctly. Bug fix error catching distribution() ensemble_partial(),ensemble_spartial() checks added check() #45 Small fix alignRasters(). Small fix harmonize field_column throughout. Improved error messages handling formula’s.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-8","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.8","text":"Implemented min size constraint (add_constraint_minsize()) #56 Added function estimating partial effects ensembles ensemble_spartial().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-8","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.8","text":"Added warnings checks missing crs supplied layers #65 Smaller bug code harmonizations ensemble_partial(), partial() spartial(). Smaller bug fixes threshold() scenario() projections. Improved error messages several functions. documentation fixes towards CRAN submission #38 Allow specify location biodiversity point records threshold().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-7","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.7","text":"Added method proximity add_control_bias() place lower weights points closer another. Added helper functions get_data() option apply threshold() directly BiodiversityScenarios. Added centroid function BiodiversityScenarios DistributionModels #29","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-7","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.7","text":"Add Error message background data different units easier understand. Added warning message threshold creation use independent data possible. Fixed min.cv bug threshold() introduced #17 Fixed add_offset() function now also allowing sf objects input. Fixed bug writing outputs write_output() Fixed bug prediction limits work correctly (distribution(...,lim = x))","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-6","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.6","text":"partial_density() function implemented #57 Re-specification limits implementation minimum convex polygon limits distribution(). Added check() function assessing assumptions fits various objects #45 Added minor internal helper functions duplicate stars objects via st_rep. Implemented local limiting factor function (limiting()) #37","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-6","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.6","text":"smaller documentation fixes towards CRAN submission #38 Bug fix method buffer pseudo-absence settings. Minor bug fixes ensemble() uncertainty calculations.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-5","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.5","text":"Addition 5 parameter logistic curve offsets parameter search add_offset().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-5","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.5","text":"smaller documentation fixes towards CRAN submission #38 Bug write_model(), now converting terra objects data.frame import/export. Smaller bug fixes, example similarity(), addition variable name sanitization predictors default.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-4","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.4","text":"Smaller bug fixes regards writing outputs adding pseudo-absences. Added short convenience function convert prediction outputs #48 Converted raster terra #17 Updated added unit checks tests","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-3","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.3","text":"Aded Boruta iterative feature selection predictor variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-3","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.3","text":"Removed Magittr dependency #41 Smaller improvements documentation removing CRAN preventing function calls. Made separation hyperparameter search functions clearer added new option filter highly correlated covariates via train().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-2","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.2","text":"Smaller documentation fixes, including make sure examples returns exported function documentations. Preparation cran release #38, including fixing common issues checks. smaller bug fixes validate() make Boyce robust. Change logo. Thanks @elliwoto Added warning validate call users aware non-independent validation. fixes github actions tests @mhesselbarth","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"ibisisdm-001","dir":"Changelog","previous_headings":"","what":"ibis.iSDM 0.0.1","title":"ibis.iSDM 0.0.1","text":"Initial public release version! Finding fixing bugs…","code":""}]
+[{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"preparing-and-altering-biodiversity-data","dir":"Articles","previous_headings":"","what":"Preparing and altering biodiversity data","title":"Preparation of biodiversity and predictor data","text":"SDM approaches require observation biodiversity data, typically form presence-presence-absence data, can available range different formats points polygons. range existing tools assist modellers preparing cleaning input data (instance biases). vignette intend give overview options. Rather highlights functions created specifically ibis.iSDM package might help situations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"adding-pseudo-absence-points-to-presence-only-data","dir":"Articles","previous_headings":"Preparing and altering biodiversity data","what":"Adding pseudo-absence points to presence-only data","title":"Preparation of biodiversity and predictor data","text":"Although philosophy ibis.iSDM package advisable use presence-models Poisson point process modelling framework (‘poipo’ modelling functions use background points (see Warton Sheperd 2010). Yet, good case can also made instead add pseudo-absence points existing presence-data. allows use logistic regressions ‘poipa’ methods ibis.iSDM generally easier interpret (response scale 0 1) also faster fit model. Adding pseudo-absence data ibis.iSDM package works first specifiying Pseudoabsence options object contains parameters many pseudo-absences sampled. respective function called pseudoabs_settings(). details available options (many) can found help file. default packages uses random sampling absence points settings can queried ibis_options()$ibis.pseudoabsence. options defined, pseudoa-absence data can added point dataset via add_pseudoabsence(). Example:","code":"## Lets load some testing data from the package  # Background layer background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\", mustWork = TRUE)) # Load virtual species points virtual_species <- sf::st_read(system.file(\"extdata/input_data.gpkg\",package = \"ibis.iSDM\", mustWork = TRUE), \"points\",quiet = TRUE)  # Add a range  virtual_range <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'range', quiet = TRUE) # Define new settings for sampling points outside the minimum convex polygon of # the known presence data abs <- pseudoabs_settings(background = background,                           nrpoints = 1000, # Sample 1000 points                           method = \"mcp\", # Option for minimum convex polygon                           inside =  FALSE # Sample exclusively outside                             ) print( abs ) # See object, check abs$data for the options  # Now add to the point data point1 <- add_pseudoabsence(virtual_species,                             # Point to the column with the presence information                             field_occurrence = 'Observed',                             settings = abs)  plot(point1['Observed']) # --- # # Another option sampling inside the range, but biased by a bias layer bias <- terra::rast(system.file(\"extdata/predictors/hmi_mean_50km.tif\",                                 package = \"ibis.iSDM\", mustWork = TRUE))  abs <- pseudoabs_settings(background = background,                           nrpoints = 100, # Sample 100 points                           method = \"range\", # Define range as method                           inside =  TRUE, # Sample exclusively inside                           layer = virtual_range, # Define the range                           bias = bias # Set a bias layer                             )  # Add again to the point data point2 <- add_pseudoabsence(virtual_species,                             # Point to the column with the presence information                             field_occurrence = 'Observed',                             settings = abs)  plot(point2['Observed'])"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"thinning-observations","dir":"Articles","previous_headings":"Preparing and altering biodiversity data","what":"Thinning observations","title":"Preparation of biodiversity and predictor data","text":"Many presence-records often spatially highly biased varying observational processes resulting quite clustered point observations. example, urban areas natural sites near considerably often frequented citizens observed wildlife sites remote areas. Particular Poisson process models can problematic models critically assume - without accounting - observational process homogeneous space. Thinning observations method remove point observations areas “oversampled”. Critically however remove points grid cells provided background case never removes entire grid cell fully. can also beneficial model convergence modelling speed, particular well-sampled species (e.g. common blackbird Turdus merula) diminishing returns fitting SDM like 1 million presence-points instead just 20000 well separated ones. ibis.iSDM package implementation spatial thinning, one can also refer Aiello-Lammens et al. alternative implementation rationale thinning. Thinning needs conducted care effectively discards data!","code":"## We use the data loaded in above plot(virtual_species['Observed'], main = \"Original data\") # Random thinning. Note the messages of number of thinned points point1 <- thin_observations(data = virtual_species,                   background = background,                   method = 'random',                   remainpoints = 1 # Retain at minimum one point per grid cell!                   ) #> (random) thinning completed!  #> Original number of records: 208 #> Number of retained records: 175  plot(point1['Observed'], main = \"Random thinning\") # Another way: Use environmental thinning to retain enough points # across the niche defined by a set of covariates covariates <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE))  point2 <- thin_observations(data = virtual_species,                   background = background,                   env = covariates,                   method = 'environmental',                   remainpoints = 5 # Retain at minimum five points!                   ) #> (environmental) thinning completed!  #> Original number of records: 208 #> Number of retained records: 28  plot(point2['Observed'], main = \"Environmentally stratified data\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"preparing-and-altering-predictor-data","dir":"Articles","previous_headings":"","what":"Preparing and altering predictor data","title":"Preparation of biodiversity and predictor data","text":"order used species distribution modelling predictors need provided common extent, grain size geographic projections. need align provided background extent distribution() ideally contain missing data. missing data, package check remove model fitting points fall grid cells missing data. ibis.iSDM package number convenience functions modify input predictors. functions rather provide nuance(s) variation modelling process, rather preparing input data (needs undertaken using terra package).","code":"# Load some test covariates predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE))"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"transforming-predictors","dir":"Articles","previous_headings":"Preparing and altering predictor data","what":"Transforming predictors","title":"Preparation of biodiversity and predictor data","text":"better model convergence usually makes sense bring predictors common unit, example noramlizing scaling . ibis.iSDM package convenience function can applied terra ‘SpatRaster’ object. NOTE: functionality also available directly add_predictors() parameter!   options transformation also available listed methods file.","code":"# Let's take a simple layer for an example layer <- predictors$bio19_mean_50km  # Transform it in various way new1 <- predictor_transform(layer, option = \"norm\") new2 <- predictor_transform(layer, option = \"scale\")  new <- c(layer, new1, new2) names(new) <- c(\"original\", \"normalized\", \"scaled\") terra::plot( new ) # Another common use case is to windsorize a layer, for example by removing # top outliers form a prediction. # Here the values are capped to a defined percentile new3 <- predictor_transform(layer, option = \"windsor\",                             # Clamp the upper values to the 90% percentile                             windsor_props = c(0,.9))  new <- c(layer, new3) names(new) <- c(\"original\", \"windsorized\") terra::plot( new )"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"derivates-of-predictors","dir":"Articles","previous_headings":"Preparing and altering predictor data","what":"Derivates of predictors","title":"Preparation of biodiversity and predictor data","text":"simple linear SDM (e.g. engine_glmnet()) includes predictors thus assumes increase response variable follows linear relationship covariate. However, reality always simple usually can assumed many relationships highly non-linear otherwise complex. standard way introduce non-linearities linear algorithm create derivates predictors, example quadratic transformation temperature. ibis.iSDM package convenience function can applied terra ‘SpatRaster’ object create additional derivates model. Note creates (cases substantial) additional predictors. NOTE: functionality also available directly add_predictors() parameter!       fine-tuned control can also achieved creating specific interactions among variables, example one expects climate interact forest cover.","code":"# Let's take a simple layer for an example layer <- predictors$ndvi_mean_50km  # Make a quadratic transformation new1 <- predictor_derivate(layer, option = \"quadratic\")  new <- c(layer, new1) names(new) <- c(\"original\", \"quadratic\") terra::plot( new ) # Create some hinge transformations new2 <- predictor_derivate(layer, option = \"hinge\",                            # The number is controlled by the number of knots                             nknots = 4                             ) terra::plot( new2 ) # What does this do precisely? # Lets check df <- data.frame( ndvi = terra::values(layer),                   terra::values(new2))  plot(df$ndvi_mean_50km, df[,2], ylab = \"First hinge of ndvi\", xlab = \"NDVI\") plot(df$ndvi_mean_50km, df[,3], ylab = \"Second hinge of ndvi\",xlab = \"NDVI\") plot(df$ndvi_mean_50km, df[,4], ylab = \"Third hinge of ndvi\", xlab = \"NDVI\") plot(df$ndvi_mean_50km, df[,5], ylab = \"Fourth hinge of ndvi\",xlab = \"NDVI\") # Create interacting variables  new <- predictor_derivate(predictors,option = \"interaction\",                           int_variables = c(\"bio01_mean_50km\", \"CLC3_312_mean_50km\"))  plot(new, main = \"Interaction variable\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"homogenize-missing-data-among-predictors","dir":"Articles","previous_headings":"Preparing and altering predictor data","what":"Homogenize missing data among predictors","title":"Preparation of biodiversity and predictor data","text":"mentioned , model training covariates extracted biodiversity observational record. Missing data case discarded. example 10 predictors considered single one missing value one grid cell, grid cell considered missing among predictors well. ibis.iSDM package convenience functions easily harmonize check extent missing data set predictors can convenient assessing errors data preparation.","code":"# Make a subset of all predictors to show the concept layers <- subset(predictors,  c(\"aspect_mean_50km\",                                         \"CLC3_312_mean_50km\",                                         \"elevation_mean_50km\"))  # All these layers have identical data coverage. # Now add missing data in one of the layers for testing layers$CLC3_312_mean_50km[sample(1:ncell(layers), 1000)] <- NA   # Harmonize the predictors new <- predictor_homogenize_na(env = layers)  # Now all the predictors have identical coverage of NA values terra::plot(new) # Or assess like this plot(!terra::noNA(new$aspect_mean_50km), main = \"Missing observations\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/01_data_preparationhelpers.html","id":"preparing-and-altering-future-scenario-data","dir":"Articles","previous_headings":"","what":"Preparing and altering future scenario data","title":"Preparation of biodiversity and predictor data","text":"Creating scenarios R requires input predictors formatted different format . ibis.iSDM package makes extensive use stars prepare load multi-dimensional data. One common issue predictors requested time dimension. example climate data might available decadal scale (e.g. 2020, 2030, 2040), yet predictions often required finer temporal grain. purpose ibis.iSDM contains dedicated function (interpolate_gaps()), can also directly called within project().","code":"# Load some stars rasters ll <- list.files(system.file('extdata/predictors_presfuture/',                              package = 'ibis.iSDM',                              mustWork = TRUE),full.names = TRUE)  # Load the same files future ones suppressWarnings(   pred_future <- stars::read_stars(ll) |> dplyr::slice('Time', seq(1, 86, by = 10)) ) sf::st_crs(pred_future) <- sf::st_crs(4326)  # The predictors are here only available every 10 years stars::st_get_dimension_values(pred_future, 3) #> Units: [(days since 1970-1-1)] #> [1] 16436 20089 23741 27394 31046 34699 38351 42004 45656  # --- # # The ibis.iSDM contains here a function to make interpolation among timesteps, # thus filling gaps in between.  # As an example, # Here we make a temporal interpolation to create an annual time series new <- interpolate_gaps(pred_future, date_interpolation = \"annual\")  stars::st_get_dimension_values(new, 3) #>  [1] \"2015-07-02\" \"2025-07-02\" \"2035-07-02\" \"2045-07-02\" \"2055-07-02\" #>  [6] \"2065-07-02\" \"2075-07-02\" \"2085-07-02\" \"2095-07-02\" \"2016-07-02\" #> [11] \"2017-07-02\" \"2018-07-02\" \"2019-07-02\" \"2020-07-02\" \"2021-07-02\" #> [16] \"2022-07-02\" \"2023-07-02\" \"2024-07-02\" \"2026-07-02\" \"2027-07-02\" #> [21] \"2028-07-02\" \"2029-07-02\" \"2030-07-02\" \"2031-07-02\" \"2032-07-02\" #> [26] \"2033-07-02\" \"2034-07-02\" \"2036-07-02\" \"2037-07-02\" \"2038-07-02\" #> [31] \"2039-07-02\" \"2040-07-02\" \"2041-07-02\" \"2042-07-02\" \"2043-07-02\" #> [36] \"2044-07-02\" \"2046-07-02\" \"2047-07-02\" \"2048-07-02\" \"2049-07-02\" #> [41] \"2050-07-02\" \"2051-07-02\" \"2052-07-02\" \"2053-07-02\" \"2054-07-02\" #> [46] \"2056-07-02\" \"2057-07-02\" \"2058-07-02\" \"2059-07-02\" \"2060-07-02\" #> [51] \"2061-07-02\" \"2062-07-02\" \"2063-07-02\" \"2064-07-02\" \"2066-07-02\" #> [56] \"2067-07-02\" \"2068-07-02\" \"2069-07-02\" \"2070-07-02\" \"2071-07-02\" #> [61] \"2072-07-02\" \"2073-07-02\" \"2074-07-02\" \"2076-07-02\" \"2077-07-02\" #> [66] \"2078-07-02\" \"2079-07-02\" \"2080-07-02\" \"2081-07-02\" \"2082-07-02\" #> [71] \"2083-07-02\" \"2084-07-02\" \"2086-07-02\" \"2087-07-02\" \"2088-07-02\" #> [76] \"2089-07-02\" \"2090-07-02\" \"2091-07-02\" \"2092-07-02\" \"2093-07-02\" #> [81] \"2094-07-02\""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"load-package-and-make-a-basic-model","dir":"Articles","previous_headings":"","what":"Load package and make a basic model","title":"Train a basic model","text":"Creating model ibis.iSDM package relatively straight forward demonstrate testdata come package. data show distribution simulated forest-associated species northern Europe. also test predictors available modelling. first lets load data: example model going use ‘Integrated Nested Laplace approximation (INLA)’ modelling framework available INLA inlabru packages. implemented separately ibis.iSDM package, especially dealing future scenarios use inlabru package advised. Now lets build simple model object. case make use presence-biodiversity records (add_biodiversity_poipo). presence-records added object created distribution() default modelled intensity \\(\\lambda\\) inhomogeneous Poisson point process model (PPM), Number Individuals \\(N\\) integrated relative rate occurrence per unit area: \\(N_i \\sim Poisson(\\lambda_i|A_i)\\). \\(\\lambda\\) can estimated relating environmental covariates \\(log(\\lambda_i) = \\alpha + \\beta(x_i)\\), \\(\\) grid cell. inhomogeneous since \\(lambda\\) varies whole sampling extent. context species distribution modelling PPMs structurally similar popular Maxent modelling framework (see Renner & Warton 2013 Renner et al. 2015. Critically, presence-records can give indication biased sampling thus sampling bias taken somehow account, either careful data preparation, apriori thinning model-based control including covariates \\(\\sigma_i\\) might explain sampling bias. print call end now shows summary statistics contained object, extent modelling background projection used, number biodiversity datasets added statistics predictors, eventual priors engine used. course steps can also done “pipe” using |> syntax. Also helpful know object contains number helper functions allow easy summary visualization contained data. example, possible plot obtain data added object.  Now finally model can estimated using supplied engine. train function many available parameters affect model fitted. Unless possible, default way fitting linear model based provided engine biodiversity data types.","code":"# Load the package library(ibis.iSDM) library(inlabru) library(xgboost) library(terra) library(uuid) library(assertthat)  # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE) # Background layer background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\", mustWork = TRUE)) # Load virtual species points virtual_species <- sf::st_read(system.file(\"extdata/input_data.gpkg\",package = \"ibis.iSDM\", mustWork = TRUE), \"points\")  #> Reading layer `points' from data source  #>   `/home/runner/work/_temp/Library/ibis.iSDM/extdata/input_data.gpkg'  #>   using driver `GPKG' #> Simple feature collection with 208 features and 5 fields #> Geometry type: POINT #> Dimension:     XY #> Bounding box:  xmin: 4.109162 ymin: 48.7885 xmax: 24.47594 ymax: 64.69323 #> Geodetic CRS:  WGS 84 # Predictors predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE)) # Make use only of a few of them predictors <- subset(predictors, c(\"bio01_mean_50km\",\"bio03_mean_50km\",\"bio19_mean_50km\",                                             \"CLC3_112_mean_50km\",\"CLC3_132_mean_50km\",                                             \"CLC3_211_mean_50km\",\"CLC3_312_mean_50km\",                                             \"elevation_mean_50km\")) # First we define a distribution object using the background layer mod <- distribution(background)  # Then lets add species data to it.  # This data needs to be in sf format and key information is that # the model knows where occurrence data is stored (e.g. how many observations per entry) as # indicated by the field_occurrence field. mod <- add_biodiversity_poipo(mod, virtual_species,                                       name = \"Virtual test species\",                                       field_occurrence = \"Observed\")  # Then lets add predictor information # Here we are interested in basic transformations (scaling), but derivates (like quadratic) # for now, but check options mod <- add_predictors(mod,                        env = predictors,                       transform = \"scale\", derivates = \"none\")  # Finally define the engine for the model # This uses the default data currently backed in the model, # !Note that any other data might require an adaptation of the default mesh parameters used by the engine! mod <- engine_inlabru(mod)  # Print out the object to see the information that is now stored within print(mod) #>  #> Background extent:  #>      xmin: -16.064, xmax: 36.322, #>      ymin: 34.95, ymax: 71.535 #>    projection: +proj=longlat +datum=WGS84 +no_defs #>  ---------  #> Biodiversity data: #>    Point - Presence only <208 records> #>  ---------  #>   predictors:     bio01_mean_50km, bio03_mean_50km, bio19_mean_50km, ... (8 predictors) #>   priors:          #>   latent:         None #>   log:             #>   engine:          print(\"Create model\") #> [1] \"Create model\"  mod <- distribution(background) |>         add_biodiversity_poipo(virtual_species,                               name = \"Virtual test species\",                               field_occurrence = \"Observed\") |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_inlabru() # Make visualization of the contained biodiversity data plot(mod$biodiversity) # Other options to explore names(mod) #>  [1] \"summary\"                     \"show_biodiversity_length\"    #>  [3] \"show_biodiversity_equations\" \"show_background_info\"        #>  [5] \"show\"                        \"set_priors\"                  #>  [7] \"set_predictors\"              \"set_offset\"                  #>  [9] \"set_log\"                     \"set_limits\"                  #> [11] \"set_latent\"                  \"set_engine\"                  #> [13] \"set_control\"                 \"set_biodiversity\"            #> [15] \"rm_priors\"                   \"rm_predictors\"               #> [17] \"rm_offset\"                   \"rm_limits\"                   #> [19] \"rm_latent\"                   \"rm_engine\"                   #> [21] \"rm_control\"                  \"priors\"                      #> [23] \"print\"                       \"predictors\"                  #> [25] \"plot_offsets\"                \"plot_bias\"                   #> [27] \"plot\"                        \"offset\"                      #> [29] \"name\"                        \"log\"                         #> [31] \"limits\"                      \"latentfactors\"               #> [33] \"initialize\"                  \"get_resolution\"              #> [35] \"get_projection\"              \"get_priors\"                  #> [37] \"get_prior_variables\"         \"get_predictor_names\"         #> [39] \"get_offset_type\"             \"get_offset\"                  #> [41] \"get_log\"                     \"get_limits\"                  #> [43] \"get_latent\"                  \"get_extent_dimensions\"       #> [45] \"get_extent\"                  \"get_engine\"                  #> [47] \"get_control\"                 \"get_biodiversity_types\"      #> [49] \"get_biodiversity_names\"      \"get_biodiversity_ids\"        #> [51] \"get_biodiversity_equations\"  \"engine\"                      #> [53] \"control\"                     \"clone\"                       #> [55] \"biodiversity\"                \"background\"                  #> [57] \".__enclos_env__\" print(\"Fit model\") #> [1] \"Fit model\"  # Finally train fit <- train(mod,              runname =  \"Test INLA run\",              verbose = FALSE # Don't be chatty              )"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"summarizing-and-plotting-the-fitted-distribution-object","dir":"Articles","previous_headings":"","what":"Summarizing and plotting the fitted distribution object","title":"Train a basic model","text":"created distribution model object can visualized interacted . print() outputs model, inherent parameters whether predictions contained within. summary() creates summary output contained model. plot() makes visualization prediction background effects() visualizes effects, usually default plot package used fit model.   See reference help pages options including calculating threshold(), partial() similarity() estimate used data.   common practice species distribution modelling resulting predictions thresholded, e.g. abstraction continious prediction created separates background areas environment supporting species presumably suitable non-suitable. Threshold can used ibis.iSDM via threshold() functions suppling either fitted model, RasterLayer Scenario object.   options functions please see help pages!","code":"# Plot the mean of the posterior predictions plot(fit, \"mean\") # Print out some summary statistics summary(fit) #> # A tibble: 9 × 8 #>   variable               mean     sd     q05     q50    q95    mode   kld #>                                   #> 1 Intercept           -2.46   0.126  -2.66   -2.46   -2.25  -2.46       0 #> 2 bio01_mean_50km     -0.0149 0.178  -0.307  -0.0149  0.277 -0.0149     0 #> 3 bio03_mean_50km     -0.492  0.162  -0.759  -0.492  -0.225 -0.492      0 #> 4 bio19_mean_50km      0.511  0.120   0.313   0.511   0.709  0.511      0 #> 5 CLC3_112_mean_50km   0.444  0.0702  0.329   0.444   0.560  0.444      0 #> 6 CLC3_132_mean_50km   0.0216 0.0598 -0.0768  0.0216  0.120  0.0216     0 #> 7 CLC3_211_mean_50km   0.946  0.107   0.771   0.946   1.12   0.946      0 #> 8 CLC3_312_mean_50km   1.09   0.0912  0.944   1.09    1.24   1.09       0 #> 9 elevation_mean_50km  0.0567 0.113  -0.130   0.0567  0.243  0.0567     0  # Show the default effect plot from inlabru effects(fit) # To calculate a partial effect for a given variable o <- partial(fit, x.var = \"CLC3_312_mean_50km\", plot = TRUE) # The object o contains the data underlying this figure  # Similarly the partial effect can be visualized spatially as 'spartial' s <- spartial(fit, x.var = \"CLC3_312_mean_50km\") plot(s[[1]], col = rainbow(10), main = \"Marginal effect of forest on the relative reporting rate\") # Calculate a threshold based on a 50% percentile criterion fit <- threshold(fit, method = \"percentile\", value = 0.5)  # Notice that this is now indicated in the fit object print(fit) #> Trained INLABRU-Model (Test INLA run) #>   Strongest summary effects: #>      Positive: CLC3_312_mean_50km, CLC3_211_mean_50km, bio19_mean_50km, ... (6) #>      Negative: bio01_mean_50km, bio03_mean_50km, Intercept (3) #>   Prediction fitted: yes #>   Threshold created: yes  # There is also a convenient plotting function fit$plot_threshold() # It is also possible to use truncated thresholds, which removes non-suitable areas # while retaining those that are suitable. These are then normalized to a range of [0-1] fit <- threshold(fit, method = \"percentile\", value = 0.5, format = \"normalize\") fit$plot_threshold()"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"validation-of-model-predictions","dir":"Articles","previous_headings":"","what":"Validation of model predictions","title":"Train a basic model","text":"ibis.iSDM package provides convenience function obtain validation results fitted models. Validation can done continious discrete predictions, latter requires computed threshold fits (see ). ‘validate’ fitted model using data used model fitting. scientific paper recommend implement cross-validation scheme obtain withheld data use independently gathered data. Validating integrated SDMs, particular fitted multiple likelihoods challenging something yet fully explored scientific literature. example strong priors can substantially improve modifying response functions model, challenging validate validation data similar biases training data. One way SDMs can validated spatial block validation, however care needs taken datasets part block.","code":"# By Default validation statistics are continuous and evaluate the predicted estimates against the number of records per grid cell. fit$rm_threshold() validate(fit, method = \"cont\") #>                                modelid                 name     method #> 1 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous #> 2 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous #> 3 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous #> 4 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous #> 5 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous #> 6 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species continuous #>       metric       value #> 1          n 175.0000000 #> 2       rmse   0.8779555 #> 3        mae   0.6723207 #> 4    logloss   1.7755858 #> 5   normgini  -0.0749004 #> 6 cont.boyce   0.2521260  # If the prediction is first thresholded, we can calculate discrete validation estimates (binary being default) fit <- threshold(fit, method = \"percentile\", value = 0.5, format = \"binary\") validate(fit, method = \"disc\") #>                                 modelid                 name   method #> 1  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 2  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 3  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 4  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 5  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 6  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 7  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 8  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 9  1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 10 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 11 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 12 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #> 13 1fe29d02-2d76-40f9-950b-362492c129bd Virtual test species discrete #>                 metric       value #> 1                    n 513.0000000 #> 2                  auc   0.6878191 #> 3     overall.accuracy   0.7465887 #> 4  true.presence.ratio   0.4036697 #> 5            precision   0.6717557 #> 6          sensitivity   0.5028571 #> 7          specificity   0.8727811 #> 8                  tss   0.3756382 #> 9                   f1   0.5751634 #> 10             logloss   6.1128139 #> 11   expected.accuracy   0.5777314 #> 12               kappa   0.3998812 #> 13         brier.score   0.2534113"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/02_train_simple_model.html","id":"constrain-a-model-in-prediction-space","dir":"Articles","previous_headings":"","what":"Constrain a model in prediction space","title":"Train a basic model","text":"Species distribution models quite often extrapolate areas species unlikely persist thus likely predict false presences false absences. “overprediction” can caused multiple factors true biological constraints (e.g. dispersal), used algorithm trying clever overfitting towards complex relationships (machine learning literature problem commonly known bias vs variance tradeoff). One option counter extent SDMs add spatial constraints spatial latent effects. underlying assumption distances geographic space can extent approximate unknown unquantified factors determine species range. options constrains integrate additional data sources add parameter constraints (see [integrate_data] vignette). Currently ibis.iSDM package supports addition spatial latent effects via add_latent_spatial(). See help file information. Note every spatial term accounts spatial autocorrelation, simply add distance observations predictor (thus assuming much spatial pattern can explained commonalities sampling process).   Another option constraining prediction place concrete limits prediction surface. can done adding factor zone layer distribution object. Internally, assessed ‘zones’ biodiversity observations fall, discarding others prediction. approach can particular suitable current future projections larger scale using instance biome layer stratification. assumes rather unlikely species distributions shift different biomes entirely, instance dispersal eco-evolutionary constraints. Note approach effectively also limits prediction background / output!","code":"# Here we are going to use the xgboost algorithm instead and set as engine below. # We are going to fit two separate Poisson Process Models (PPMs) on presence-only data.  # Load the predictors again predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\"), \"*.tif\",full.names = TRUE)) predictors <- subset(predictors, c(\"bio01_mean_50km\",\"bio03_mean_50km\",\"bio19_mean_50km\",                                             \"CLC3_112_mean_50km\",\"CLC3_132_mean_50km\",                                             \"CLC3_211_mean_50km\",\"CLC3_312_mean_50km\",                                             \"elevation_mean_50km\",                                    \"koeppen_50km\")) # One of them (Köppen) is a factor, we will now convert this to a true factor variable predictors$koeppen_50km <- terra::as.factor(predictors$koeppen_50km)  # Create a distribution modelling pipeline x <- distribution(background) |>    add_biodiversity_poipo(virtual_species, field_occurrence = 'Observed', name = 'Virtual points') |>   add_predictors(predictors, transform = 'scale', derivates = \"none\") |>   engine_xgboost(iter = 8000)  # Now train 2 models, one without and one with a spatial latent effect mod_null <- train(x, runname = 'Normal PPM projection', only_linear = TRUE, verbose = FALSE) # And with an added constrain # Calculated as nearest neighbour distance (NND) between all input points mod_dist <- train(x |> add_latent_spatial(method = \"nnd\"),                   runname = 'PPM with NND constrain', only_linear = TRUE, verbose = FALSE) #>  |---------|---------|---------|---------| =========================================                                             # Compare both plot(background, main = \"Biodiversity data\"); plot(virtual_species['Observed'], add = TRUE) plot(mod_null) plot(mod_dist) # Create again a distribution object, but this time with limits (use the Köppen-geiger layer from above) # The zones layer must be a factor layer (e.g. is.factor(layer) )  # Zone layers can be supplied directly to distribution(background, limits = zones) # or through an extrapolation control as shown below. x <- distribution(background) |>    add_biodiversity_poipo(virtual_species, field_occurrence = 'Observed', name = 'Virtual points') |>   add_predictors(predictors, transform = 'scale', derivates = \"none\") |>   # Since we are adding the koeppen layer as zonal layer, we disgard it from the predictors   rm_predictors(\"koeppen_50km\") |>    add_control_extrapolation(layer = predictors$koeppen_50km, method = \"zones\") |>    engine_xgboost(iter = 3000, learning_rate = 0.01)  # Spatially limited prediction mod_limited <- train(x, runname = 'Limited prediction background', only_linear = TRUE, verbose = FALSE)  # Compare the output plot(mod_limited)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"load-relevant-packages-and-testing-data","dir":"Articles","previous_headings":"","what":"Load relevant packages and testing data","title":"Data integration","text":"Lets load prepared test data exercise. time going make use several datasets. can define generic model use sections .","code":"# Load the package library(ibis.iSDM) library(inlabru) library(glmnet) library(xgboost) library(terra) library(igraph) library(assertthat)  # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE) # Background layer background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\", mustWork = TRUE)) # Load virtual species points virtual_species <- sf::st_read(system.file(\"extdata/input_data.gpkg\",package = \"ibis.iSDM\", mustWork = TRUE), \"points\", quiet = TRUE)  virtual_range <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'range', quiet = TRUE)  # In addition we will use the species data to generate a presence-absence dataset with pseudo-absence points. # Here we first specify the settings to use: ass <- pseudoabs_settings(background = background, nrpoints = 200,                           method =  \"random\") virtual_pseudoabs <- add_pseudoabsence(df = virtual_species, field_occurrence = \"Observed\",                                        settings = ass)  # Predictors predictors <- terra::rast(list.files(system.file(\"extdata/predictors/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.tif\",full.names = TRUE)) # Make use only of a few of them predictors <- subset(predictors, c(\"bio01_mean_50km\",\"bio03_mean_50km\",\"bio19_mean_50km\",                                             \"CLC3_112_mean_50km\",\"CLC3_132_mean_50km\",                                             \"CLC3_211_mean_50km\",\"CLC3_312_mean_50km\",                                             \"elevation_mean_50km\")) # First define a generic model and engine using the available predictors basemodel <- distribution(background) |>        add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_inlabru()"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-through-predictors","dir":"Articles","previous_headings":"","what":"Integration through predictors","title":"Data integration","text":"simple way integrating prior observations species distribution models add covariate. based assumption instance expert-drawn range map can useful predicting species exist might might find suitable habitat (see instance Domisch et al. 2016). benefit approach predictors can easily added kinds engines ibis.ISDM package also used scenarios. Expert-ranges can currently added simple binary distance transform. latter options available bossMaps R-package described Merow et al. 2017. Another option added possibility add thresholded masks based elevational () limits. idea generate two layers, one areas lower upper range one upper range. Regression thresholded layers can thus approximate lower upper bounds. instance suppose species known occur 300 800m sea level, can added follows:","code":"# Here we simply add the range as simple binary predictor mod1 <- basemodel |>     add_predictor_range(virtual_range, method = \"distance\")  # We can see that the range has been added to the predictors object # 'distance_range' mod1$get_predictor_names() #> [1] \"bio01_mean_50km\"     \"bio03_mean_50km\"     \"bio19_mean_50km\"     #> [4] \"CLC3_112_mean_50km\"  \"CLC3_132_mean_50km\"  \"CLC3_211_mean_50km\"  #> [7] \"CLC3_312_mean_50km\"  \"elevation_mean_50km\" \"distance_range\" # Specification  basemodel <- distribution(background) |>        add_predictors(env = predictors, transform = \"scale\", derivates = \"none\")  |>        engine_inlabru()   mod1 <- basemodel |>    add_predictor_elevationpref(layer = predictors$elevation_mean_50km,                               lower = 300, upper = 800)  # Plot the threshold for an upper plot( mod1$predictors$get_data()[[c(\"elev_low\", \"elev_high\")]] )"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-through-offsets","dir":"Articles","previous_headings":"","what":"Integration through offsets","title":"Data integration","text":"Apart including spatial-explicit prior biodiversity knowledge predictors SDM model, - particular Poisson Process Models (PPM) - also different approach, include variable offset prediction. effectively tells respective engine change intercepts coefficients based existing knowledge, can instance existing coefficient. Offsets can specified addition nuisance model, instance either adding expert-delineated range offset factoring spatial bias areas high sampling density accessibility. Multiple offsets can specified given PPM simply multiplying , since \\(log(off_1 * off_2) = log(off_1) + log(off_2)\\). comprehensive overview including offsets SDMs can found Merow et al. (2016).  ways add offsets model object, either directly (add_offset()) externally calculated RasterLayer instance “BossMaps” R-package, calculate range (add_offset_range()) elevation (add_offset_elevation()) offset, also biased offset (add_offset_bias()) case offset removed prediction.","code":"# Specification  mod1 <- distribution(background)  |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\")  |>        add_biodiversity_poipo(virtual_species,field_occurrence = \"Observed\") |>         add_offset_range(virtual_range, distance_max = 5e5) |>         engine_glmnet() |>     # Train   train(runname = \"Prediction with range offset\",only_linear = TRUE)  plot(mod1)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-with-priors","dir":"Articles","previous_headings":"","what":"Integration with priors","title":"Data integration","text":"different type integration also possible use informed priors, can set fixed random effects model. Bayesian context prior generally understood form uncertain quantity meant reflect direction /magnitude model parameters usually known -priori inference prediction. Offsets can also understood “priors”, however context SDMs, usually included spatial-explicit data, opposed priors available tabular form (known habitat affiliations). Since ibis.iSDM package supports variety engines Bayesian strict sense (engine_gdb engine_xgboost), specification priors differs depending engine question. Generally [Prior-class] objects can grouped : Probabilistic priors estimates placed example mean (\\(\\mu\\)) standard deviation (\\(\\sigma\\)) precision case [engine_inla]. priors usually allow greatest amount flexibility since able incorporate information sign magnitude coefficient. Monotonic constraints direction coefficient predictor model, \\(f(x_1) >= f(x_2)\\) \\(f(x_1) <= f(x_2)\\). Useful incorporate instance prior ecological knowledge certain response function example positive. complex priors specified random spatial effects penalized complexity priors used SPDE effects [add_latent_spatial()]. Probabilistic priors inclusion probability certain variable certainty variable included regularized outcome. example used case [engine_breg] [engine_glmnet]. Prior specifications specific engine information can found individual help pages priors() function.   also now convenience function allows extract coefficients weights existing model can passed another model engine (get_priors()). requirement fitted model provided well target engine coefficients/priors created.","code":"# Set a clean base model with biodiversity data x <- distribution(background) |>        add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        add_biodiversity_poipo(virtual_species, field_occurrence = \"Observed\") |>         engine_inlabru()  # Make a first model mod1 <- train(x, only_linear = TRUE)  # Now assume we now that the species occurs more likely in intensively farmed land.  # We can use this information to construct a prior for the linear coefficient. p <- INLAPrior(variable = \"CLC3_211_mean_50km\",                type = \"normal\",                hyper = c(2, 1000) # Precision priors, thus larger sigmas indicate higher precision                ) # Single/Multiple priors need to be passed to `priors` and then added to the model object. pp <- priors(p) # The variables and values in this object can be queried as well pp$varnames() #> f9eade5e-69a1-40b0-a738-f90a1c441153  #>                 \"CLC3_211_mean_50km\"  # Priors can then be added via  mod2 <- train(x |> add_priors(pp), only_linear = TRUE) # Or alternatively directly as parameter via add_predictors, # e.g. add_predictors(env = predictors, priors = pp)  # Compare the difference in effects p1 <- partial(mod1, pp$varnames(), plot = TRUE) p2 <- partial(mod2, pp$varnames(), plot = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"integration-with-ensembles","dir":"Articles","previous_headings":"","what":"Integration with ensembles","title":"Data integration","text":"Another straight forward way model-based integration simply fit two separate models different biodiversity dataset create ensemble . approach also works across different engines variety data types (cases requiring normalization given difference units model assumptions). (Note also possible create ensemble partial responses via ensemble_partial()).","code":"# Create and fit two models mod1 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_glmnet() |>        # Add dataset 1        add_biodiversity_poipo(poipo = virtual_species, name = \"Dataset1\",field_occurrence = \"Observed\") |>        train(runname = \"Test1\", only_linear = TRUE)  mod2 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>        engine_xgboost(iter = 5000) |>         # Add dataset 2, Here we simple simulate presence-only points from a range       add_biodiversity_polpo(virtual_range, name = \"Dataset2\",field_occurrence = \"Observed\",                              simulate = TRUE,simulate_points = 300) |>         train(runname = \"Test1\", only_linear = FALSE)  # Show outputs of each model individually and combined plot(mod1) plot(mod2) # Now create an ensemble: # By setting normalize to TRUE we furthermore ensure each prediction # is on a comparable scale [0-1]. e <- ensemble(mod1, mod2, method = \"mean\", normalize = TRUE)  # The ensemble contains the mean and the coefficient of variation across all objects plot(e)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"combined-and-joint-likelihood-estimation","dir":"Articles","previous_headings":"","what":"Combined and joint likelihood estimation","title":"Data integration","text":"examples always added single biodiversity data source model trained, add multiple different ones? outlined Isaac et al. 2020 joint, model-based integration different data sources allows borrow strengths different types datasets (quantity, quality) accurate parameter estimations well control biases. Particular SDMs also benefit avoiding make unreasonable assumptions absence species, commonly done addition pseudo-absences (despite called pseudo, logistic likelihood function treats true absence). Depending engine, ibis.iSDM package currently supports either combined joint estimation several datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"combined-integration","dir":"Articles","previous_headings":"Combined and joint likelihood estimation","what":"Combined integration","title":"Data integration","text":"default engines support joint estimation (see ) make use combined integration, currently three different options: “predictor”: predicted output first (previously fitted) models added predictor stack thus predictors subsequent models (Default). “offset”: predicted output first (previously fitted) models added spatial offsets subsequent models. Offsets back-transformed depending model family. might work likelihood functions engines! “prior”: option make use coefficients previous model define priors used next model. Note option creates priors based previous fits can result unreasonable constrains (particular coefficients driven largely latent variables). Can used projections (scenario()). “interaction”: case two datasets type also possible make use factor interactions. case prediction made based first reference level (e.g. first added dataset) others “partialed” prediction. method works one fits model multiple datasets response (e.g. Bernoulli distributed). Can used projections (scenario()). “weights”: type integration works two biodiversity datasets type. datasets combined one, however observations weighted weights parameter add_biodiversity call. can example used give one dataset arbitrary (expert-defined) higher value compared another. can specified parameter train(). Note methods (like “predictor” & “offset”), models trained sequence datasets added!","code":"# Specification  mod1 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>      # A presence only dataset       add_biodiversity_poipo(virtual_species,field_occurrence = \"Observed\") |>       # A Presence absence dataset       add_biodiversity_poipa(virtual_pseudoabs,field_occurrence = \"Observed\") |>         engine_xgboost() |>    # Train   train(runname = \"Combined prediction\",only_linear = TRUE,         method_integration = \"predictor\")  # The resulting object contains only the final prediction, e.g. that of the presence-absence model plot(mod1)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/03_integrate_data.html","id":"joint-likelihood-estimation","dir":"Articles","previous_headings":"Combined and joint likelihood estimation","what":"Joint likelihood estimation","title":"Data integration","text":"engines, notably [engine_inla], [engine_inlabru] [engine_stan] support joint estimation multiple likelihoods. algorithmic approach package generally follows approach outlined presence-datasets modelled log-Gaussian Cox process expected number individuals estimated function area \\(\\) following Poisson distribution: \\[\\begin{align*} N() &\\sim {\\sf Poisson}\\left(\\int_{} \\lambda()\\right) \\\\ \\end{align*}\\] \\[\\begin{align*} \\log(\\lambda()) = \\alpha_{1} + \\sum_{k}^{K} \\beta_{k}x_{} \\end{align*}\\] \\(N\\) number individuals, \\(\\) Area given spatial unit \\(\\), \\(N()\\) estimate relative rate occurrence per unit area (ROR). \\(k\\) increment \\(K\\) number predictors. \\(\\lambda\\) intensity function, \\(\\alpha\\) intercept \\(\\beta\\) parameter coefficients environmental covariates. Note interactions Presence-absence data estimated draws Bernoulli distribution: \\[\\begin{align*} Y_{} &\\sim {\\sf Bernoulli(p_{})}, = 1, 2, ... \\\\ \\end{align*}\\] \\[\\begin{align*} \\log(-\\log(1-p_{})) &= \\alpha_{2} + \\sum_{k}^{K} \\beta_{k}x_{} \\end{align*}\\] \\(Y\\) presence-absence record (usually standardized survey) sampled Bernoulli distribution given spatial unit \\(\\). \\(\\alpha\\) intercept \\(\\beta\\) parameter coefficients environmental covariates. log-likelihood can understood cloglog functon. Joint likelihood estimated multiplying two likelihoods \\(\\prod_{l}^{L} f(l)\\), \\(L\\) individual likelihood, \\(\\beta_{k}\\) shared parameters two likelihoods. works assume \\(cloglog(p_i) \\approx log(\\lambda())\\). Equally also possible add shared latent spatial effects Gaussian fields (approximated stochastic partial differential equation (SPDE)) model, assuming shared factors - biases - affecting datasets. See Engine comparison overview engines support level integration.","code":"# Define a model mod1 <- distribution(background) |>         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>      # A presence only dataset       add_biodiversity_poipo(virtual_species,field_occurrence = \"Observed\") |>       # A Presence absence dataset       add_biodiversity_poipa(virtual_pseudoabs,field_occurrence = \"Observed\") |>       # Use inlabru for estimation and default parameters.     # INLA requires the specification of a mesh which in this example is generated from the data.       engine_inlabru() |>    # Train   train(runname = \"Combined prediction\", only_linear = TRUE,         method_integration = \"predictor\")  # The resulting object contains the combined prediction with shared coefficients among datasets. plot(mod1) # Note how an overall intercept as well as separate intercepts for each dataset are added. summary(mod1) #> # A tibble: 11 × 8 #>    variable                   mean      sd      q05     q50    q95    mode   kld #>                                          #>  1 Intercept               -0.324  25.8    -42.8    -0.324  42.1   -0.324      0 #>  2 Intercept_species.._po… -0.324  25.8    -42.8    -0.324  42.1   -0.324      0 #>  3 Intercept_species.._po… -0.324  25.8    -42.8    -0.324  42.1   -0.324      0 #>  4 bio01_mean_50km         -0.0787  0.132   -0.296  -0.0787  0.138 -0.0787     0 #>  5 bio03_mean_50km         -0.481   0.121   -0.679  -0.481  -0.283 -0.481      0 #>  6 bio19_mean_50km          0.458   0.0872   0.315   0.458   0.602  0.458      0 #>  7 CLC3_112_mean_50km       0.390   0.0497   0.308   0.390   0.471  0.390      0 #>  8 CLC3_132_mean_50km       0.0951  0.0483   0.0157  0.0951  0.174  0.0951     0 #>  9 CLC3_211_mean_50km       0.887   0.0779   0.759   0.887   1.02   0.887      0 #> 10 CLC3_312_mean_50km       0.971   0.0662   0.862   0.971   1.08   0.971      0 #> 11 elevation_mean_50km      0.0250  0.0852  -0.115   0.0250  0.165  0.0250     0"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"load-relevant-packages-and-testing-data","dir":"Articles","previous_headings":"","what":"Load relevant packages and testing data","title":"Creating biodiversity projections","text":"purpose example loading testing data species distributions well contemporary future predictors. Note names predictors used building distribution model consistent creating projections! ## Train model create future projection make use data loaded () first create species distribution model contemporary conditions (b) project obtained coefficients future using future predictors. guidance distribution models trained, see vignettes (1). scenario object can finally trained via project().","code":"# Load the packages library(ibis.iSDM) library(stars) library(xgboost) library(terra) library(igraph) library(ggplot2) library(ncdf4) library(assertthat)  # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE) # Background and biodiversity data background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM')) virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'points', quiet = TRUE)  # Note we are loading different predictors than in previous examples # These are in netcdf4 format, a format specific for storing spatial-temporal data including metadata. ll <- list.files(system.file(\"extdata/predictors_presfuture/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.nc\",full.names = TRUE)  # From those list of predictors are first loading the current ones as raster data # We are loading only data from the very first, contemporary time step for model fitting pred_current <- terra::rast() for(i in ll) suppressWarnings( pred_current <- c(pred_current, terra::rast(i, lyrs = 1) ) ) names(pred_current) <- tools::file_path_sans_ext( basename(ll) )  # Get future predictors # These we will load in using the stars package and also ignoring the first time step pred_future <- stars::read_stars(ll) |> stars:::slice.stars('Time', 2:86) st_crs(pred_future) <- st_crs(4326) # Set projection # Rename future predictors to those of current names(pred_future) <- names(pred_current)  # Plot the test data plot(pred_current['secdf'],      col = colorRampPalette(c(\"grey20\", \"orange\", \"lightgreen\", \"green\"))(10),      main = \"Share of secondary vegetation\") # Train model adding the data loaded above x <- distribution(background) |>    add_biodiversity_poipo(virtual_points, field_occurrence = 'Observed', name = 'Virtual points') |>    # Note that we scale the predictors here   add_predictors(pred_current, transform = 'scale',derivates = 'none') |>    engine_glmnet(alpha = 0)  #> Loaded glmnet 4.1-8  # Train the model modf <- train(x, runname = 'Simple PPM', verbose = FALSE)  # Add a threshold to this model by getting 05 percentile of values modf <- threshold(modf, method = 'percentile', value = 0.05)  # -- # # Now lets create a scenarios object via scenarios sc <- scenario(modf) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from the model object.   threshold()  # This creates a scenario object sc #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2100-01-01 (83.9 years) #>  ---------  #>   Threshold:      0.031 (percentile) #>  ---------  #>   Scenarios fitted: None # The object contains its own functions. See the scenarios help file for more information on  # what is possible with them names(sc) #>  [1] \"threshold\"            \"verify\"               \"t\"                    #>  [4] \"summary_beforeafter\"  \"summary\"              \"show\"                 #>  [7] \"set_simulation\"       \"set_predictors\"       \"set_data\"             #> [10] \"set_constraints\"      \"scenarios\"            \"save\"                 #> [13] \"rm_predictors\"        \"print\"                \"predictors\"           #> [16] \"plot_threshold\"       \"plot_relative_change\" \"plot_migclim\"         #> [19] \"plot_animation\"       \"plot\"                 \"modelobject\"          #> [22] \"modelid\"              \"mask\"                 \"limits\"               #> [25] \"initialize\"           \"get_timeperiod\"       \"get_thresholdvalue\"   #> [28] \"get_threshold\"        \"get_simulation\"       \"get_resolution\"       #> [31] \"get_projection\"       \"get_predictors\"       \"get_predictor_names\"  #> [34] \"get_model\"            \"get_limits\"           \"get_data\"             #> [37] \"get_constraints\"      \"get_centroid\"         \"constraints\"          #> [40] \"clone\"                \"calc_scenarios_slope\" \"apply_threshold\"      #> [43] \".__enclos_env__\" sc.fit1 <- sc |> project() # Note that an indication of fitted scenarios has been added to the object sc.fit1 #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2100-01-01 (83.9 years) #>  ---------  #>   Threshold:      0.031 (percentile) #>  ---------  #>   Scenarios fitted: Yes"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"summarizing-and-plotting-the-fitted-projections","dir":"Articles","previous_headings":"","what":"Summarizing and plotting the fitted projections","title":"Creating biodiversity projections","text":"distribution models number ways scenarios can visualized interacted : plot() makes visualization projections time steps (!) plot_relative_change() calculates change suitability area first last timestep categorizes result accordingly. Note SDMs directly infer colonization extinction, gains losses suitable habitat! calc_scenarios_slope() calculates slope (rate change) across timesteps. Useful summarizing results summary() creates summary output contained scenarios. threshold() specified, function summarize amount area timestep. get_data() gets created scenarios stars object (plus thresholds specified).      Finally, scenarios projections can also saved specific outputs. , enabled via write_output() works just [BiodiversityScenario] objects, difference output can specified netCDF-4 file.","code":"# Plot all scenarios. With a large number of predictors this figure will be messy... plot(sc.fit1) # or sc.fit1$plot() # As an alternative, visualize the linear slope per grid cell and across all time steps o <- sc.fit1$calc_scenarios_slope(plot = TRUE) # Another option is to calculate the relative change between start and finish o <- sc.fit1$plot_relative_change(plot = TRUE) # We can also summarize the thresholded data o <- sc.fit1$summary() plot(area_km2~band, data = o, type = 'b',      main = \"Suitable habitat across Time\",      ylab = \"Amount of area (km2)\", xlab = \"Time\") # How does habitat gain and loss change over time? plot(totchange_gain_km2~band, data = o, type = 'n',      main = \"Habitat gain and loss\", ylim = c(-1.5e4, 1.5e4),      ylab = \"Amount of area (km2)\", xlab = \"Time\") lines(o$totchange_gain_km2~o$band, col = \"blue\") lines((o$totchange_loss_km2)~o$band, col = \"red\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"adding-constraints-to-projections","dir":"Articles","previous_headings":"","what":"Adding constraints to projections","title":"Creating biodiversity projections","text":"simple scenario use naive assumption , depending response functions fitted distribution model, suitable habitat within background modelling region potentially reachable species. reality might however geographic (e.g. islands), environmental biotic constraints far species can disperse. can specified constrain function [add_constraint()] variety constraints currently available, depend packages. add_constraint() Generic wrapper specific ‘method’ can supplied. See documentation information available options parameters. add_constraint_dispersal() add dispersal constraint projections applied time step. Supports various options 'sdd_fixed' fixed dispersal kernels, 'sdd_nexpkernel' negative exponential kernel 'sdd_kissmig' applying kissmig framework. add_constraint_MigClim() Use MigClim R-package simulate dispersal events time steps. number parameters required adding constrain also overwrite default plotting capacities (example via sc$plot_migclim()). See also help file Engler et al. (2012) information. add_constraint_connectivity() Add connectivity constrain projection. Currently hard barriers implemented, future additional sub-modules planned enable options . add_constraint_adaptability() Simple constraints adaptability species novel climatic conditions. Currently simple nichelimits implemented, ‘cap’ projections novel environments observed ranges contemporary predictors. add_constraint_boundary() Specifying hard boundary constraint projections, example limiting (future) projections certain area biome contemporary range. Lastly also options stabilize suitability projections via project() function. Specifying stabilization results projections smoothed informed incremental time steps. can particularly help projections use variables known make sudden, abrupt jumps time steps (e.g. precipitation anomalies).     Another option constraining prediction also imposing zonal limit (instance climatically defined) projections (see alternatively add_constraint_boundary() ). done fitting SDM reference conditions (see example limits (1) ) considered (future) projections.","code":"# Adding a simple negative exponential kernel to constrain the predictions sc.fit2 <- sc |>       add_constraint(method = \"sdd_nex\", value = 1e5) |>     # Directly fit the object    project(stabilize = F)  # Also fit one projection a nichelimit has been added sc.fit3 <- sc |>       add_constraint(method = \"sdd_nex\", value = 1e5) |>     add_constraint_adaptability(method = \"nichelimit\") |>     # Directly fit the object    project(stabilize = F)  # Note how constrains are indicated in the scenario object. sc.fit3 #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2100-01-01 (83.9 years) #>  ---------  #>   Constraints:    dispersal (sdd_nexpkernel), adaptability (nichelimit) #>   Threshold:      0.031 (percentile) #>  ---------  #>   Scenarios fitted: Yes  # The naive assumption is that there is unlimited dispersal across the whole background # Note how the projection with dispersal constrain results in a considerable smaller amount of suitable habitat. sc.fit1$plot(which = 40) # Baseline sc.fit2$plot(which = 40) # With dispersal constrain sc.fit3$plot(which = 40) # With dispersal limit and nichelimitation (within a standard deviation) # Lets compare the difference in projections compared to the naive one defined earlier.  o1 <- sc.fit1$summary() o2 <- sc.fit2$summary() o3 <- sc.fit3$summary() arlim <- c(min(o1$area_km2, o2$area_km2, o3$area_km2)-10000,            max(o1$area_km2, o2$area_km2, o3$area_km2))  plot(area_km2~band, data = o1, type = 'n',      ylim = arlim,      main = \"Suitable habitat projection\",      ylab = \"Amount of area (km2)\", xlab = \"Time\") lines(o1$area_km2~o1$band, col = \"black\", lty = 1) lines(o2$area_km2~o2$band, col = \"black\", lty = 2) lines(o3$area_km2~o3$band, col = \"black\", lty = 3) legend(\"bottomleft\",    legend = c(\"Unlimited dispersal\", \"Constrained dispersal\",              \"Constrained dispersal and niche limit\"),    lty = c(1, 2, 3),   cex = 1.2,   bty = \"n\") # Lastly it is also possible to directly summarize the state  # before (usually first year) and end (last year). sc.fit2$summary_beforeafter() #> # A tibble: 13 × 5 #>    runname    category                  period       value unit       #>                                              #>  1 Simple PPM Current range             2016-01-01 431.    ha         #>  2 Simple PPM Future range              2100-01-01 417.    ha         #>  3 Simple PPM Unsuitable                84 years   191.    ha         #>  4 Simple PPM Loss                      84 years    14.7   ha         #>  5 Simple PPM Gain                      84 years     0.693 ha         #>  6 Simple PPM Stable                    84 years   416.    ha         #>  7 Simple PPM Percent loss              84 years     3.42  %          #>  8 Simple PPM Percent gain              84 years     0.161 %          #>  9 Simple PPM Range change              84 years   -14.0   ha         #> 10 Simple PPM Percent change            84 years    -6.83  %          #> 11 Simple PPM Sorensen index            84 years     0.984 similarity #> 12 Simple PPM Centroid distance         84 years    19.8   km         #> 13 Simple PPM Centroid change direction 84 years     7.91  deg"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/04_biodiversity_projections.html","id":"specific-parsers-for-globiom-related-scenarios","dir":"Articles","previous_headings":"","what":"Specific parsers for GLOBIOM related scenarios","title":"Creating biodiversity projections","text":"IIASA’s Global Biosphere Management Model (GLOBIOM) partial equilibrium model used analyze competition land use agriculture, forestry, bioenergy, main land-based production sectors. builds . ibis.iSDM part IIASA’s suite integrated models, direct link available make use downscaled GLOBIOM outputs. Implemented functions either directly format data via [formatGLOBIOM()] add DistributionModel-class BiodiversityScenario-class object directly via add_predictors_globiom() .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"mechanistic-species-distribution-modelling","dir":"Articles","previous_headings":"","what":"Mechanistic species distribution modelling","title":"Mechanistic species distribution modelling","text":"vignette describes available options incorporating mechanistic modelling approaches ibis.iSDM package. approaches can broadly separated “added” existing modelling routines, ibis.iSDM outputs can used input mechanistic modelling. package provides basic wrappers. delve options mechanistic SDMs ibis.iSDM package, useful remind us term ‘mechanism’ actually means. literature range different definitions, sometimes referring mechanistic SDMs incorporate ecological processes (e.g. demography, dispersal, eco-evolutionary principles). Yet often, correlative SDMs also declared “mechanistic” somehow incorporate specific constrain response function towards environmental variable. example, micro-climatic limits persistence species Briscoe et al. 2023, presence biotic interactions (estimated separate SDM different species) also sometimes referred limiting mechanisms (Ohlmann et al. 2023). latter approaches - largely fine-tuning specific response function - can extent emulated creating specific derivates adding covariate priors (add_priors()) model predictors (add_predictors_model()) SDM. methods added package become available can readily incorporated modelling framework. types integration can also directly modelled integration. details provided vignettes data preparation creating derivates vignette data integration. Users package also directed various add_constraint() functions, many enable corrections projected scenarios.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"adding-ecological-processes-to-correlative-sdms","dir":"Articles","previous_headings":"Mechanistic species distribution modelling","what":"Adding ecological processes to correlative SDMs","title":"Mechanistic species distribution modelling","text":"range wrappers implemented ibis.iSDM allow convenient passing outputs parameters mechanistic modelling packages. wrappers support convenient addition ecological processes dispersal scenarios data integration. enable ibis.iSDM outputs directly become inputs simulations. case key parameters available, package users encouraged check various options add_constraint() function. mechanistic approaches require quite extensive model understanding many cases additional training. Furthermore range parameters usually required outputs meaningful. beyond scope vignette provide introduction various models. Rather, demonstrated linkages ibis.iSDM models can made, reader referred original publication underlying approach (see help page references).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"adding-dispersal-to-scenarios-with-kissmig","dir":"Articles","previous_headings":"Mechanistic species distribution modelling > Adding ecological processes to correlative SDMs","what":"Adding dispersal to scenarios with KISSMig","title":"Mechanistic species distribution modelling","text":"KISSMig model provide simple model estimate limit dispersal species distribution models (Nobis & Normand, 2014). include ecological mechanism related recruitment , instead works simple stochastic migration estimator allows inclusion time-lagged dispersal local neighborhoods. ibis.iSDM package KISSMig simulator can added dispersal constraint (among others) scenario objects. Example:  Now lets add KISSMig dispersal constraints. constrain directly used fitted suitability estimates projected timestep also makes use created thresholded layer. Per time-step dispersal events stochastically simulated constraint range expansions next modelling steps. See ?kissmig::kissmig help-page help explanations parameters.","code":"library(ibis.iSDM) library(terra) #> terra 1.7.71 library(ggplot2) # Don't print out as many messages options(\"ibis.setupmessages\" = FALSE)  # Background and biodiversity data background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM')) virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'points', quiet = TRUE) # Add some pseudo-absence information for later poa <- virtual_points |> add_pseudoabsence(field_occurrence = 'Observed',                                            template = background)  # Note we are loading different predictors than in previous examples # These are in netcdf4 format, a format specific for storing spatial-temporal data including metadata. ll <- list.files(system.file(\"extdata/predictors_presfuture/\", package = \"ibis.iSDM\", mustWork = TRUE), \"*.nc\",full.names = TRUE)  # From those list of predictors are first loading the current ones as raster data # We are loading only data from the very first, contemporary time step for model fitting pred_current <- terra::rast() for(i in ll) suppressWarnings( pred_current <- c(pred_current, terra::rast(i, lyrs = 1) ) ) names(pred_current) <- tools::file_path_sans_ext( basename(ll) )  # Get future predictors # These we will load in some time steps using the stars package and ignoring the first time step suppressWarnings( pred_future <- stars::read_stars(ll) |> stars:::slice.stars('Time', seq(2,86,by=10)) ) sf::st_crs(pred_future) <- sf::st_crs(4326) # Set projection # Rename future predictors to those of current names(pred_future) <- names(pred_current)  # ------ # # Fit a model fit <- distribution(background) |>    add_biodiversity_poipa(poa, field_occurrence = 'Observed', name = 'Virtual points') |>    # Note that we scale the predictors here   add_predictors(pred_current, transform = 'scale',derivates = 'none') |>    engine_glmnet(alpha = 0) |>    # Train the model   train(verbose = FALSE) |>    # Add simple percentile thresholds   threshold(method = 'percentile', value = .33)  # Show the threshold fit$plot_threshold() # Create a scenario object sc <- scenario(fit) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from    # the fitted model object.   threshold()     # Add KISSMig constraint sc1 <- sc |>    add_constraint_dispersal(method = \"kissmig\",                            type = \"DIS\", # Final distribution result                            value = 10, # Number of iteration steps                            # These parameters are for KISSMig and get passed on                            # Probablitiy of local extinction between iterations                            pext = 0.5,                            # Probability corner cells are colonized.                            pcor = 0.2                            )  sc2 <- sc |>    add_constraint_dispersal(method = \"kissmig\",                            type = \"DIS\", # Final distribution result                            value = 10, # Number of iteration steps                            # These parameters are for KISSMig and get passed on                            # Probablitiy of local extinction between iterations                            pext = 0.9,                            # Probability corner cells are colonized.                            pcor = 0.1                            )  # Project two scenarios with varying local extinction probability df1 <- project(sc1, verbose = FALSE) |> summary() #> Linking to GEOS 3.10.2, GDAL 3.4.1, PROJ 8.2.1; sf_use_s2() is FALSE df2 <- project(sc2, verbose = FALSE) |> summary() df <- dplyr::bind_rows(df1 |> dplyr::mutate(scenario = \"low\"),                        df2 |> dplyr::mutate(scenario = \"high\") ) # ------ # ggplot(df, aes(x = band, y= area_km2/1e6,                group = scenario, color = scenario)) +   theme_bw(base_size = 16) +   geom_line() +   labs(x = \"Time\", y = \"Occupied area (Million km2)\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"adding-dispersal-to-scenarios-with-migclim","dir":"Articles","previous_headings":"Mechanistic species distribution modelling > Adding ecological processes to correlative SDMs","what":"Adding dispersal to scenarios with MIGCLIM","title":"Mechanistic species distribution modelling","text":"Another dispersal simulator MIGCLIM (Engler et al. 2014), stochastic simulator innovatively allows differentiate short long-distance dispersal events well varying propagule pressure. Unfortunately currently available CRAN anymore (stand September 2023), possibly lack maintenance missing dependency. package can still downloaded github however (https://github.com/robinengler/MigClim/). Assuming user able install MigClim package ’s dependencies (also disappared CRAN), can run ibis.iSDM follows: example updated update current R versions (>3.0) becomes available.","code":"prj <- scenario(fit) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from    # the fitted model object.   threshold() |>  # Check the help files for the function for an explanation of the parameters.   add_constraint_MigClim(rcThresholdMode = 'continuous',                          dispSteps = 1,                          dispKernel = c(1.0, 0.4, 0.16, 0.06, 0.03),                          barrierType = \"strong\",                          lddFreq = 0, lddRange = c(1000, 10000),                          iniMatAge = 1, propaguleProdProb = c(0.2, 0.6,0.8, 0.95),                          replicateNb = 10) |>    # Project the model   project()  # MIGCLIM outputs are provided a single updated layer and can be plotted through # a customized plotting function. prj$plot_migclim()"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/05_mechanistic_estimation.html","id":"simulating-spatial-explicit-population-abundance-with-steps","dir":"Articles","previous_headings":"Mechanistic species distribution modelling > Adding ecological processes to correlative SDMs","what":"Simulating spatial-explicit population abundance with steps","title":"Mechanistic species distribution modelling","text":"steps package implements spatial-temporal explicit metapopulation simulator (Visintin et al. 2021) able account varying vital rates, dispersal barriers density dependence. steps simulator, thus makes use range parameters critical correlative assumptions estimate example abundance given time step. ibis.iSDM package linkage steps can established directly scenario projections simply adding separate module. added, steps used make spatial-temporal abundance estimates aligned projection time step, eventual specified barriers provided parameters regards vital rates density-dependence. Note: wrapper functionality implemented ibis.iSDM package based assumption higher habitat suitability (estimated correlative SDM) linearly correlated higher population abundance. noted assumptions questioned interpreted caution (Lee-Yaw et al. 2021). Users always clearly understand rationale behind parameter choices!","code":"require(\"steps\") #> Loading required package: steps  # Define some arbitrary vital rates for the transition for this purpose # Define vital rates vt <- matrix(c(0.0,0.52,0.75,               0.52,0.28,0.0,               0.0,0.52,0.75),               nrow = 3, ncol = 3, byrow = TRUE) colnames(vt) <- rownames(vt) <- c('juvenile','subadult','adult')  # We again specify a scenario as before using the fitted model prj <- scenario(fit) |>    # Apply the same variable transformations as above.    add_predictors(pred_future, transform = 'scale') |>    # Calculate thresholds at each time step. The threshold estimate is taken from    # the fitted model object.   threshold() |>    # We then specify that we we    simulate_population_steps(vital_rates = vt)  # Notice how we have added steps as additional simulation outcome prj #> Spatial-temporal scenario: #>   Used model: DistributionModel #>  ---------  #>   Predictors:     bio01, bio12, crops, ... (9 predictors) #>   Time period:    2016-01-01 -- 2096-01-01 (79.9 years) #>  ---------  #>   Threshold:      0.521 (percentile) #>   Simulations:    simulation (steps) #>  ---------  #>   Scenarios fitted: None # Now project scenario1 <- project(prj) plot(scenario1, \"population\") # Also see a different one where we add a dispersal constraint and density dependence dispersal <- steps::fast_dispersal(dispersal_kernel = steps::exponential_dispersal_kernel(distance_decay = 1)) scenario2 <- project(prj |>                        simulate_population_steps(vt,                                                  dispersal = dispersal,                                                  density_dependence = steps::ceiling_density(3) ) )  # We can see that the dispersal constraint and higher density dependence cleary # results in a population abundance that tends to be concentrated in central Europe. plot(scenario2, \"population\")"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/06_engine_comparison.html","id":"capabilities-of-included-engines","dir":"Articles","previous_headings":"","what":"Capabilities of included engines","title":"Comparison of different engines","text":"outlined Fletcher et al. (2019), many different forms integration [ensemble] modelling, adding [offsets], predictors (e.g. [add_predictor_range()] ) [priors] full integration different likelihoods (See (Data integration) ). options available every engine supported ibis.iSDM package table shows currently implemented engines various types integrations supported . Stating name function call engine supported model complexity linear (ln) non-linear (nl) formulations, although noted linear models can approximate non-linearity including transformations (Maxent, e.g. hinge/product/quadratic). every engine supports different types integration via ensembles, offsets, priors, joint likelihood estimation ensemble compositing models using separate datasets species. multiple biodiversity datasets added engine support joint likelihood estimation, parameter method_integration [train()] determines different predictions integrated. Available options integration via predictors, offsets, interactions, priors weights (see help file [train()] information).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/07_package_comparison.html","id":"comparison-with-other-packages","dir":"Articles","previous_headings":"","what":"Comparison with other packages","title":"Capabilities compared to other SDM packages","text":"Species distribution modelling (SDM) approaches around quite result number ecological modelling focused packages developed. general customized towards specific purposes modelling paradigm. isn’t just another SDM package? Indeed , ibis.iSDM number particular features set apart SDM packages: focuses particularly integration guiding principle different ways heterogeneous sources evidence can integrated. puts strong focus biodiversity types, particular Poisson-Process models (PPMs) default way analyzing presence-data. follows object-based modular programming philosophy, taking inspiration tidy programming approaches. supports number Bayesian SDM approaches algorithms, field traditionally less represented owing computational constraints. customized create modify spatio-temporal scenarios, including IIASA integrated land-use assessment model GLOBIOM. Thus overall, idea package part trying bring innovation SDM modelling world, also trying bring together strengths different existing tools. Non exhaustive list acknowledging SDM packages R compare ibis.iSDM provided : hSDM -> Bayesian framework hierachical mixed models. Fast, little flexibility regards weights, offsets different datatypes. multispeciesPP -> Package allows integrated SDMs, however developed since years key gaps remain particular regards different modelling approaches. inlabru -> Package specifically Lox-Gaussian-Cox Process (LGCP) models INLA, now integrated also engine ibis.iSDM pointedSDMs -> Another wrapper INLA allows integrate different datasets SDM. Less focus priors, offsets scenarios. biomod2 -> Popular package ensemble modelling, fixed specific (non-Bayesian) engines data types integration options. sdmTMB -> Package fitting spatial-Temporal SDMs specific biodiversity data. modleR -> similar biomod2 wrapper construct ensembles models. kuenm -> Another wrapper Maxent. flexSDM Similar biomod2 wrapper SDMs, coming several helper functions data preparation cross-validation. Besides SDMs also new packages available spatial integrated species occupancy models, spOccupancy. Occupancy modelling however requires specific biodiversity data information infer detectability species occurrences.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"frequently-asked-questions-faq","dir":"Articles","previous_headings":"","what":"Frequently Asked Questions (FAQ)","title":"Frequently Asked Questions (FAQ)","text":"document contains series frequently asked questions using ibis.iSDM package work progress.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"data-and-model-preparation","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Data and model preparation","title":"Frequently Asked Questions (FAQ)","text":"ibis.iSDM R-package can handle standard spatial formats R (vector raster formats) works predominantly [sf], [SpatRaster] [stars] packages much formatting processing work. adding [biodiversity] [predictor] variables distribution() object number default validity checks alignments commonly conducted, instance ensuring provided points align geographic projection. ease modelling avoid unfortunate errors crashes, ideally ensure following steps taken: 'background' layer describing modelling extent provided directly [sf] 'POLYGON' 'MULTIPOLYGON' object covers biodiversity predictor data. provided data geographic projection. Biodiversity data provided [sf] format covers 'background' bounding box. Furthermore biodiversity dataset set \"field_occurrence\" field numeric values. appropriately formatted (see also ). Important: environmental predictors becomes important ensure nodata values appropriately handled. Unfortunately many implemented [engines] can handle nodata values well, thus necessary pre-processing remove rows covariate extraction least one variable missing data. instance assinging constant NA values: Technically, impossible estimate probability occurrence just presence-data (commonly available databases like GBIF). people normally add called pseudo-absence (often excessive numbers) entire background data, approximating probability occurrence assuming detection probability uniform landscape (see Merow et al. 2013). ibis.iSDM package follows design principle data types (e.g. presence-presence-absence records) modelled least amount assumptions possible. presence-records default way estimating kind responses habitat suitability estimate data following Poisson-Process modelling approach. However, possible add pseudo-absence points presence-dataset follows: Also see add_pseudoabsence() pseudoabs_settings() help pages settings also first article website. example possible define pseudo-absence sampling specific spatial formats, sampling within outside minimum convex polygon (MCP) presence points within certain buffer. Yes, ibis.iSDM package uses range different functionalities , existing packages functions required specific purpose, packages question installed. easy convenience functions install packages ibis_dependencies() installs packages listed getOption(\"ibis.dependencies\").","code":"predictors[is.na(predictors)] <- 0 virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM'), 'points',quiet = TRUE) # This takes the default pseudo-absence options created when loading the Ibis package. virtual_points <- add_pseudoabsence(virtual_points, field_occurrence = \"Observed\") # Check that absence points are present unique(virtual_points$Observed)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"model-setup","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Model setup","title":"Frequently Asked Questions (FAQ)","text":"Yes, can desirable outcome modelling. instance one can make - absence better information dispersal constrain (see [add_constrain_dispersal]) - assumption certain species can disperse within given ecoregion beyond. See instance method section Wessels, Merow Trisos (2021). directly ibis.iSDM R-package, one specify limit projection [distribution()] object. context zones extent whole background (extent spatial scale). prediction however limited zones supplied biodiversity observations fall . dedicated function ([create_zonaloccurrence_mask()]) help set zones, either taking existing categorical raster datasets constructing buffers around existing presence records (example reflect assumed maximum dispersal distances). ibis.iSDM R-package allows users add prior information parameters model estimated. priors added engine-specific priors format depends engine question (see specific help pages information). prior can generally define via combination ENGINENAME + Prior wrapped PriorList used estimation. Example: Multiple priors Engine can defined PriorList. Whenever prior variable set , overwrites previous value. great number SDM literature suggests altering background / pseudo-absence points created, can greatly affect model outcomes (see add_pseudoabsence() references). ibis.iSDM R-package options available modify pseudo-absence points created. default package creates least 10 000 points least 25% presence-points (ever larger). change default pseudo-absence sampling settings, two options. Either change global default settings pseudo-absence sampling adding settings add_biodiversity function. overwrite global settings, following: Alternatively one think specifying specific pseudo-absence sampling information one biodiversity dataset specifically: code ibis.iSDM R-package default already parallelized many computationally-intensive operations making use cores (can find example case, please raise issue). number cores generally decided option \"ibis.nthread\" [ibis_options()]. cases, parallelized code run via [parallel] [doParallel] packages, although code infancy support [future] parallelization approaches well, offering greater flexibility. See function [ibis_future] information also use. typical use case thus run separate models (via train()) loop scheduler High-Performance-Computer. Users careful case shared resources, e.g. don’t parallelize operations machine. need parallelize multiple models instance, suggested disable 'ibis.runparallel' option. Yes. add_offset() add_offset_range() functions allows specify spatial explicit offset term added regression model question. offset generally just coefficient set specific value. get one offset, one just needs combine different provided offsets way consistent get fixed value (see reference. can done either summing transformed value (discouraged can errorprone) simply multiplying . Internally provided offsets model object combined via simple addition together. thus requires users transform aprior (instance log transform) adding estimation.","code":"# Where zone is a provided raster mod <- distribution(background, limits = zone) |>     add_biodiversity_poipo(species_data) |>     engine_gdb() |>     train() plot(mod)  # Alternatively one can also create such limits based on a minimum convex polygon # of the provided data. Here we create a non-buffered MCP across all points used # in species_data to constrain the prediction. mod <- distribution(background, limits_method = \"mcp\", mcp_buffer = 0) |>     add_biodiversity_poipo(species_data) |>     engine_gdb() |>     train() plot(mod) # We have prior information that 'Forest' is important for a species # In this case and for the INLA engine we define normal prior on the mean and precision p <- INLAPrior(variable = \"Forest\",type = \"normal\",hyper = c(2, 10)) # This is then wrapped in a PriorList pp <- priors(p) print( pp )  # We can specify multiple priors of course p <- list(   INLAPrior(variable = \"Forest\",type = \"normal\",hyper = c(2, 10)),   INLAPrior(variable = \"Cropland\",type = \"normal\",hyper = c(0, 1)) ) pp <- priors(pp)  # And can now added to the model mod <- distribution(background, limits = zone) |>     add_biodiversity_poipo(species_data) |>     add_predictors(covariates) |>     add_priors(priors = pp)   engine_inlabru() # Define new settings with greater number of background points ss <- pseudoabs_settings(background = NULL, nrpoints =  1e6) # Overwrite the default settings options(\"ibis.pseudoabsence\" = ss) # Define absence layer with biased background to sample from ss <- pseudoabs_settings(background = NULL, bias = bias_layer)  # Assuming background and point data exists x <- distribution(background) |>     add_biodiversity_poipo(points, pseudoabsence_settings = ss) # Check ibis options if set ibis_options() options('ibis.runparallel' = FALSE) # Set to FALSE offset1 <- runif(10) offset2 <- runif(10) # Identical log(offset1) + log(offset2) log(offset1*offset2)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"fitting-and-scenarios","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Fitting and Scenarios","title":"Frequently Asked Questions (FAQ)","text":"two options can enabled reduce number messages: setting parameter verbose train() FALSE messages created respective engine suppressed. Setting parameter ibis.setupmessages FALSE suppresses package related message. can done via Cross-validation deliberatly integrated package. Users like make use cross-validation techniques thus need set external modelling routines. Reason multiple types integration package, construction (independent) testing datasets trivial (considering example offsets, priors multiple datasets). ibis.iSDM R-package two engines makes use INLA framework, namely [engine_inla] [engine_inlabru]. package author started developing package, [engine_inlabru] yet support multiple likelihoods thus implemented directly. Predictions [engine_inla] [engine_inlabru] identical, although latter infer predictions directly, instead simulating posterior. simulation particularly helpful creating (future) projections otherwise new model need fitted every newdata object. creating predictive models SDMs often concern predict variable range outside environmental conditions model trained. ibis.iSDM package supports variable ‘clamping’ predictions similar popular Maxent model, however [engine]. Clamping can enabled setting parameter clamp [train] TRUE. restricts spatial (spatial-temporal) projections combined range predictor variables observed training localities. Similar functionalities also available separately scenario projections setting adaptability constraints (see [add_constraint_adaptability] [add_constraint_boundary]). many predictors SDM can cause substantial -parametrization subsequently overfitting (e.g. model reproducing data trained rather projecting areas unknown). recommended () either use engine strong regularization, example [engine_glmnet] [engine_gdb], (b) train model caution minimum number observations (arbitrary rule thumb, least 10 observations additional predictor included), (c) make use pre-estimation removal predictor, example variable importance criteria colinearity. See code example. distribution model trained inference_only parameter train() set FALSE (Default), outputs prediction found created object SpatRaster. default engines produce SpatRaster object least one band called “mean” average prediction engine. also result returned created model object plotted. addition, Bayesian Engines bands quantifying posterior predictive uncertainty might available can plotted well. raster can also saved spatial GeoTiff given filename using write_output() function. Example: usually due either number rounds estimation low learning_rate high. Try different options parameters engine. good way check performance also plot evaluation log logloss.","code":"options(\"ibis.setupmessages\" = FALSE) # Prior to model fitting, remove highly collinear predictors through a pearson correlation assessment mod <- distribution(background) |>     add_biodiversity_poipo(species_data) |>     engine_glmnet() |>     train(filter_predictors = \"pearson\")  # Alternatively use a RandomForest estimator to remove the least important variables mod <- distribution(background) |>     add_biodiversity_poipo(species_data) |>     engine_glmnet() |>     train(filter_predictors = \"RF\") mod <- distribution(background) |>     add_biodiversity_poipo(species_data) |>     engine_inlabru() |>     train() # To plot  plot(mod, \"mean\") plot(mod, \"sd\")  # To get the layer mod$get_data(\"prediction\")  # To save the output layer as floating point geoTiff write_output(mod, \"myoutput.tif\", type = \"gtif\", dt = \"FLT4S\") # Requires a fitted model plot(fit$get_data(\"fit_best\")$evaluation_log)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"model-troubleshooting","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Model troubleshooting","title":"Frequently Asked Questions (FAQ)","text":"various forms integration simple approach adding [ensembles], [priors] [offsets] fully integrated multiple likelihood models (see Fletcher et al. 2019). Thus, users range possibilities combine different sources evidence modelling. regards different [engines] treat multiple biodiversity datasets. Unfortunately [engine_inla()], [engine_inlabru()] [engine_stan()] support fully integrated multiple likelihood models. full overview can found Engine comparison table. [engines] combine multiple datasets running separate models sequence order determined sequence datasets added model. Within train() function, users option specifying previous predictions handled [method_integration] parameter. example predictions one model added predictors offset next. coefficients one model can used create starting priors next model. default, presence biodiversity data modelled point-process model (PPM, see Renner et al. 2015). Similar Maximum Entropy models models can quite sensitive biased input, common non-structured biodiversity observations presence points tend clustered urban easily accessible areas. avoid predictions biased towards covariates, number things can potentially done . Modify targeted background sampling better control background points. can instance done via add_pseudoabsence() pseudoabs_settings() methods. See respective help files. Make use spatial thinning approaches. See instance Aiello-Lammers et al. 2015 Steen et al. 2021. Note however spatial thinning remove data points, affecting instance poisson distributed models (PPMs) process. Theibis.iSDM package functionality spatial thinning implemented thin_observations() function. Partial biased variable prediction. add_control_bias() function can used specify value needs partialed model. bias_value specified can set instance 0 amount assumed equivalent minimal bias. Consider setting [clamp] parameter train() TRUE. Add spatial offset account bias introduced Merow et al. 2016. can done via add_offset_bias() function requires preparation bias layer advance. Apply rigorous filtering bias control input data. end correction can replace good data preparation cleaning. Remember GIGO principle.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/08_frequently-asked-questions.html","id":"any-other-questions-and-issues","dir":"Articles","previous_headings":"Frequently Asked Questions (FAQ)","what":"Any other questions and issues","title":"Frequently Asked Questions (FAQ)","text":"Often easier communicate index suitability (scale [0-1]) stakeholders policy, can principle derived ibis.iSDM output. Especially using Poisson Process models infer suitability given area, units can hard interpret non-scientists. easy way achieve added function Biodiversity distribution object. See example. feature, bug ;) Many covariates often come unusual characters symbols can readily used equations queries tabular data. sanitize_names() function cleans variable names removes / resets non conform symbols.","code":"# Train a model fit <- distribution(background) |>    # Presence-absence data   add_biodiversity_poipo(my_gbifpoints) |>    add_predictors(predictors) |>    engine_glmnet() |>    train()  # Make a transformed prediction of the suitability layer # The output is a normalized prediction surface  # created via (x - min) / (max - min) or x/sum(x) respectively pred <- fit$calc_suitabilityindex() # It can be disabled by setting the following option to false at the start of the script. options('ibis.cleannames' = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/articles/contributing.html","id":"contributing-to-development-of-the-ibis-isdm-r-package","dir":"Articles","previous_headings":"","what":"Contributing to development of the ibis.iSDM R-package","title":"Contributing to the Package development","text":"welcome contributions ibis.iSDM R-package. contributions simple typo fixes, additions documentation testthat tests, enhancing vignettes provide greater understanding package, completely new functions. latter, please get touch package author one maintainers first. Pull requests master branch require confirmation code review package maintainers.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/articles/contributing.html","id":"development-guidelines","dir":"Articles","previous_headings":"Contributing to development of the ibis.iSDM R-package","what":"Development guidelines","title":"Contributing to the Package development","text":"ibis.iSDM contains primarily functions fitting models. Speed flexibility key Don’t repeat . Create new functions necessary classes. Equally try reuse common names R, e.g. plot, summary Please run code checks tests regularly. Avoid using additional package dependencies possible. Comment code!! Use assertions verify inputs functions. bored, please write unit tests ensure evaluate (CRTL+SHIFT+T)! (also see issues projects) open issues","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Martin Jung. Author, maintainer, copyright holder. Maximilian H.K. Hesselbarth. Contributor.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Jung, M. (2023). integrated species distribution modelling framework heterogeneous biodiversity data. Ecological Informatics, 102127. Jung, M., Hesselbarth, H.K.M. (2023). integrated species distribution modelling framework heterogeneous biodiversity data. R package version 0.0.5","code":"@Article{,   title = {An integrated species distribution modelling framework for heterogeneous biodiversity data},   author = {Martin Jung},   journal = {Ecological Informatics},   volume = {76},   year = {2023},   pages = {102127},   url = {https://doi.org/10.1016/j.ecoinf.2023.102127}, } @Misc{,   title = {An integrated species distribution modelling framework for heterogeneous biodiversity data},   author = {Martin Jung and Maximilian H.K. Hesselbarth},   year = {2023},   version = {0.0.9}, }"},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"the-ibis-framework---an-integrated-model-for-biodiversity-distribution-projections","dir":"","previous_headings":"","what":"A R-package for Integrated Biodiversity distribution modelling","title":"A R-package for Integrated Biodiversity distribution modelling","text":"ibis.iSDM package provides series convenience functions fit integrated Species Distribution Models (iSDMs). integrated models generally refer SDMs incorporate information different biodiversity datasets, external parameters priors offsets respect certain variables regions. See Fletcher et al. (2019) Isaac et al. (2020) introduction iSDMs.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"A R-package for Integrated Biodiversity distribution modelling","text":"latest version can installed GitHub. CRAN release planned, meantime package can found R-universe well.","code":"# For installation (Not yet done) install.packages(\"ibis.iSDM\", repos = \"https://iiasa.r-universe.dev\")  # For Installation directly from github install.packages(\"remotes\") remotes::install_github(\"IIASA/ibis.iSDM\")"},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"basic-usage","dir":"","previous_headings":"","what":"Basic usage","title":"A R-package for Integrated Biodiversity distribution modelling","text":"See relevant reference site articles. Note package active development parameters functions might change. Citation: Jung, Martin. 2023. “Integrated Species Distribution Modelling Framework Heterogeneous Biodiversity Data.” Ecological Informatics, 102127, DOI","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"acknowledgement-","dir":"","previous_headings":"","what":"Acknowledgement","title":"A R-package for Integrated Biodiversity distribution modelling","text":"ibis.iSDM developed maintained Biodiversity, Ecology Conservation group International Institute Applied Systems Analysis (IIASA), Austria.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/index.html","id":"contributors","dir":"","previous_headings":"","what":"Contributors","title":"A R-package for Integrated Biodiversity distribution modelling","text":"contributions project gratefully acknowledged using allcontributors package following -contributors specification. Contributions kind welcome!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a tree-based split probability prior for BART — BARTPrior","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"Function include prior information split probability Bayesian additive regression tree model added via engine_bart. Priors engine_bart specified transition probabilities variables internally used generate splits regression tree. Specifying prior can thus help 'enforce' split given variable. can numeric coded values 0 1.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"","code":"BARTPrior(variable, hyper = 0.75, ...)  # S4 method for character BARTPrior(variable, hyper = 0.75, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"variable character matched existing predictors latent effects. hyper numeric object number >0 equal 1. Defaults 0.75. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"Even given variable included split regression classification tree, necessarily mean prediction changes value non-informative (split can occur early ). however affect variable importance estimates calculated model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a tree-based split probability prior for BART — BARTPrior","text":"Chipman, H., George, E., McCulloch, R. (2009) BART: Bayesian Additive Regression Trees. Chipman, H., George, E., McCulloch R. (2006) Bayesian Ensemble Learning. Advances Neural Information Processing Systems 19, Scholkopf, Platt Hoffman, Eds., MIT Press, Cambridge, MA, 265-272.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","title":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","text":"helper function specify several BARTPrior objects hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","text":"","code":"BARTPriors(variable, hyper = 0.75, ...)  # S4 method for character BARTPriors(variable, hyper = 0.75, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BARTPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a BART prior — BARTPriors","text":"variable character matched existing predictors latent effects. hyper numeric object number >0 equal 1. Defaults 0.75. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"Function include prior information via Zellner-style spike slab prior generalized linear models used engine_breg. priors similar horseshoe priors used regularized engine_stan models penalize regressions assuming predictors effect 0.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"","code":"BREGPrior(variable, hyper = NULL, ip = NULL)  # S4 method for character BREGPrior(variable, hyper = NULL, ip = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"variable character matched existing predictors. hyper numeric estimate mean regression coefficients. ip numeric estimate 0 1 inclusion probability target variable (Default: NULL).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"Zellner-style spike slab prior generalized linear models specified described Boom R-package. Currently supported two options work models Poisson binomial (Bernoulli) distributed errors. Two types priors can provided variable: \"coefficient\" Allows specify Gaussian priors mean coefficients model. Priors coefficients can provided via \"hyper\" parameter. Note variables prior can still regularized model. \"inclusion.probability\" vector giving prior probability inclusion specified variable. can useful prior information preference known strength . coefficients set, inclusion probability also modified default. However even knowing particular estimate beta coefficients direction, one can still provide estimate inclusion probability. words: hyperparameters 'hyper' 'ip' NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"Hugh Chipman, Edward . George, Robert E. McCulloch, M. Clyde, Dean P. Foster, Robert . Stine (2001), \"Practical Implementation Bayesian Model Selection\" Lecture Notes-Monograph Series, Vol. 38, pp. 65-134. Institute Mathematical Statistics.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new spike and slab prior for Bayesian generalized linear models — BREGPrior","text":"","code":"if (FALSE) { # Positive coefficient p1 <- BREGPrior(variable = \"forest\", hyper = 2, ip = NULL) p1 # Coefficient and direction unknown but variable def. important p2 <- BREGPrior(variable = \"forest\", hyper = NULL, ip = 1) p2 }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","title":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","text":"helper function specify several BREGPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","text":"","code":"BREGPriors(variable, hyper = NULL, ip = NULL)  # S4 method for character BREGPriors(variable, hyper = NULL, ip = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BREGPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a BREG prior — BREGPriors","text":"variable character matched existing predictors. hyper numeric estimate mean regression coefficients. ip numeric estimate 0 1 inclusion probability target variable (Default: NULL).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":null,"dir":"Reference","previous_headings":"","what":"BiodiversityDataset prototype description — BiodiversityDataset-class","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"BiodiversityDataset prototype description","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"name default name dataset character. id character unique id dataset. equation formula object containing equation dataset modelled. family family used dataset character. link link function used data character. type character type character. weight numeric containing custom weights per observation dataset. field_occurrence character name column name containing observations. data Contains observational data sf format. use_intercept logical flag whether intercepts included dataset. pseudoabsence_settings Optionally provided pseudoabsence settings.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"BiodiversityDataset$new() BiodiversityDataset$print() BiodiversityDataset$set_equation() BiodiversityDataset$get_equation() BiodiversityDataset$show_equation() BiodiversityDataset$get_id() BiodiversityDataset$get_type() BiodiversityDataset$get_column_occ() BiodiversityDataset$get_family() BiodiversityDataset$get_link() BiodiversityDataset$get_data() BiodiversityDataset$get_weight() BiodiversityDataset$show() BiodiversityDataset$get_observations() BiodiversityDataset$mask() BiodiversityDataset$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$new(   name,   id,   equation,   family,   link,   type,   weight,   field_occurrence,   data,   use_intercept,   pseudoabsence_settings )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"name default name dataset character. id character unique id dataset. equation formula object containing equation dataset modelled. family family used dataset character. link link function used data character. type character type character. weight numeric containing custom weights per observation dataset. field_occurrence character name column name containing observations. data Contains observational data sf format. use_intercept logical flag whether intercepts included dataset. pseudoabsence_settings Optionally provided pseudoabsence settings.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-set-equation-","dir":"Reference","previous_headings":"","what":"Method set_equation()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Set new equation writes formula","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$set_equation(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"x new formula object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-equation-","dir":"Reference","previous_headings":"","what":"Method get_equation()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get equation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_equation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"placeholder formula object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-show-equation-","dir":"Reference","previous_headings":"","what":"Method show_equation()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Function print equation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$show_equation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"message screen.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-id-","dir":"Reference","previous_headings":"","what":"Method get_id()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get Id within dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-type-","dir":"Reference","previous_headings":"","what":"Method get_type()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get type dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_type(short = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"short logical flag formatted shortform.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character type","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-column-occ-","dir":"Reference","previous_headings":"","what":"Method get_column_occ()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get field occurrence information","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_column_occ()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character occurence field","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-family-","dir":"Reference","previous_headings":"","what":"Method get_family()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get family","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_family()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character family dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-link-","dir":"Reference","previous_headings":"","what":"Method get_link()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get custom link function","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_link()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"character family dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get data object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_data()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"sf object data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-weight-","dir":"Reference","previous_headings":"","what":"Method get_weight()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Get weight","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_weight()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"numeric weights within dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Print input messages","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"message screen.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-get-observations-","dir":"Reference","previous_headings":"","what":"Method get_observations()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Collect info statistics number observations","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$get_observations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"numeric number observations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Convenience function mask input datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed mask","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"","code":"BiodiversityDataset$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDataset-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDataset prototype description — BiodiversityDataset-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":null,"dir":"Reference","previous_headings":"","what":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Acts container specified set BiodiversityDataset contained within. Functions provided summarize across BiodiversityDataset-class objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"can likely beautified .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"data list BiodiversityDataset objects. name default name collection character.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"BiodiversityDatasetCollection$new() BiodiversityDatasetCollection$print() BiodiversityDatasetCollection$show() BiodiversityDatasetCollection$get_types() BiodiversityDatasetCollection$get_names() BiodiversityDatasetCollection$set_data() BiodiversityDatasetCollection$get_data_object() BiodiversityDatasetCollection$get_data() BiodiversityDatasetCollection$get_coordinates() BiodiversityDatasetCollection$mask() BiodiversityDatasetCollection$rm_data() BiodiversityDatasetCollection$length() BiodiversityDatasetCollection$get_observations() BiodiversityDatasetCollection$get_equations() BiodiversityDatasetCollection$get_families() BiodiversityDatasetCollection$get_links() BiodiversityDatasetCollection$get_columns_occ() BiodiversityDatasetCollection$get_weights() BiodiversityDatasetCollection$get_ids() BiodiversityDatasetCollection$get_id_byType() BiodiversityDatasetCollection$get_id_byName() BiodiversityDatasetCollection$show_equations() BiodiversityDatasetCollection$plot() BiodiversityDatasetCollection$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$new()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$print(format = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"format logical flag whether message printed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Aliases calls print.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-types-","dir":"Reference","previous_headings":"","what":"Method get_types()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Types biodiversity datasets included ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_types(short = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"short logical flag whether types short format.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-names-","dir":"Reference","previous_headings":"","what":"Method get_names()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get names format necessary","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_names(format = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"format logical flag whether names formatted","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Add new Biodiversity dataset collection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"x character name id dataset. value BiodiversityDataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-data-object-","dir":"Reference","previous_headings":"","what":"Method get_data_object()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get specific Biodiversity dataset id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_data_object(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Returns BiodiversityDataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get biodiversity observations given dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_data(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Returns data set BiodiversityDataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-coordinates-","dir":"Reference","previous_headings":"","what":"Method get_coordinates()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get coordinates given biodiversity dataset. Else return wkt object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_coordinates(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"coordinates given object data.frame.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Convenience function mask input datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$mask(mask, inverse = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-rm-data-","dir":"Reference","previous_headings":"","what":"Method rm_data()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Remove specific biodiversity dataset id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$rm_data(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"id character given id dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Number Biodiversity Datasets connection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"numeric number datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-observations-","dir":"Reference","previous_headings":"","what":"Method get_observations()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get number observations datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_observations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"numeric number observations across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-equations-","dir":"Reference","previous_headings":"","what":"Method get_equations()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get equations datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_equations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector equations across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-families-","dir":"Reference","previous_headings":"","what":"Method get_families()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get families datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_families()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector families across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-links-","dir":"Reference","previous_headings":"","what":"Method get_links()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get custom link functions","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_links()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector link functions across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-columns-occ-","dir":"Reference","previous_headings":"","what":"Method get_columns_occ()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get fields observation columns","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_columns_occ()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector names observation columns.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-weights-","dir":"Reference","previous_headings":"","what":"Method get_weights()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get weights across datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_weights()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector weights set per dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-ids-","dir":"Reference","previous_headings":"","what":"Method get_ids()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get ids assets collection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_ids()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"list vector ids datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-id-bytype-","dir":"Reference","previous_headings":"","what":"Method get_id_byType()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Search specific biodiversity dataset type","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_id_byType(type)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"type character given data type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character id(s) datasets given type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-get-id-byname-","dir":"Reference","previous_headings":"","what":"Method get_id_byName()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Get id name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$get_id_byName(name)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"name character given name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"character id(s) datasets given name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-show-equations-","dir":"Reference","previous_headings":"","what":"Method show_equations()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Show equations datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$show_equations(msg = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"msg logical whether use print message instead.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Shows equations screen character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Plot whole collection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$plot()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"","code":"BiodiversityDatasetCollection$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDatasetCollection-class.html","id":"arguments-12","dir":"Reference","previous_headings":"","what":"Arguments","title":"BiodiversityDatasetCollection super class description — BiodiversityDatasetCollection-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Biodiversity Distribution master class — BiodiversityDistribution-class","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Base R6 class biodiversity distribution objects. Serves container supplies data functions R6 classes. Generally stores objects parameters added model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Run names() distribution object show available functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"implemented yet. implemented yet.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"background SpatRaster sf object delineating modelling extent. limits optional sf object potential extrapolation limits biodiversity BiodiversityDatasetCollection object. predictors PredictorDataset object. priors optional PriorList object. control optional Control object. latentfactors character whether latentfactors used. offset character whether methods used. log optional Log object. engine Engine object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"BiodiversityDistribution$new() BiodiversityDistribution$print() BiodiversityDistribution$show() BiodiversityDistribution$name() BiodiversityDistribution$show_background_info() BiodiversityDistribution$set_limits() BiodiversityDistribution$get_limits() BiodiversityDistribution$rm_limits() BiodiversityDistribution$get_predictor_names() BiodiversityDistribution$set_latent() BiodiversityDistribution$get_latent() BiodiversityDistribution$rm_latent() BiodiversityDistribution$get_priors() BiodiversityDistribution$set_priors() BiodiversityDistribution$set_biodiversity() BiodiversityDistribution$set_predictors() BiodiversityDistribution$set_engine() BiodiversityDistribution$get_engine() BiodiversityDistribution$rm_engine() BiodiversityDistribution$get_prior_variables() BiodiversityDistribution$set_offset() BiodiversityDistribution$get_offset() BiodiversityDistribution$rm_offset() BiodiversityDistribution$plot_offsets() BiodiversityDistribution$get_offset_type() BiodiversityDistribution$set_control() BiodiversityDistribution$get_control() BiodiversityDistribution$rm_control() BiodiversityDistribution$plot_bias() BiodiversityDistribution$get_log() BiodiversityDistribution$set_log() BiodiversityDistribution$get_extent() BiodiversityDistribution$get_extent_dimensions() BiodiversityDistribution$get_projection() BiodiversityDistribution$get_resolution() BiodiversityDistribution$rm_predictors() BiodiversityDistribution$rm_priors() BiodiversityDistribution$show_biodiversity_length() BiodiversityDistribution$show_biodiversity_equations() BiodiversityDistribution$get_biodiversity_equations() BiodiversityDistribution$get_biodiversity_types() BiodiversityDistribution$get_biodiversity_ids() BiodiversityDistribution$get_biodiversity_names() BiodiversityDistribution$plot() BiodiversityDistribution$summary() BiodiversityDistribution$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Initializes object creates BiodiversityDataset default.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$new(background, limits, biodiversity, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"background SpatRaster sf object delineating modelling extent. limits optional sf object potential extrapolation limits biodiversity BiodiversityDatasetCollection object. ... objects","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Looks returns properties contained objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"alias print","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-name-","dir":"Reference","previous_headings":"","what":"Method name()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Returns self-describing name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-background-info-","dir":"Reference","previous_headings":"","what":"Method show_background_info()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Summarizes extent projection set background","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show_background_info()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-limits-","dir":"Reference","previous_headings":"","what":"Method set_limits()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Specify new limits background","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_limits(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x list object method limit type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-limits-","dir":"Reference","previous_headings":"","what":"Method get_limits()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get provided limits set waiver","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list waiver.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-limits-","dir":"Reference","previous_headings":"","what":"Method rm_limits()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove limits set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-predictor-names-","dir":"Reference","previous_headings":"","what":"Method get_predictor_names()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Function querying predictor names existing","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_predictor_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-latent-","dir":"Reference","previous_headings":"","what":"Method set_latent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Adding latent factors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_latent(type, method = NULL, separate_spde = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"type character given type. method character method. separate_spde logical flag whether duplicate SPDE effects created.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-latent-","dir":"Reference","previous_headings":"","what":"Method get_latent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get latent factors found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_latent()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-latent-","dir":"Reference","previous_headings":"","what":"Method rm_latent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove latent factors found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_latent()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-priors-","dir":"Reference","previous_headings":"","what":"Method get_priors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get prior object found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_priors()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-priors-","dir":"Reference","previous_headings":"","what":"Method set_priors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Specify new prior object. Overwrites existing ones","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_priors(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-biodiversity-","dir":"Reference","previous_headings":"","what":"Method set_biodiversity()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Adds new biodiversity object existing empty collection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_biodiversity(id, p)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"id character id defining object. p BiodiversityDataset object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-predictors-","dir":"Reference","previous_headings":"","what":"Method set_predictors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new Predictor object object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_predictors(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x PredictorDataset predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-engine-","dir":"Reference","previous_headings":"","what":"Method set_engine()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new Engine object object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_engine(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x Engine object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-engine-","dir":"Reference","previous_headings":"","what":"Method get_engine()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Gets name current engine set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_engine()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character engine name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-engine-","dir":"Reference","previous_headings":"","what":"Method rm_engine()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Removes current engine set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_engine()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-prior-variables-","dir":"Reference","previous_headings":"","what":"Method get_prior_variables()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get prior variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_prior_variables()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character variable names priors added.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-offset-","dir":"Reference","previous_headings":"","what":"Method set_offset()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Specify new offsets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_offset(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x new SpatRaster object used offset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-offset-","dir":"Reference","previous_headings":"","what":"Method get_offset()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get offset (print name)","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_offset()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character offsets .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-offset-","dir":"Reference","previous_headings":"","what":"Method rm_offset()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove offsets found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_offset(what = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Optional character specific offsets remove.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-plot-offsets-","dir":"Reference","previous_headings":"","what":"Method plot_offsets()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Plot offset found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$plot_offsets()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-23","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"graphical element.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-offset-type-","dir":"Reference","previous_headings":"","what":"Method get_offset_type()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get offset parameters found","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-24","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_offset_type()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-24","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list offset parameters found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-control-","dir":"Reference","previous_headings":"","what":"Method set_control()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new bias control","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-25","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_control(type = \"bias\", x, method, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"type character type control object. x new bias control object. Expecting SpatRaster object. method method used create object. value bias value numeric.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-25","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-control-","dir":"Reference","previous_headings":"","what":"Method get_control()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get bias control (print name)","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-26","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_control(type = \"bias\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"type character type control object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-26","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character bias object found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-control-","dir":"Reference","previous_headings":"","what":"Method rm_control()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove bias controls found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-27","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_control()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-27","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-plot-bias-","dir":"Reference","previous_headings":"","what":"Method plot_bias()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Plot bias variable set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-28","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$plot_bias()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-28","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"graphical element.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-log-","dir":"Reference","previous_headings":"","what":"Method get_log()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Returns output filename current log object set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-29","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_log()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-29","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character output returned.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-set-log-","dir":"Reference","previous_headings":"","what":"Method set_log()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Set new log object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-30","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$set_log(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"x Log object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-30","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-extent-","dir":"Reference","previous_headings":"","what":"Method get_extent()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get extent","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-31","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_extent()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-31","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Background extent NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-extent-dimensions-","dir":"Reference","previous_headings":"","what":"Method get_extent_dimensions()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get dimensions extent background","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-32","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_extent_dimensions()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-32","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Background extent NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get projection background crs format.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-33","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-33","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Return resolution background object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-34","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-34","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"vector resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-predictors-","dir":"Reference","previous_headings":"","what":"Method rm_predictors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove predictiors. Either specific ones.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-35","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_predictors(names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-12","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"names character predictors removed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-35","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-rm-priors-","dir":"Reference","previous_headings":"","what":"Method rm_priors()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Remove priors. Either specific ones.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-36","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$rm_priors(names = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-13","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"names character priors removed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-36","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-biodiversity-length-","dir":"Reference","previous_headings":"","what":"Method show_biodiversity_length()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Show number biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-37","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show_biodiversity_length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-37","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"numeric sum biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-show-biodiversity-equations-","dir":"Reference","previous_headings":"","what":"Method show_biodiversity_equations()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Show Equations biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-38","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$show_biodiversity_equations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-38","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message screen.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-equations-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_equations()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Get equations biodiversity records","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-39","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_equations()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-39","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-types-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_types()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Query biodiversity types object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-40","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_types()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-40","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"character vector.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-ids-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_ids()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Return biodiversity dataset ids object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-41","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_ids()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-41","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list ids biodiversity datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-get-biodiversity-names-","dir":"Reference","previous_headings":"","what":"Method get_biodiversity_names()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Return character names biodiversity datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-42","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$get_biodiversity_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-42","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"list names biodiversity datasets","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Plots content class.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-43","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$plot()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-43","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"Summary function object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-44","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$summary()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"returns-44","dir":"Reference","previous_headings":"","what":"Returns","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"message.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"usage-45","dir":"Reference","previous_headings":"","what":"Usage","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"BiodiversityDistribution$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"arguments-14","dir":"Reference","previous_headings":"","what":"Arguments","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityDistribution-class.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Biodiversity Distribution master class — BiodiversityDistribution-class","text":"","code":"# Query available functions and entries background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM',mustWork = TRUE)) # Define model x <- distribution(background) #> [Setup] 2024-02-06 14:28:41.024205 | Creating distribution object... names(x) #>  [1] \".__enclos_env__\"             \"engine\"                      #>  [3] \"log\"                         \"offset\"                      #>  [5] \"latentfactors\"               \"control\"                     #>  [7] \"priors\"                      \"predictors\"                  #>  [9] \"biodiversity\"                \"limits\"                      #> [11] \"background\"                  \"clone\"                       #> [13] \"summary\"                     \"plot\"                        #> [15] \"get_biodiversity_names\"      \"get_biodiversity_ids\"        #> [17] \"get_biodiversity_types\"      \"get_biodiversity_equations\"  #> [19] \"show_biodiversity_equations\" \"show_biodiversity_length\"    #> [21] \"rm_priors\"                   \"rm_predictors\"               #> [23] \"get_resolution\"              \"get_projection\"              #> [25] \"get_extent_dimensions\"       \"get_extent\"                  #> [27] \"set_log\"                     \"get_log\"                     #> [29] \"plot_bias\"                   \"rm_control\"                  #> [31] \"get_control\"                 \"set_control\"                 #> [33] \"get_offset_type\"             \"plot_offsets\"                #> [35] \"rm_offset\"                   \"get_offset\"                  #> [37] \"set_offset\"                  \"get_prior_variables\"         #> [39] \"rm_engine\"                   \"get_engine\"                  #> [41] \"set_engine\"                  \"set_predictors\"              #> [43] \"set_biodiversity\"            \"set_priors\"                  #> [45] \"get_priors\"                  \"rm_latent\"                   #> [47] \"get_latent\"                  \"set_latent\"                  #> [49] \"get_predictor_names\"         \"rm_limits\"                   #> [51] \"get_limits\"                  \"set_limits\"                  #> [53] \"show_background_info\"        \"name\"                        #> [55] \"show\"                        \"print\"                       #> [57] \"initialize\""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Base R6 class biodiversity scenario objects. Serves container supplies data functions R6 classes functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"sets threshold method internally 'fixed'. requires \"gganimate\" package. requires set threshold() scenario object. requires set threshold prior projection.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"modelobject name model projection. modelid id model used projection. limits sf object used constraint prediction. predictors predictor object projection. constraints constraints set projection. scenarios resulting stars objects.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"BiodiversityScenario$new() BiodiversityScenario$print() BiodiversityScenario$verify() BiodiversityScenario$show() BiodiversityScenario$get_projection() BiodiversityScenario$get_resolution() BiodiversityScenario$get_model() BiodiversityScenario$get_limits() BiodiversityScenario$get_predictor_names() BiodiversityScenario$get_timeperiod() BiodiversityScenario$get_constraints() BiodiversityScenario$get_threshold() BiodiversityScenario$get_thresholdvalue() BiodiversityScenario$apply_threshold() BiodiversityScenario$set_predictors() BiodiversityScenario$set_constraints() BiodiversityScenario$get_simulation() BiodiversityScenario$set_simulation() BiodiversityScenario$get_predictors() BiodiversityScenario$rm_predictors() BiodiversityScenario$get_data() BiodiversityScenario$set_data() BiodiversityScenario$plot() BiodiversityScenario$plot_threshold() BiodiversityScenario$plot_migclim() BiodiversityScenario$plot_animation() BiodiversityScenario$plot_relative_change() BiodiversityScenario$summary() BiodiversityScenario$summary_beforeafter() BiodiversityScenario$calc_scenarios_slope() BiodiversityScenario$mask() BiodiversityScenario$get_centroid() BiodiversityScenario$save() BiodiversityScenario$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$new()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Print names properties scenarios.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-verify-","dir":"Reference","previous_headings":"","what":"Method verify()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Verify set Model exist check self-validity","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$verify()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Show name Model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Model objectname","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get projection projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"sf object geographic projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get resultion projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"numeric indication resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-model-","dir":"Reference","previous_headings":"","what":"Method get_model()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get actual model used projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_model()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"DistributionModel object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-limits-","dir":"Reference","previous_headings":"","what":"Method get_limits()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get provided projection limits set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"sf object NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-predictor-names-","dir":"Reference","previous_headings":"","what":"Method get_predictor_names()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get names predictors scenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_predictor_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character vector names.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-timeperiod-","dir":"Reference","previous_headings":"","what":"Method get_timeperiod()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get time period projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_timeperiod(what = \"range\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character whether full time period just range returned.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"time period start end.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-constraints-","dir":"Reference","previous_headings":"","what":"Method get_constraints()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get constrains model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_constraints()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list constraints within scenario.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-threshold-","dir":"Reference","previous_headings":"","what":"Method get_threshold()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get thresholds specified.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_threshold()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list method value threshold.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-thresholdvalue-","dir":"Reference","previous_headings":"","what":"Method get_thresholdvalue()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Duplicate function internal consistency return threshold","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_thresholdvalue()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list method value threshold.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-apply-threshold-","dir":"Reference","previous_headings":"","what":"Method apply_threshold()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Apply new threshold projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$apply_threshold(tr = new_waiver())"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"tr numeric value new threshold.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-predictors-","dir":"Reference","previous_headings":"","what":"Method set_predictors()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set new predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_predictors(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x PredictorDataset object supplied.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-constraints-","dir":"Reference","previous_headings":"","what":"Method set_constraints()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set new constrains","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_constraints(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x SpatRaster object added constraint.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-simulation-","dir":"Reference","previous_headings":"","what":"Method get_simulation()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get simulation options parameters gound","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_simulation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"list parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-simulation-","dir":"Reference","previous_headings":"","what":"Method set_simulation()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set simulation objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_simulation(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x new simulation entries options list set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-predictors-","dir":"Reference","previous_headings":"","what":"Method get_predictors()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get Predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_predictors()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"predictor dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-rm-predictors-","dir":"Reference","previous_headings":"","what":"Method rm_predictors()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Remove predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$rm_predictors(names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"names character vector names","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get scenario predictions data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_data(what = \"scenarios\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character vector names ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Set new data object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$set_data(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"x new data object measuing scenarios.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot predictions made .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot(what = \"suitability\", which = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character describing layers plotted. numeric subset specific time steps. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-threshold-","dir":"Reference","previous_headings":"","what":"Method plot_threshold()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Convenience function plot thresholds set","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_threshold(which = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"numeric subset specific time steps.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-23","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-migclim-","dir":"Reference","previous_headings":"","what":"Method plot_migclim()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot Migclim results existing.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-24","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_migclim()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-24","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-animation-","dir":"Reference","previous_headings":"","what":"Method plot_animation()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot animation scenarios possible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-25","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_animation(what = \"suitability\", fname = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character describing layers plotted. fname optional filename write result.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-25","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-plot-relative-change-","dir":"Reference","previous_headings":"","what":"Method plot_relative_change()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Plot relative change baseline projected thresholds","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-26","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$plot_relative_change(   position = NULL,   variable = \"mean\",   plot = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"position layer plotted variable character variable plotted plot logical flag whether plot results return object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-26","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"graphical representation SpatRaster.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarize change layers timesteps","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-27","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$summary(   layer = \"threshold\",   plot = FALSE,   relative = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-12","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"layer character variable plotted plot logical flag whether plot results return coefficients. relative logical coefficients converted relative change.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-27","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarized coefficients data.frame","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-summary-beforeafter-","dir":"Reference","previous_headings":"","what":"Method summary_beforeafter()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarize -change first last layer.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-28","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$summary_beforeafter()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-28","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Summarized coefficients data.frame","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-calc-scenarios-slope-","dir":"Reference","previous_headings":"","what":"Method calc_scenarios_slope()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Calculate slopes across projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-29","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$calc_scenarios_slope(   what = \"suitability\",   plot = TRUE,   oftype = \"stars\" )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-13","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"character layer plotted (default: \"suitability\"). plot logical flag whether plot results return coefficients. oftype character output type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-29","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"SpatRaster layer stars object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Convenience function mask input projections.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-30","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-14","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-30","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-get-centroid-","dir":"Reference","previous_headings":"","what":"Method get_centroid()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Get centroids projection layers","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-31","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$get_centroid(patch = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-15","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"patch logical centroid calculated weighted values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-31","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Returns sf object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-save-","dir":"Reference","previous_headings":"","what":"Method save()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Save object output somewhere","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-32","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$save(fname, type = \"tif\", dt = \"FLT4S\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-16","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"fname output filename character. type format character. Matched list supported formats. dt datatype used, float64","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"returns-32","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"Saved spatial prediction drive.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"usage-33","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"","code":"BiodiversityScenario$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/BiodiversityScenario-class.html","id":"arguments-17","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for a biodiversity scenario from a trained model — BiodiversityScenario-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Class for the trained Model object — DistributionModel-class","title":"Class for the trained Model object — DistributionModel-class","text":"trained Models inherit options plus additional ones defined engine inference.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Class for the trained Model object — DistributionModel-class","text":"pretified commands outsourced.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Class for the trained Model object — DistributionModel-class","text":"id character id trained model name description model character. model list containing input datasets parameters model. settings Settings object information inference. fits list containing prediction fitted model.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Class for the trained Model object — DistributionModel-class","text":"DistributionModel$new() DistributionModel$get_name() DistributionModel$print() DistributionModel$show() DistributionModel$plot() DistributionModel$plot_threshold() DistributionModel$show_duration() DistributionModel$summary() DistributionModel$effects() DistributionModel$get_equation() DistributionModel$get_data() DistributionModel$set_data() DistributionModel$get_thresholdvalue() DistributionModel$get_thresholdtype() DistributionModel$show_rasters() DistributionModel$get_projection() DistributionModel$get_resolution() DistributionModel$rm_threshold() DistributionModel$calc_suitabilityindex() DistributionModel$get_centroid() DistributionModel$has_limits() DistributionModel$has_offset() DistributionModel$mask() DistributionModel$save() DistributionModel$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Class for the trained Model object — DistributionModel-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$new(name)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"name description model character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-name-","dir":"Reference","previous_headings":"","what":"Method get_name()","title":"Class for the trained Model object — DistributionModel-class","text":"Return name model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"character model name used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Class for the trained Model object — DistributionModel-class","text":"Print names summarizes model within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Class for the trained Model object — DistributionModel-class","text":"Show name Model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"character run name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"Class for the trained Model object — DistributionModel-class","text":"Plots prediction found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$plot(what = \"mean\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"character specific layer plotted.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"graphical representation prediction","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-plot-threshold-","dir":"Reference","previous_headings":"","what":"Method plot_threshold()","title":"Class for the trained Model object — DistributionModel-class","text":"Plots thresholded prediction found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$plot_threshold(what = 1)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"character numeric layer plotted.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"graphical representation thresholded prediction found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-show-duration-","dir":"Reference","previous_headings":"","what":"Method show_duration()","title":"Class for the trained Model object — DistributionModel-class","text":"Show model run time settings exist","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$show_duration()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"numeric estimate duration took fit models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Class for the trained Model object — DistributionModel-class","text":"Get effects importance tables model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$summary(obj = \"fit_best\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"obj character object return.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"data.frame summarizing model, usually coefficient.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-effects-","dir":"Reference","previous_headings":"","what":"Method effects()","title":"Class for the trained Model object — DistributionModel-class","text":"Generic plotting function effect plots","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$effects(x = \"fit_best\", what = \"fixed\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"x character object question. character type coefficients. ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"graphical representation coefficents.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-equation-","dir":"Reference","previous_headings":"","what":"Method get_equation()","title":"Class for the trained Model object — DistributionModel-class","text":"Get equation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_equation()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"formula inferred model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"Class for the trained Model object — DistributionModel-class","text":"Get specific fit Model","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_data(x = \"prediction\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"x character stating returned.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"SpatRaster object prediction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"Class for the trained Model object — DistributionModel-class","text":"Set new fit Model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"x name new fit. value SpatRaster layer inserted.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-thresholdvalue-","dir":"Reference","previous_headings":"","what":"Method get_thresholdvalue()","title":"Class for the trained Model object — DistributionModel-class","text":"Get threshold value calculated","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_thresholdvalue()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"numeric threshold value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-thresholdtype-","dir":"Reference","previous_headings":"","what":"Method get_thresholdtype()","title":"Class for the trained Model object — DistributionModel-class","text":"Get threshold type format calculated.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_thresholdtype()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"vector character method numeric threshold value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-show-rasters-","dir":"Reference","previous_headings":"","what":"Method show_rasters()","title":"Class for the trained Model object — DistributionModel-class","text":"List rasters object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$show_rasters()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"vector logical flags various objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"Class for the trained Model object — DistributionModel-class","text":"Get projection background.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"geographic projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"Class for the trained Model object — DistributionModel-class","text":"Get resolution projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"numeric estimates distribution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-rm-threshold-","dir":"Reference","previous_headings":"","what":"Method rm_threshold()","title":"Class for the trained Model object — DistributionModel-class","text":"Remove calculated thresholds","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$rm_threshold()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-calc-suitabilityindex-","dir":"Reference","previous_headings":"","what":"Method calc_suitabilityindex()","title":"Class for the trained Model object — DistributionModel-class","text":"Calculate suitability index given projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$calc_suitabilityindex(method = \"normalize\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"method method used normalization.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Class for the trained Model object — DistributionModel-class","text":"Methods can either normalized minimum maximum. relative total using sumof values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Returns SpatRaster.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-get-centroid-","dir":"Reference","previous_headings":"","what":"Method get_centroid()","title":"Class for the trained Model object — DistributionModel-class","text":"Get centroids prediction layers","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$get_centroid(patch = FALSE, layer = \"mean\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"patch logical centroid calculated weighted values. layer character layer use.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-19","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Returns sf object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-has-limits-","dir":"Reference","previous_headings":"","what":"Method has_limits()","title":"Class for the trained Model object — DistributionModel-class","text":"Logical indication prediction limited.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-20","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$has_limits()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-20","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"logical flag.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-has-offset-","dir":"Reference","previous_headings":"","what":"Method has_offset()","title":"Class for the trained Model object — DistributionModel-class","text":"offset used?","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-21","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$has_offset()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-21","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"logical flag.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"Class for the trained Model object — DistributionModel-class","text":"Convenience function mask input datasets.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-22","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed mask","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-22","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-save-","dir":"Reference","previous_headings":"","what":"Method save()","title":"Class for the trained Model object — DistributionModel-class","text":"Save prediction output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-23","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$save(fname, type = \"gtif\", dt = \"FLT4S\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-10","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"fname output filename character. type format character. Matched list supported formats. dt datatype used, float64","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"returns-23","dir":"Reference","previous_headings":"","what":"Returns","title":"Class for the trained Model object — DistributionModel-class","text":"Saved spatial prediction drive.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Class for the trained Model object — DistributionModel-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"usage-24","dir":"Reference","previous_headings":"","what":"Usage","title":"Class for the trained Model object — DistributionModel-class","text":"","code":"DistributionModel$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/DistributionModel-class.html","id":"arguments-11","dir":"Reference","previous_headings":"","what":"Arguments","title":"Class for the trained Model object — DistributionModel-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine class description — Engine-class","title":"Engine class description — Engine-class","text":"Basic object engine, engines inherit .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Engine class description — Engine-class","text":"engine class name engine. name name engine data data parameters necessary make engine work.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Engine class description — Engine-class","text":"Engine$new() Engine$print() Engine$show() Engine$get_class() Engine$get_data() Engine$list_data() Engine$set_data() Engine$get_self() Engine$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Engine class description — Engine-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$new(engine, name)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"engine class name engine. name name engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Engine class description — Engine-class","text":"Print Engine name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Engine class description — Engine-class","text":"Aliases calls print.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-get-class-","dir":"Reference","previous_headings":"","what":"Method get_class()","title":"Engine class description — Engine-class","text":"Get class description","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$get_class()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"character class saved engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"Engine class description — Engine-class","text":"Get specific data engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$get_data(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"x respecified data added engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"list data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-list-data-","dir":"Reference","previous_headings":"","what":"Method list_data()","title":"Engine class description — Engine-class","text":"List data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$list_data()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"character vector data entries.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"Engine class description — Engine-class","text":"Set data engine","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"x character name id dataset. value new list parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-get-self-","dir":"Reference","previous_headings":"","what":"Method get_self()","title":"Engine class description — Engine-class","text":"Dummy function get self object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$get_self()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Engine class description — Engine-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Engine class description — Engine-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine class description — Engine-class","text":"","code":"Engine$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Engine-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine class description — Engine-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Monotonic constrained priors for boosted regressions — GDBPrior","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"Monotonic constrains gradient descent boosting models work way priors specific coefficient magnitude importance specified. Rather monotonic constraints enforce specific directionality regression coefficients instance coefficient positive negative. Important: Specifying monotonic constrain engine_gdb guarantee variable retained model can still regularized .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"","code":"GDBPrior(variable, hyper = \"increasing\", ...)  # S4 method for character GDBPrior(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"variable character matched existing predictors variables. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'positive', 'negative' 'none'. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"Similar priors can also defined engine_xgboost via XGBPrior().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Monotonic constrained priors for boosted regressions — GDBPrior","text":"Hofner, B., Müller, J., & Hothorn, T. (2011). Monotonicity‐constrained species distribution models. Ecology, 92(10), 1895-1901.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","title":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","text":"helper function specify several GLMNETPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","text":"","code":"GDBPriors(variable, hyper = \"increasing\", ...)  # S4 method for character GDBPriors(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GDBPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a GDB prior — GDBPriors","text":"variable character matched existing predictors variables. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'positive', 'negative' 'none'. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Regression penalty priors for GLMNET — GLMNETPrior","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"engine_glmnet engine support priors typical sense, however possible specify called penalty factors well lower upper limits variables model. default penalty multiplier 1 coefficient X covariate, .e. coefficients penalized equally informed intersection absence information covariates. contrast variable penalty.factor equal 0 penalized . addition, possible specifiy lower upper limit specific coefficients, constrain certain range. default ranges set -Inf Inf respectively, can reset specific value range altering \"lims\" (see examples). regularized regression supports options priors, check Bayesian engine_breg.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"","code":"GLMNETPrior(variable, hyper = 0, lims = c(-Inf, Inf), ...)  # S4 method for character GLMNETPrior(variable, hyper = 0, lims = c(-Inf, Inf), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"variable character variable passed prior object. hyper numeric value 0 1 state penalization factor. default set 0, implying \"variable\" provided regularized . lims numeric vector lower upper limits coefficient (Default: c(-Inf, Inf)). ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Regression penalty priors for GLMNET — GLMNETPrior","text":"","code":"if (FALSE) { # Retain variable p1 <- GLMNETPrior(variable = \"forest\", hyper = 0) p1 # Smaller chance to be regularized p2 <- GLMNETPrior(variable = \"forest\", hyper = 0.2, lims = c(0, Inf)) p2 }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","title":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","text":"helper function specify several GLMNETPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","text":"","code":"GLMNETPriors(variable, hyper = 0, lims = c(-Inf, Inf))  # S4 method for character GLMNETPriors(variable, hyper = 0, lims = c(-Inf, Inf))"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/GLMNETPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for a GLMNET prior — GLMNETPriors","text":"variable character variable passed prior object. hyper numeric value 0 1 state penalization factor. default set 0, implying \"variable\" provided regularized . lims numeric vector lower upper limits coefficient (Default: c(-Inf, Inf)).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new INLA prior — INLAPrior","title":"Create a new INLA prior — INLAPrior","text":"fixed random effect INLA supports range different priors exponential distributions. Currently supported INLA ibis.iSDM following priors can specified via \"type\": \"normal\" \"gaussian\": Priors normal distributed set specified variable. Required parameters mean precision estimate provided \"hyper\". Note precision equivalent (rather inverse) typical standard deviation specified Gaussian priors. Defaults set mean 0 precision 0.001. \"clinear\": Prior places constraint linear coefficients model coefficient specified interval \"c(lower,upper)\". Specified hyper values can negative, positive infinite. \"spde\", specifically 'prior.range' 'prior.sigma': Specification penalized complexity priors can added SPDE spatial random effect added via add_latent_spatial(). range penalized complexity prior can specified 'prior.range' uncertainty via 'prior.sigma' supplied options 'type' 'hyper'. priors available INLA  names(INLA::inla.models()$prior) )  might also work, tested!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new INLA prior — INLAPrior","text":"","code":"INLAPrior(variable, type = \"normal\", hyper = c(0, 0.001), ...)  # S4 method for character,character INLAPrior(variable, type = \"normal\", hyper = c(0, 0.001), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new INLA prior — INLAPrior","text":"variable character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper-parameters. See description. default values set mean 0 precision 0.001. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create a new INLA prior — INLAPrior","text":"Compared engines, INLA unfortunately support priors related stringent parameter regularization Laplace Horseshoe priors, limits capability engine_inla regularization. said many default uninformative priors act already regularize coefficients degree.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new INLA prior — INLAPrior","text":"Rue, H., Riebler, ., Sørbye, S. H., Illian, J. B., Simpson, D. P., & Lindgren, F. K. (2017). Bayesian computing INLA: review. Annual Review Statistics Application, 4, 395-421. Simpson, D., Rue, H., Riebler, ., Martins, T. G., & Sørbye, S. H. (2017). Penalising model component complexity: principled, practical approach constructing priors. Statistical science, 32(1), 1-28.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","title":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","text":"helper function specify several INLAPrior objects hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","text":"","code":"INLAPriors(variables, type, hyper = c(0, 0.001), ...)  # S4 method for vector,character INLAPriors(variables, type, hyper = c(0, 0.001), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/INLAPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables and types are supplied for INLA — INLAPriors","text":"variables vector character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper-parameters. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Log prototype. — Log-class","title":"Log prototype. — Log-class","text":"Basic R6 object Log, Log inherit ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Log prototype. — Log-class","text":"filename character log stored. output log content.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Log prototype. — Log-class","text":"Log$new() Log$print() Log$open() Log$close() Log$get_filename() Log$set_filename() Log$delete() Log$open_system() Log$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Log prototype. — Log-class","text":"Initializes object specifies default parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$new(filename, output)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"filename character log stored. output log content.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Log prototype. — Log-class","text":"Print message filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-open-","dir":"Reference","previous_headings":"","what":"Method open()","title":"Log prototype. — Log-class","text":"Opens connection output filename.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$open(type = c(\"output\", \"message\"))"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"type character vector output types.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-close-","dir":"Reference","previous_headings":"","what":"Method close()","title":"Log prototype. — Log-class","text":"Closes connection output file","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$close()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-get-filename-","dir":"Reference","previous_headings":"","what":"Method get_filename()","title":"Log prototype. — Log-class","text":"Get output filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$get_filename()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"character filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-set-filename-","dir":"Reference","previous_headings":"","what":"Method set_filename()","title":"Log prototype. — Log-class","text":"Set new output filename","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$set_filename(value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"value character new filename.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-delete-","dir":"Reference","previous_headings":"","what":"Method delete()","title":"Log prototype. — Log-class","text":"Delete log file","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$delete()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-open-system-","dir":"Reference","previous_headings":"","what":"Method open_system()","title":"Log prototype. — Log-class","text":"Open log system viewer","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$open_system()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Log prototype. — Log-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Log prototype. — Log-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Log prototype. — Log-class","text":"","code":"Log$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Log-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Log prototype. — Log-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":null,"dir":"Reference","previous_headings":"","what":"PredictorDataset class description — PredictorDataset-class","title":"PredictorDataset class description — PredictorDataset-class","text":"class describes PredictorDataset used store covariates within.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"PredictorDataset class description — PredictorDataset-class","text":"id id collection character. data predictor dataset usually SpatRaster. name name object. timeperiod timeperiod field","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"PredictorDataset class description — PredictorDataset-class","text":"PredictorDataset$new() PredictorDataset$print() PredictorDataset$get_name() PredictorDataset$get_id() PredictorDataset$get_names() PredictorDataset$get_predictor_names() PredictorDataset$get_data() PredictorDataset$get_time() PredictorDataset$get_projection() PredictorDataset$get_resolution() PredictorDataset$crop_data() PredictorDataset$mask() PredictorDataset$set_data() PredictorDataset$rm_data() PredictorDataset$show() PredictorDataset$summary() PredictorDataset$has_derivates() PredictorDataset$length() PredictorDataset$plot() PredictorDataset$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"PredictorDataset class description — PredictorDataset-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$new(id, data, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"id id collection character. data predictor dataset usually SpatRaster. ... parameters found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"PredictorDataset class description — PredictorDataset-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$print(format = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"format logical flag whether message printed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-name-","dir":"Reference","previous_headings":"","what":"Method get_name()","title":"PredictorDataset class description — PredictorDataset-class","text":"Return name object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Default character name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-id-","dir":"Reference","previous_headings":"","what":"Method get_id()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get Id object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Default character name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-names-","dir":"Reference","previous_headings":"","what":"Method get_names()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get names data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"character names data value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-predictor-names-","dir":"Reference","previous_headings":"","what":"Method get_predictor_names()","title":"PredictorDataset class description — PredictorDataset-class","text":"Alias get_names","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_predictor_names()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"character names data value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-data-","dir":"Reference","previous_headings":"","what":"Method get_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get specific dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_data(df = FALSE, na.rm = TRUE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"df logical whether data returned data.frame. na.rm logical NA removed data.frame. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"SpatRaster data.frame.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-time-","dir":"Reference","previous_headings":"","what":"Method get_time()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get time dimension object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_time(...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"vector time dimension dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-projection-","dir":"Reference","previous_headings":"","what":"Method get_projection()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get Projection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_projection()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"vector geographical projection object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-get-resolution-","dir":"Reference","previous_headings":"","what":"Method get_resolution()","title":"PredictorDataset class description — PredictorDataset-class","text":"Get Resolution","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$get_resolution()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"numeric vector spatial resolution data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-crop-data-","dir":"Reference","previous_headings":"","what":"Method crop_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Utility function clip predictor dataset another dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$crop_data(pol)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"pol sf object used cropping data","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisibile TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-mask-","dir":"Reference","previous_headings":"","what":"Method mask()","title":"PredictorDataset class description — PredictorDataset-class","text":"Utility function mask predictor dataset another dataset","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$mask(mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"mask SpatRaster sf object. inverse logical flag inverse masked instead. ... parameters passed masking.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-set-data-","dir":"Reference","previous_headings":"","what":"Method set_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Add new Predictor dataset collection","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$set_data(x, value)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"x character new name stored. value new SpatRaster object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-rm-data-","dir":"Reference","previous_headings":"","what":"Method rm_data()","title":"PredictorDataset class description — PredictorDataset-class","text":"Remove specific Predictor name","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$rm_data(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"x character predictor name removed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"PredictorDataset class description — PredictorDataset-class","text":"Alias print method","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"Invisible","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"PredictorDataset class description — PredictorDataset-class","text":"Collect info statistics optional decimals","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$summary(digits = 2)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-8","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"digits numeric Giving rounding precision","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-15","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"data.frame summarizing data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-has-derivates-","dir":"Reference","previous_headings":"","what":"Method has_derivates()","title":"PredictorDataset class description — PredictorDataset-class","text":"Indication predictors derivates outers","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-16","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$has_derivates()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-16","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"logical flag.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"PredictorDataset class description — PredictorDataset-class","text":"Number Predictors object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-17","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-17","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"numeric estimate","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-plot-","dir":"Reference","previous_headings":"","what":"Method plot()","title":"PredictorDataset class description — PredictorDataset-class","text":"Basic Plotting function","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-18","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$plot()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"returns-18","dir":"Reference","previous_headings":"","what":"Returns","title":"PredictorDataset class description — PredictorDataset-class","text":"graphical interpretation predictors object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"PredictorDataset class description — PredictorDataset-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"usage-19","dir":"Reference","previous_headings":"","what":"Usage","title":"PredictorDataset class description — PredictorDataset-class","text":"","code":"PredictorDataset$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PredictorDataset-class.html","id":"arguments-9","dir":"Reference","previous_headings":"","what":"Arguments","title":"PredictorDataset class description — PredictorDataset-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Base Prior class — Prior-class","title":"Base Prior class — Prior-class","text":"class sets base class priors inherited priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Base Prior class — Prior-class","text":"Defines Prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Base Prior class — Prior-class","text":"functionality likely deprecated checks superseeded.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Base Prior class — Prior-class","text":"id character id prior. name character name prior. type character type prior. variable character variable name prior. distribution character distribution prior relevant. value numeric character prior value, e.g. hyper-parameters. prob Another numeric entry prior field. inclusion probability. lims limitation lower upper bounds numeric value.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Base Prior class — Prior-class","text":"Prior$new() Prior$print() Prior$validate() Prior$get() Prior$set() Prior$get_id() Prior$get_name() Prior$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Base Prior class — Prior-class","text":"Initializes object prepared various prior variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$new(   id,   name,   variable,   value,   type = NULL,   distribution = NULL,   prob = NULL,   lims = NULL )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"id character id prior. name character name prior. variable character variable name prior. value numeric character prior value, e.g. hyper-parameters. type character type prior. distribution character distribution prior relevant. prob Another numeric entry prior field. inclusion probability. lims limitation lower upper bounds numeric value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Base Prior class — Prior-class","text":"Print prior type variable.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-validate-","dir":"Reference","previous_headings":"","what":"Method validate()","title":"Base Prior class — Prior-class","text":"Generic validation function provided value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$validate(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"x new prior value.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-get-","dir":"Reference","previous_headings":"","what":"Method get()","title":"Base Prior class — Prior-class","text":"Get prior values","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$get(what = \"value\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"character entry returned (Default: value).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-set-","dir":"Reference","previous_headings":"","what":"Method set()","title":"Base Prior class — Prior-class","text":"Set prior","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$set(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"x new prior value numeric character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-get-id-","dir":"Reference","previous_headings":"","what":"Method get_id()","title":"Base Prior class — Prior-class","text":"Get specific ID prior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$get_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"character id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-get-name-","dir":"Reference","previous_headings":"","what":"Method get_name()","title":"Base Prior class — Prior-class","text":"Get Name object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$get_name()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Base Prior class — Prior-class","text":"Returns character class name.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Base Prior class — Prior-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Base Prior class — Prior-class","text":"","code":"Prior$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Prior-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"Base Prior class — Prior-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":null,"dir":"Reference","previous_headings":"","what":"List of Priors supplied to an class — PriorList-class","title":"List of Priors supplied to an class — PriorList-class","text":"class represents collection Prior objects. provides methods accessing, adding removing priors list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"List of Priors supplied to an class — PriorList-class","text":"PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"List of Priors supplied to an class — PriorList-class","text":"priors list Prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"List of Priors supplied to an class — PriorList-class","text":"PriorList$new() PriorList$print() PriorList$show() PriorList$length() PriorList$ids() PriorList$varnames() PriorList$classes() PriorList$types() PriorList$exists() PriorList$add() PriorList$get() PriorList$collect() PriorList$rm() PriorList$summary() PriorList$combine() PriorList$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"List of Priors supplied to an class — PriorList-class","text":"Initializes object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$new(priors)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"priors list Prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"List of Priors supplied to an class — PriorList-class","text":"Print summary statistics","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"List of Priors supplied to an class — PriorList-class","text":"Aliases calls print.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"List of Priors supplied to an class — PriorList-class","text":"Number priors object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"numeric number priors set","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-ids-","dir":"Reference","previous_headings":"","what":"Method ids()","title":"List of Priors supplied to an class — PriorList-class","text":"Ids prior objects","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$ids()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"list ids priors objects query","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-varnames-","dir":"Reference","previous_headings":"","what":"Method varnames()","title":"List of Priors supplied to an class — PriorList-class","text":"Variable names priors object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$varnames()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character list variable names priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-classes-","dir":"Reference","previous_headings":"","what":"Method classes()","title":"List of Priors supplied to an class — PriorList-class","text":"Function return classes contained priors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$classes()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character list class names priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-types-","dir":"Reference","previous_headings":"","what":"Method types()","title":"List of Priors supplied to an class — PriorList-class","text":"Get types contained priors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$types()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character list type names priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-exists-","dir":"Reference","previous_headings":"","what":"Method exists()","title":"List of Priors supplied to an class — PriorList-class","text":"certain variable type combination exist prior ?","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$exists(variable, type = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"variable character variable name. type character type.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-8","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"character id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-add-","dir":"Reference","previous_headings":"","what":"Method add()","title":"List of Priors supplied to an class — PriorList-class","text":"Add new prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-9","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$add(p)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"p Prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-9","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-get-","dir":"Reference","previous_headings":"","what":"Method get()","title":"List of Priors supplied to an class — PriorList-class","text":"Get specific prior values list set","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-10","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$get(variable, type = NULL, what = \"value\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-3","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"variable character variable name. type character type name character specific entry return (Default: prior value).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-10","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-collect-","dir":"Reference","previous_headings":"","what":"Method collect()","title":"List of Priors supplied to an class — PriorList-class","text":"Collect priors given id multiple.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-11","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$collect(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-4","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"id character prior id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-11","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-rm-","dir":"Reference","previous_headings":"","what":"Method rm()","title":"List of Priors supplied to an class — PriorList-class","text":"Remove set prior id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-12","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$rm(id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-5","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"id character prior id.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-12","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"List of Priors supplied to an class — PriorList-class","text":"Summary function lists priors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-13","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$summary()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-13","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"data.frame summarized priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-combine-","dir":"Reference","previous_headings":"","what":"Method combine()","title":"List of Priors supplied to an class — PriorList-class","text":"Combining function combine PriorList another new one","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-14","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$combine(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-6","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"x new PriorList object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"returns-14","dir":"Reference","previous_headings":"","what":"Returns","title":"List of Priors supplied to an class — PriorList-class","text":"Invisible TRUE","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"List of Priors supplied to an class — PriorList-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"usage-15","dir":"Reference","previous_headings":"","what":"Usage","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"PriorList$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"arguments-7","dir":"Reference","previous_headings":"","what":"Arguments","title":"List of Priors supplied to an class — PriorList-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/PriorList-class.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"List of Priors supplied to an class — PriorList-class","text":"","code":"if (FALSE) { priors(     INLAPrior('var1','normal',c(0,0.1)),     INLAPrior('var2','normal',c(0,0.1))    ) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new STAN prior — STANPrior","title":"Create a new STAN prior — STANPrior","text":"Function create new prior engine_stan models. Priors currently can set specific environmental predictors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new STAN prior — STANPrior","text":"","code":"STANPrior(variable, type, hyper = c(0, 2), ...)  # S4 method for character,character STANPrior(variable, type, hyper = c(0, 2), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new STAN prior — STANPrior","text":"variable character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper parameters. First entry treated mean (Default: 0), second standard variation (Default: 2) Gaussian distribution respective coefficient. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new STAN prior — STANPrior","text":"Lemoine, N. P. (2019). Moving beyond noninformative priors: choose weakly informative priors Bayesian analyses. Oikos, 128(7), 912-928. Carpenter, B., Gelman, ., Hoffman, M. D., Lee, D., Goodrich, B., Betancourt, M., ... & Riddell, . (2017). Stan: probabilistic programming language. Journal statistical software, 76(1), 1-32.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new STAN prior — STANPrior","text":"","code":"if (FALSE) {  pp <- STANPrior(\"forest\", \"normal\", c(0,1)) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables and types are supplied for STAN — STANPriors","title":"Helper function when multiple variables and types are supplied for STAN — STANPriors","text":"helper function specify several STANPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables and types are supplied for STAN — STANPriors","text":"","code":"STANPriors(variables, type, hyper = c(0, 2), ...)  # S4 method for vector,character STANPriors(variables, type, hyper = c(0, 2), ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/STANPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables and types are supplied for STAN — STANPriors","text":"variables vector character matched existing predictors latent effects. type character specifying type prior set. hyper vector numeric values used hyper-parameters. ... Variables passed prior object","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":null,"dir":"Reference","previous_headings":"","what":"Prototype for model settings object — Settings-class","title":"Prototype for model settings object — Settings-class","text":"Basic R6 object Settings object, List stores settings used related model training.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"public-fields","dir":"Reference","previous_headings":"","what":"Public fields","title":"Prototype for model settings object — Settings-class","text":"name default name settings character. modelid character model id belongs . data list contained settings.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"public-methods","dir":"Reference","previous_headings":"","what":"Public methods","title":"Prototype for model settings object — Settings-class","text":"Settings$new() Settings$print() Settings$show() Settings$length() Settings$duration() Settings$summary() Settings$get() Settings$set() Settings$clone()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-new-","dir":"Reference","previous_headings":"","what":"Method new()","title":"Prototype for model settings object — Settings-class","text":"Initializes object creates empty list","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$new()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"NULL","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-print-","dir":"Reference","previous_headings":"","what":"Method print()","title":"Prototype for model settings object — Settings-class","text":"Print names properties Biodiversity datasets contained within","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-1","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$print()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-1","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"message screen","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-show-","dir":"Reference","previous_headings":"","what":"Method show()","title":"Prototype for model settings object — Settings-class","text":"Shows name settings","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-2","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$show()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-2","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"character name settings.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-length-","dir":"Reference","previous_headings":"","what":"Method length()","title":"Prototype for model settings object — Settings-class","text":"Number options","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-3","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$length()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-3","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"numeric number options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-duration-","dir":"Reference","previous_headings":"","what":"Method duration()","title":"Prototype for model settings object — Settings-class","text":"Computation duration convenience function","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-4","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$duration()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-4","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"amount time passed model fitting found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-summary-","dir":"Reference","previous_headings":"","what":"Method summary()","title":"Prototype for model settings object — Settings-class","text":"Summary call contained parameters","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-5","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$summary()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-5","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"list parameters object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-get-","dir":"Reference","previous_headings":"","what":"Method get()","title":"Prototype for model settings object — Settings-class","text":"Get specific setting","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-6","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$get(what)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Prototype for model settings object — Settings-class","text":"character respective setting.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-6","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"setting found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-set-","dir":"Reference","previous_headings":"","what":"Method set()","title":"Prototype for model settings object — Settings-class","text":"Set new settings","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-7","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$set(what, x, copy = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"arguments-1","dir":"Reference","previous_headings":"","what":"Arguments","title":"Prototype for model settings object — Settings-class","text":"character name new settings. x new setting stored. Can object. copy logical whether new settings object created.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"returns-7","dir":"Reference","previous_headings":"","what":"Returns","title":"Prototype for model settings object — Settings-class","text":"setting found object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"method-clone-","dir":"Reference","previous_headings":"","what":"Method clone()","title":"Prototype for model settings object — Settings-class","text":"objects class cloneable method.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"usage-8","dir":"Reference","previous_headings":"","what":"Usage","title":"Prototype for model settings object — Settings-class","text":"","code":"Settings$clone(deep = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/Settings-class.html","id":"arguments-2","dir":"Reference","previous_headings":"","what":"Arguments","title":"Prototype for model settings object — Settings-class","text":"deep Whether make deep clone.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new monotonic prior for boosted regressions — XGBPrior","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"Function include prior information monotonic constrain extreme gradient descent boosting model engine_xgboost. Monotonic priors enforce directionality direction certain variables, however specifying monotonic constrain guarantee variable regularized model fitting.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"","code":"XGBPrior(variable, hyper = \"increasing\", ...)  # S4 method for character,character XGBPrior(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"variable character matched existing predictors latent effects. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'none'. ... Variables passed prior object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"Chen, T., , T., Benesty, M., Khotilovich, V., Tang, Y., & Cho, H. (2015). Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4), 1-4.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPrior.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new monotonic prior for boosted regressions — XGBPrior","text":"","code":"if (FALSE) {  pp <- XGBPrior(\"forest\", \"increasing\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPriors.html","id":null,"dir":"Reference","previous_headings":"","what":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","title":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","text":"helper function specify several XGBPrior hyper-parameters, different variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPriors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","text":"","code":"XGBPriors(variable, hyper = \"increasing\", ...)  # S4 method for character XGBPriors(variable, hyper = \"increasing\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/XGBPriors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Helper function when multiple variables are supplied for XGBOOST — XGBPriors","text":"variable character matched existing predictors latent effects. hyper character object describing type constrain. Available options 'increasing', 'decreasing', 'convex', 'concave', 'none'. ... Variables passed prior object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"function adds presence-absence biodiversity dataset distribution object. Opposed presence-data, presence-absence biodiversity records usually originate structured biodiversity surveys absence species given region specifically assessed. analysts choice also possible format presence-biodiversity data presence-absence form, adding pseudo-absence add_pseudoabsence. See help file information.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"","code":"add_biodiversity_poipa(   x,   poipa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_poipa(   x,   poipa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"x distribution() (.e. BiodiversityDistribution) object. poipa data.frame sf object presence-absence point occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records indicating presence/absence. default set \"observed\" error thrown numeric column name exist. formula character formula object passed. Default (NULL) use covariates. family character stating family used  (Default: 'binomial'). link character overwrite default link function (Default: NULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length parameter \"poipa\". separate_intercept logical value stating whether separate intercept added . shared likelihood models engines engine_inla, engine_inlabru engine_stan. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"default, logit link function used logistic regression setting unless specific engine support generalised linear regressions (e.g. engine_bart).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"Renner, . W., J. Elith, . Baddeley, W. Fithian, T. Hastie, S. J. Phillips, G. Popovic, D. . Warton. 2015. Point process models presence-analysis. Methods Ecology Evolution 6:366–379. Guisan . Zimmerman N. 2000. Predictive habitat distribution models ecology. Ecol. Model. 135: 147–186.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipa.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity point dataset to a distribution object (presence-absence). — add_biodiversity_poipa","text":"","code":"if (FALSE) { # Define model x <- distribution(background) |> add_biodiversity_poipa(virtual_species) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"function adds presence-biodiversity dataset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"","code":"add_biodiversity_poipo(   x,   poipo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_poipo(   x,   poipo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"x distribution() (.e. BiodiversityDistribution) object. poipo data.frame sf object presence-point occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records. formula character formula object passed. Default use covariates (specified). family character stating family used (Default: 'Poisson'). link character overwrite default link function (Default: codeNULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length \"poipo\". Note: Weights reformated inverse models area offsets (e.g. 5 converted 1/5). separate_intercept logical value stating whether separate intercept added shared likelihood models engines engine_inla, engine_inlabru engine_stan. Otherwise ignored. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). pseudoabsence_settings Either NULL pseudoabs_settings() created settings object. ... parameters passed object. Normally used unless described details.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"function allows add presence-biodiversity records distribution ibis.iSDM Presence-data usually modelled inferential model (see Guisan Zimmerman, 2000) relate occurrence relation environmental covariates selected sample 'background' points. common approach estimation one supported type dataset poisson-process models (PPM) presence-points fitted -weighted Poisson regression. See Renner et al. 2015 overview.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"Guisan . Zimmerman N. 2000. Predictive habitat distribution models ecology. Ecol. Model. 135: 147–186. Renner, . W., J. Elith, . Baddeley, W. Fithian, T. Hastie, S. J. Phillips, G. Popovic, D. . Warton. 2015. Point process models presence-analysis. Methods Ecology Evolution 6:366–379.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_poipo.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity point dataset to a distribution object (presence-only) — add_biodiversity_poipo","text":"","code":"# Load background background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM',mustWork = TRUE)) # Load virtual species virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg', package='ibis.iSDM',mustWork = TRUE),'points',quiet = TRUE) # Define model x <- distribution(background) |> add_biodiversity_poipo(virtual_points, field_occurrence = \"Observed\") #> [Setup] 2024-02-06 14:28:46.686455 | Creating distribution object... #> [Setup] 2024-02-06 14:28:46.687315 | Adding poipo dataset..."},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"function can used add sf polygon dataset existing distribution object. Presence-absence polygon data assumes area within polygon can treated 'presence' species, area outside polygon species absent.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"","code":"add_biodiversity_polpa(   x,   polpa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_polpa(   x,   polpa,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"binomial\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"x distribution() (.e. BiodiversityDistribution) object. polpa sf polygon object presence-absence occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records. formula character formula object passed. Default (NULL) use covariates . family character stating family used (Default: binomial). link character overwrite default link function (Default: NULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length \"polpa\". simulate Simulate poipa points within boundaries. Result passed add_biodiversity_poipa (Default: FALSE). simulate_points numeric number points created simulation. simulate_bias SpatRaster layer describing eventual preference simulation (Default: NULL). simulate_strategy character stating strategy sampling. Can set either. 'random' 'regular', latter requiring raster supplied 'simulate_weights' parameter. separate_intercept logical value stating whether separate intercept added shared likelihood models engines engine_inla, engine_inlabru engine_stan. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). pseudoabsence_settings Either NULL pseudoabs_settings() created settings object. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"default approach polygon data sample presence-absence points across region polygons. function thus adds wrapper add_biodiversity_poipa() presence-points created model. Note polygon used directly modelling link covariates polygonal data established regular sampling points within polygon thus equivalent simulating points directly. integration range data predictor offset, see add_predictor_range() add_offset_range() instead.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpa.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity polygon dataset to a distribution object (presence-absence) — add_biodiversity_polpa","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_biodiversity_polpa(protectedArea) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":null,"dir":"Reference","previous_headings":"","what":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"function can used add sf polygon dataset existing distribution object. Presence-polygon data treated differential point data engines particular way points generated.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"","code":"add_biodiversity_polpo(   x,   polpo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )  # S4 method for BiodiversityDistribution,sf add_biodiversity_polpo(   x,   polpo,   name = NULL,   field_occurrence = \"observed\",   formula = NULL,   family = \"poisson\",   link = NULL,   weight = 1,   simulate = FALSE,   simulate_points = 100,   simulate_bias = NULL,   simulate_strategy = \"random\",   separate_intercept = TRUE,   docheck = TRUE,   pseudoabsence_settings = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"x distribution() (.e. BiodiversityDistribution) object. polpo sf polygon object presence-occurrences. name name biodiversity dataset used internal identifier. field_occurrence numeric character location biodiversity point records. formula character formula object passed. Default use covariates (specified). family character stating family used (Default: poisson). link character overwrite default link function (Default: NULL). weight numeric value acting multiplier regards weights used modelling. Larger weights indicate higher weighting relative datasets. default set 1 one dataset added. vector also supported must length \"polpo\". simulate Simulate poipo points within boundaries. Result passed add_biodiversity_poipo (Default: FALSE). simulate_points numeric number points created simulation (Default: 100). simulate_bias SpatRaster layer describing eventual preference simulation (Default: NULL). simulate_strategy character stating strategy sampling. Can set either. 'random' 'regular', latter requiring raster supplied 'simulate_weights' parameter. separate_intercept logical value stating whether separate intercept added shared likelihood models engines engine_inla, engine_inlabru engine_stan. docheck logical whether additional checks performed (e.g. intersection tests) (Default: TRUE). pseudoabsence_settings Either NULL pseudoabs_settings() created settings object. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"Adds biodiversity data distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"default approach polygon data sample presence-points across region polygons. function thus adds wrapper add_biodiversity_poipo() presence-points created model. points simulated directly (Default) polygon processed train() creating regular point data supplied predictors. Use add_biodiversity_polpa() create binomial distributed inside-outside points given polygon! integration range data predictor offset, see add_predictor_range() add_offset_range() instead.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_biodiversity_polpo.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add biodiversity polygon dataset to a distribution object (presence-only) — add_biodiversity_polpo","text":"","code":"if (FALSE) {  x <- distribution(mod) |>    add_biodiversity_polpo(protectedArea) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a constraint to an existing scenario — add_constraint","title":"Add a constraint to an existing scenario — add_constraint","text":"function adds constrain BiodiversityScenario object constrain (future) projections. constrains can instance constraints possible dispersal distance, connectivity identified patches limitations species adaptability. constrains require pre-calculated thresholds present BiodiversityScenario object!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a constraint to an existing scenario — add_constraint","text":"","code":"add_constraint(mod, method, ...)  # S4 method for BiodiversityScenario add_constraint(mod, method, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a constraint to an existing scenario — add_constraint","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. ... passed parameters. See also specific methods adding constraints.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add a constraint to an existing scenario — add_constraint","text":"Adds constraints data BiodiversityScenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add a constraint to an existing scenario — add_constraint","text":"Constraints can added scenario objects increase decrease suitability given area target feature. function acts wrapper add constraints. Currently supported following options: Dispersal: sdd_fixed - Applies fixed uniform dispersal distance per modelling timestep. sdd_nexpkernel - Applies dispersal distance using negative exponential kernel origin. kissmig - Applies kissmig stochastic dispersal model. Requires `kissmig` package. Applied modelling time step. migclim - Applies dispersal algorithm MigClim modelled objects. Requires \"MigClim\" package. comprehensive overview benefits including dispersal constrains species distribution models can found Bateman et al. (2013). Connectivity: hardbarrier - Defines hard barrier dispersal events. definition sets values larger 0 barrier layer 0 projection. Barrier provided \"resistance\" parameter. resistance - Allows provision static dynamic layer multiplied projection time step. Can example used reduce suitability given area (using pressures included model). respective layer(s) provided \"resistance\" parameter. Provided layers incorporated abs(resistance - 1) multiplied prediction. Adaptability: nichelimit - Specifies limit environmental niche allow modest amount extrapolation beyond known occurrences. can particular useful limit influence increasing marginal responses avoid biologically unrealistic projections. Boundary size: boundary - Applies hard boundary constraint projection, thus disallowing expansion range outside provide layer. Similar specifying projection limits (see distribution), can used specifically constrain projection within certain area (e.g. species range island). minsize - Allows specify certain size must satisfied order thresholded patch occupied. Can thought minimum size requirement. See add_constraint_minsize() required parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a constraint to an existing scenario — add_constraint","text":"Bateman, B. L., Murphy, H. T., Reside, . E., Mokany, K., & VanDerWal, J. (2013). Appropriateness full‐, partial‐‐dispersal scenarios climate change impact modelling. Diversity Distributions, 19(10), 1224-1234. Nobis MP Normand S (2014) KISSMig - simple model R account limited migration analyses species distributions. Ecography 37: 1282-1287. Mendes, P., Velazco, S. J. E., de Andrade, . F. ., & Júnior, P. D. M. (2020). Dealing overprediction species distribution models: adding distance constraints can improve model accuracy. Ecological Modelling, 431, 109180.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a constraint to an existing scenario — add_constraint","text":"","code":"if (FALSE) { # Assumes that a trained 'model' object exists  mod <- scenario(model) |>   add_predictors(env = predictors, transform = 'scale', derivates = \"none\") |>   add_constraint_dispersal(method = \"kissmig\", value = 2, pext = 0.1) |>   project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":null,"dir":"Reference","previous_headings":"","what":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"function adds constrain defined MigClim approach (Engler et al. 2013) BiodiversityScenario object constrain future projections. detailed description MigClim, please respective reference UserGuide. default parameters chosen suggestions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"","code":"add_constraint_MigClim(   mod,   rcThresholdMode = \"continuous\",   dispSteps = 1,   dispKernel = c(1, 0.4, 0.16, 0.06, 0.03),   barrierType = \"strong\",   lddFreq = 0,   lddRange = c(1000, 10000),   iniMatAge = 1,   propaguleProdProb = c(0.2, 0.6, 0.8, 0.95),   replicateNb = 10,   dtmp = terra::terraOptions(print = F)$tempdir )  # S4 method for BiodiversityScenario add_constraint_MigClim(   mod,   rcThresholdMode = \"continuous\",   dispSteps = 1,   dispKernel = c(1, 0.4, 0.16, 0.06, 0.03),   barrierType = \"strong\",   lddFreq = 0,   lddRange = c(1000, 10000),   iniMatAge = 1,   propaguleProdProb = c(0.2, 0.6, 0.8, 0.95),   replicateNb = 10,   dtmp = terra::terraOptions(print = F)$tempdir )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"mod BiodiversityScenario object specified predictors. rcThresholdMode character either binary continuous value (Default: continuous). dispSteps numeric parameters number dispersal steps. Dispersal steps executed timestep (prediction layer). ideally aligned number steps projection. Minimum 1 (Default) maximum 99. dispKernel vector number dispersal Kernel applied. Can set either uniform numeric vector, e.g. c(1,1,1,1) proportional decline (1,0.4,0.16,0.06,0.03) (Default). Depending resolution raster, parameter needs adapted barrierType character indicating whether set barrier set 'strong' 'weak' barriers. Strong barriers prevent dispersal across barrier weak barriers whole \"dispKernel\" length covered barrier (Default: 'strong'). lddFreq numeric parameter indicating frequency long-distance dispersal (LDD) events. Default 0, long-distance dispersal. lddRange numeric value highlighting minimum maximum distance LDD events. Note: units distance cells, thus projection units raster. iniMatAge Initial maturity age. Used together propaguleProd proxy population growth. Must set cell age time units dispersal steps (Default: 1). propaguleProdProb Probability source cell produce propagules function time since colonization. Set probability vector defines probability cell producing propagules. replicateNb Number replicates used analysis (Default: 10). dtmp character folder temporary files created.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"Adds MigClim onstrain BiodiversityScenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"barrier parameter defined \"add_barrier\".","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"Engler R., Hordijk W. Guisan . MIGCLIM R package – seamless integration dispersal constraints projections species distribution models. Ecography, Robin Engler, Wim Hordijk Loic Pellissier (2013). MigClim: Implementing dispersal species distribution models. R package version 1.6.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_MigClim.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add constrains to the modelled distribution projection using the MigClim\napproach — add_constraint_MigClim","text":"","code":"if (FALSE) { # Assumes that a trained 'model' object exists  mod <- scenario(model) |>   add_predictors(env = predictors, transform = 'scale',                  derivates = \"none\") |>   add_constraint_MigClim() |>   project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"Adaptability constraints assume suitable habitat species (future) projections might unsuitable outside range conditions currently observed species. Currently nichelimit implemented, adds simple constrain predictor parameter space, can defined \"value\" parameter. example setting 1 (Default), projections constrained within range maximum 1 standard deviation range covariates used model training.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"","code":"add_constraint_adaptability(   mod,   method = \"nichelimit\",   names = NULL,   value = 1,   increment = 0,   ... )  # S4 method for BiodiversityScenario add_constraint_adaptability(   mod,   method = \"nichelimit\",   names = NULL,   value = 1,   increment = 0,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. names character vector names predictors adaptability threshold set (Default: NULL ). value numeric value units standard deviation (Default: 1). increment numeric constant added value every time step (Default: 0). Allows incremental widening niche space, thus opening constraints. ... passed parameters. See also specific methods adding constraints.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_adaptability.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds an adaptability constraint to a scenario object — add_constraint_adaptability","text":"","code":"if (FALSE) { scenario(fit) |>  add_constraint_adaptability(value = 1) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a boundary constraint to a scenario object — add_constraint_boundary","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"purpose boundary constraints limit future projection within specified area (example range ecoregion). can help limit unreasonable projections geographic space. Similar boundary constraints also possible define \"zone\" scenario projections, similar done model training. difference boundary constraint boundary constraint applied posthoc hard cut projection, zones allow projection (constraints) applied within zone. Note: Setting boundary constraint future projections effectively potentially suitable areas!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"","code":"add_constraint_boundary(mod, layer, ...)  # S4 method for BiodiversityScenario,sf add_constraint_boundary(mod, layer, method = \"boundary\", ...)  # S4 method for BiodiversityScenario,ANY add_constraint_boundary(mod, layer, method = \"boundary\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"mod BiodiversityScenario object specified predictors. layer SpatRaster sf object extent model background. binary used posthoc masking projected grid cells. ... passed parameters. See also specific methods adding constraints. method character indicating type constraints added scenario. See details information.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_boundary.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds a boundary constraint to a scenario object — add_constraint_boundary","text":"","code":"if (FALSE) { # Add scenario constraint scenario(fit) |> add_constraint_boundary(range) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_connectivity.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","title":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","text":"Adds connectivity constraint scenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_connectivity.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","text":"","code":"add_constraint_connectivity(mod, method, value = NULL, resistance = NULL, ...)  # S4 method for BiodiversityScenario add_constraint_connectivity(mod, method, value = NULL, resistance = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_connectivity.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a connectivity constraint to a scenario object. — add_constraint_connectivity","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. value many dispersal \"constrain\" set numeric value specifying fixed constrain constant units \"m\" (Default: NULL). kissmig value needs give number iteration steps (within year migration steps). adaptability constraints parameter specifies extent (units standard deviation) extrapolations performed. resistance SpatRaster object describing resistance surface barrier use connectivity constrains (Default: NULL). ... passed parameters. See also specific methods adding constraints.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":null,"dir":"Reference","previous_headings":"","what":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"Add dispersal constraint existing scenario","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"","code":"add_constraint_dispersal(mod, method, value = NULL, type = NULL, ...)  # S4 method for BiodiversityScenario add_constraint_dispersal(mod, method, value = NULL, type = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"mod BiodiversityScenario object specified predictors. method character indicating type constraints added scenario. See details information. value many dispersal \"constrain\" set numeric value specifying fixed constrain constant units \"m\" (Default: NULL). kissmig value needs give number iteration steps (within year migration steps). adaptability constraints parameter specifies extent (units standard deviation) extrapolations performed. type character indicating type used method. See instance `kissmig`. ... passed parameters. See also specific methods adding constraints.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_dispersal.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add dispersal constraint to an existing scenario — add_constraint_dispersal","text":"following additional parameters can bet set: pext: numeric indicator `kissmig` probability colonized cell becomes uncolonised, .e., species gets locally extinct (Default: 0.1). pcor: numeric probability corner cells considered 3x3 neighbourhood (Default: 0.2).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a size constraint on a scenario — add_constraint_minsize","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"function applies minimum size constraint scenario() created object. rationale given species isolated habitat patches smaller given size might viable / unrealistic species establish (long-term) presence. idea thus apply constraint patches bigger certain size retained timesteps. thus potential reduce subsequent colonizations neighbouring patches.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"","code":"add_constraint_minsize(   mod,   value,   unit = \"km2\",   establishment_step = FALSE,   ... )  # S4 method for BiodiversityScenario,numeric add_constraint_minsize(   mod,   value,   unit = \"km2\",   establishment_step = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"mod BiodiversityScenario object specified predictors. value numeric value describing minimum amount area given patch unit character unit area. Options available km2 (Default) ha. establishment_step logical flag indicating whether given patch removed small previous time step (yet implemented!) ... passed parameters. See also specific methods adding constraints.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"Area values specific unit need supplied.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"function requires scenario set threshold()!","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_constraint_minsize.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds a size constraint on a scenario — add_constraint_minsize","text":"","code":"if (FALSE) { scenario(fit) |>  add_predictors(future_covariates) |>  threshold() |>  add_constraint_minsize(value = 1000, unit = \"km2\") |>  project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a control to a BiodiversityModel object to control biases — add_control_bias","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Sampling biases pervasive drivers spatial location biodiversity datasets. integration , presumably less biased data can one way controlling sampling biases, another way control directly bias model. Currently supported methods : \"partial\" - approach described Warton et al. (2013) control biases model, including specified variable (\"layer\") model, \"partialling\" projection phase. Specifically variable set specified value (\"bias_value\"), default minimum value observed across background. \"offset\" - Dummy method points add_offset_bias() functionality (see note). Makes use offsets factor specified bias variable. \"proximity\" - Use proximity distance points weight model. option effectively places greater weight points farther away. Note: best case can control spatial bias aggregation, worst case can place lot emphasis points likely outliers misidentification (terms species). See also details explanations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"","code":"add_control_bias(   x,   layer,   method = \"partial\",   bias_value = NULL,   maxdist = NULL,   alpha = 1,   add = TRUE )  # S4 method for BiodiversityDistribution add_control_bias(   x,   layer,   method = \"partial\",   bias_value = NULL,   maxdist = NULL,   alpha = 1,   add = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. Specify variable already added \"x\" avoid issues duplications. method character vector describing method used bias control. Available options \"partial\" (Default), \"offset\" \"proximity\". bias_value numeric value \"layer\". Specifying numeric value sets layer target value projection. default value set minimum value found layer (Default: NULL). maxdist numeric giving maximum distance method \"proximity\" used. unset uses default distance centroid minimum convex polygon encircling points. alpha numeric given initial weight points method \"proximity\" used (Default: 1). example, set values smaller 1 neighbouring points weighted less. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Adds bias control option distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"case \"proximity\" weights assigned point, placing higher weight points away less overlap. Weights assigned maximum distance can provided user (parameter \"maxdist\"). distance ideally informed knowledge species modelled (e.g., maximum dispersal distance). provided, set distance centroid minimum convex polygon encircling observations. parameter \"alpha\" weighting factor can used diminish effect neighboring points.  given observation \\(\\), weight \\(w\\) defined $$w_i = 1 / (1 + \\epsilon)$$ $$\\epsilon = \\sum_{n=1}^{N}((1 - d_n)/d_sac)^\\alpha$$ \\(N\\) total number points closer maximum distance (\\(d_sac\\)) point \\(\\), \\(d_n\\) distance focal point \\(\\) point \\(n\\).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Covariate transformations applied predictors need applied bias . Another option consider biases particular Poisson-point process models remove offset. Functionality available add_offset_bias() method. Setting method \"offset\" automatically point option.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"Warton, D.., Renner, .W. Ramp, D., 2013. Model-based control observer bias analysis presence-data ecology. PloS one, 8(11), p.e79168. Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453 Botella, C., Joly, ., Bonnet, P., Munoz, F., & Monestiez, P. (2021). Jointly estimating spatial sampling effort habitat suitability multiple species opportunistic presence‐data. Methods Ecology Evolution, 12(5), 933-945.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_bias.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a control to a BiodiversityModel object to control biases — add_control_bias","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_predictors(covariates) |>    add_control_bias(biasvariable, bias_value = NULL) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"One main aims species distribution models (SDMs) project space time. projections common issue extrapolation - unconstrained - SDMs can indicate areas suitable unlikely occupied species habitats (often due historic biotic factors). extent can related insufficient quantification niche (e.g. niche truncation considering subset observations within actual distribution), cases can also general barriers constraints limit projections (e.g. islands). control method adds options model distribution object. Currently supported methods : * \"zones\" - wrapper allow addition zones distribution model object, similar also possible via distribution(). Required spatial layer describes environmental zoning. * \"mcp\" - Rather using external additional layer, option constraints predictions certain distance points vicinity. Buffer distances unit projection used can configured via \"mcp_buffer\". * \"nt2\" - Constraints predictions using multivariate combination novelty index (NT2) following Mesgaran et al. (2014). method also available similarity() function. * \"shape\" - implementation 'shape' method introduced Velazco et al. (2023). user defined threshold effectively limits model extrapolation projections made beyond extent judged defensible informed training observations. See also details explanations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"","code":"add_control_extrapolation(   x,   layer,   method = \"mcp\",   mcp_buffer = 0,   novel = \"within\",   limits_clip = FALSE )  # S4 method for BiodiversityDistribution add_control_extrapolation(   x,   layer,   method = \"mcp\",   mcp_buffer = 0,   novel = \"within\",   limits_clip = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"x distribution() (.e. BiodiversityDistribution) object. layer SpatRaster sf object limits prediction surface intersected input data (Default: NULL). method character vector describing method used controlling extrapolation. Available options \"zones\", \"mcp\" (Default), \"nt2\" \"shape\". mcp_buffer numeric distance buffer mcp (Default 0). used \"mcp\" used. novel conditions masked respectively, either novel conditions within \"within\" (Default) also including outside reference conditions \"outside\". use method = \"nt2\", method = \"mess\" variable always \"within\". limits_clip logical limits clip predictors fitting model (TRUE) just prediction (FALSE, default).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"Adds extrapolation control option distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"method \"zones\" zoning layer can supplied used intersect provided training points . projections made model can constrained project areas consider training points unlikely . Examples zones separation islands mainlands, biomes, lithological soil conditions. layer available, also possible constraint predictions distance minimum convex polygon surrounding training points method \"mcp\" (optionally buffered). can make sense particular rare species fully sampled across niche. \"NT2\" \"MESS\" index possible constrain prediction conditions within (novel = \"within\") also include outside (novel = \"outside\") conditions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"method \"zones\" also possible directly within distribution().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"Randin, C. F., Dirnböck, T., Dullinger, S., Zimmermann, N. E., Zappa, M., & Guisan, . (2006). niche‐based species distribution models transferable space?. Journal biogeography, 33(10), 1689-1703. https://doi.org/10.1111/j.1365-2699.2006.01466.x Chevalier, M., Broennimann, O., Cornuault, J., & Guisan, . (2021). Data integration methods account spatial niche truncation effects regional projections species distribution. Ecological Applications, 31(7), e02427. https://doi.org/10.1002/eap.2427 Velazco, S. J. E., Brooke, M. R., De Marco Jr., P., Regan, H. M., & Franklin, J. (2023). far can extrapolate species distribution model? Exploring Shape, novel method. Ecography, 11, e06992. https://doi.org/10.1111/ecog.06992 Mesgaran, M. B., R. D. Cousens, B. L. Webber, J. Franklin. (2014) dragons: tool quantifying novelty due covariate range correlation change projecting species distribution models. Diversity Distributions 20:1147-1159.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_control_extrapolation.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a control to a BiodiversityModel object to control extrapolation — add_control_extrapolation","text":"","code":"if (FALSE) {  # To add a zone layer for extrapolation constraints.  x <- distribution(background) |>    add_predictors(covariates) |>    add_control_extrapolation(method = \"zones\", layer = zones) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":null,"dir":"Reference","previous_headings":"","what":"Add latent spatial effect to the model equation — add_latent_spatial","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"general understand latent spatial effects occurrence spatial dependency observations, might either caused spatial biases, similarities underlying sampling processes unmeasured latent covariates, e.g. quantified. package supports range different spatial effects, however differ another impact estimated prediction. effects simply add spatial dependence covariate, others make use spatial random effects account spatial dependence predictions. default effects added dataset covariate shared spatial field (e.g. SPDE). See details explanation available options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"","code":"add_latent_spatial(   x,   method = \"spde\",   priors = NULL,   separate_spde = FALSE,   ... )  # S4 method for BiodiversityDistribution add_latent_spatial(   x,   method = \"spde\",   priors = NULL,   separate_spde = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"x distribution() (.e. BiodiversityDistribution) object. method character describing kind spatial effect added model. See details. priors \"Prior-List\" object supplied latent effect. Relevant engine_inla NULL equates use default priors. separate_spde logical parameter indicating whether, case SPDE effects, separate effects likelihood fitted. Default (FALSE) uses copy first added likelihood. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"Adds latent spatial effect distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"several different options depend engine used. case unsupported method engine chosen modified next similar method. Available : \"spde\" - stochastic partial differential equation (SPDE) engine_inla engine_inlabru. SPDE effects aim capturing variation response variable space, covariates accounted . Examining spatial distribution spatial error can reveal covariates might missing. example, elevation positively correlated response variable, included model, see higher posterior mean areas higher elevation. Note calculations SPDE's can computationally costly. \"car\" - conditional autocorrelative errors (CAR) engine_inla. yet implemented full. \"kde\" - additional covariate kernel density input point observations. \"poly\" - spatial trend correction adding coordinates polynominal transformation. method assumed transformation spatial coordinates can - included additional predictor - explain variance distribution. method interact species occurrences. \"nnd\" - nearest neighbour distance. function calculates euclidean distance point nearest grid cell known species occurrence. Originally proposed Allouche et al. (2008) can applied across datasets BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"Allouche, O.; Steinitz, O.; Rotem, D.; Rosenfeld, .; Kadmon, R. (2008). Incorporating distance constraints species distribution models. Journal Applied Ecology, 45(2), 599-609. doi:10.1111/j.1365-2664.2007.01445.x Mendes, P., Velazco, S. J. E., de Andrade, . F. ., & Júnior, P. D. M. (2020). Dealing overprediction species distribution models: adding distance constraints can improve model accuracy. Ecological Modelling, 431, 109180.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_latent_spatial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add latent spatial effect to the model equation — add_latent_spatial","text":"","code":"if (FALSE) {  distribution(background) |> add_latent_spatial(method = \"poly\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":null,"dir":"Reference","previous_headings":"","what":"Adds a log file to distribution object — add_log","title":"Adds a log file to distribution object — add_log","text":"function allows specify file Log file, used save console outputs, prints messages.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Adds a log file to distribution object — add_log","text":"","code":"add_log(x, filename)  # S4 method for BiodiversityDistribution,character add_log(x, filename)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Adds a log file to distribution object — add_log","text":"x distribution() (.e. BiodiversityDistribution) object. filename character object. destination must writeable filename ends 'txt'.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Adds a log file to distribution object — add_log","text":"Adds log file distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_log.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Adds a log file to distribution object — add_log","text":"","code":"if (FALSE) {  x <- distribution(background) |>     add_log()  x }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify a spatial explicit offset — add_offset","title":"Specify a spatial explicit offset — add_offset","text":"Including offsets another option integrate spatial prior information linear additive regression models. Offsets shift intercept regression fit certain amount. Although one offset can added regression model, possible combine several spatial-explicit estimates one offset calculating sum spatial-explicit layers.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify a spatial explicit offset — add_offset","text":"","code":"add_offset(x, layer, add = TRUE)  # S4 method for BiodiversityDistribution,SpatRaster add_offset(x, layer, add = TRUE)  # S4 method for BiodiversityDistribution,sf add_offset(x, layer, add = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify a spatial explicit offset — add_offset","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify a spatial explicit offset — add_offset","text":"Adds offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify a spatial explicit offset — add_offset","text":"function allows set specific offset regression model. offset provided spatial SpatRaster object. function simply adds layer distribution() object. Note transformation offset (log) done externally! layer range requires additional formatting, consider using function add_offset_range() additional functionalities distance transformations.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Specify a spatial explicit offset — add_offset","text":"Since offsets make sense linear regressions (instance regression tree based methods engine_bart), work engines. Offsets specified non-supported engines ignored estimation","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify a spatial explicit offset — add_offset","text":"Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify a spatial explicit offset — add_offset","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_predictors(covariates) |>    add_offset(nicheEstimate) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify a spatial explicit offset as bias — add_offset_bias","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"Including offsets another option integrate spatial prior information linear additive regression models. Offsets shift intercept regression fit certain amount. Although one offset can added regression model, possible combine several spatial-explicit estimates one offset calculating sum spatial-explicit layers.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"","code":"add_offset_bias(x, layer, add = TRUE, points = NULL)  # S4 method for BiodiversityDistribution,SpatRaster add_offset_bias(x, layer, add = TRUE, points = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE). points optional sf object key points. location points used calculate probability cell sampled accounting area differences. (Default: NULL).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"Adds bias offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"functions emulates use add_offset() function, however applies inverse transformation remove provided layer overall offset. instance offset already specified (area), function removes provided bias.layer via \"offset(log(.area)-log(bias.layer))\" Note transformation offset (log) done externally! generic offset added, consider using add_offset() function. layer expert-based range requires additional parametrization, consider using function add_offset_range() bossMaps R-package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_bias.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify a spatial explicit offset as bias — add_offset_bias","text":"","code":"if (FALSE) {  x <- distribution(background) |>    add_predictors(covariates) |>    add_offset_bias(samplingBias) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify elevational preferences as offset — add_offset_elevation","title":"Specify elevational preferences as offset — add_offset_elevation","text":"function implements elevation preferences offset defined Ellis‐Soto et al. (2021). code adapted Supporting materials script.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify elevational preferences as offset — add_offset_elevation","text":"","code":"add_offset_elevation(x, elev, pref, rate = 0.0089, add = TRUE)  # S4 method for BiodiversityDistribution,SpatRaster,numeric add_offset_elevation(x, elev, pref, rate = 0.0089, add = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify elevational preferences as offset — add_offset_elevation","text":"x distribution() (.e. BiodiversityDistribution) object. elev SpatRaster elevation given background. pref numeric vector length 2 giving lower upper bound known elevational preferences. Can set Inf unknown. rate numeric rate used offset (Default: .0089). parameter specifies decay near zero probability elevation expert limits. add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify elevational preferences as offset — add_offset_elevation","text":"Adds elevational offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify elevational preferences as offset — add_offset_elevation","text":"Specifically functions calculates continuous decay decreasing probability species occur elevation limits. requires SpatRaster elevation information. generalized logistic transform (aka Richard's curve) used calculate decay suitable elevational areas, \"rate\" parameter allowing vary steepness decline. Note offsets created function default log-transformed export. addition function also mean-centers output recommended Ellis-Soto et al.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify elevational preferences as offset — add_offset_elevation","text":"Ellis‐Soto, D., Merow, C., Amatulli, G., Parra, J.L., Jetz, W., 2021. Continental‐scale 1 km hummingbird diversity derived fusing point records lateral elevational expert information. Ecography (Cop.). 44, 640–652. https://doi.org/10.1111/ecog.05119 Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_elevation.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify elevational preferences as offset — add_offset_elevation","text":"","code":"if (FALSE) {  # Adds the offset to a distribution object  distribution(background) |> add_offset_elevation(dem, pref = c(400, 1200)) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":null,"dir":"Reference","previous_headings":"","what":"Specify a expert-based species range as offset — add_offset_range","title":"Specify a expert-based species range as offset — add_offset_range","text":"function additional options compared generic add_offset(), allowing customized options specifically expert-based ranges offsets spatialized polygon information species occurrences. even control needed, user informed \"bossMaps\" package Merow et al. (2017). functionalities package emulated \"distance_function\" set \"log\". tries fit 5-parameter logistic function estimate distance range (Merow et al. 2017).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Specify a expert-based species range as offset — add_offset_range","text":"","code":"add_offset_range(   x,   layer,   distance_max = Inf,   family = \"poisson\",   presence_prop = 0.9,   distance_clip = FALSE,   distance_function = \"negexp\",   field_occurrence = \"observed\",   fraction = NULL,   point = FALSE,   add = TRUE )  # S4 method for BiodiversityDistribution,SpatRaster add_offset_range(x, layer, fraction = NULL, add = TRUE)  # S4 method for BiodiversityDistribution,sf add_offset_range(   x,   layer,   distance_max = Inf,   family = \"poisson\",   presence_prop = 0.9,   distance_clip = FALSE,   distance_function = \"negexp\",   field_occurrence = \"observed\",   fraction = NULL,   point = FALSE,   add = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Specify a expert-based species range as offset — add_offset_range","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. distance_max numeric threshold maximum distance beyond range considered high likelihood containing species occurrences (Default: Inf \"m\"). Can set NULL 0 indicate distance calculated. family character denoting type model offset added. default assumes 'poisson' distributed model result output created function log-transformed. however 'binomial' distribution chosen, output `logit` transformed. integrated models leave default. presence_prop numeric giving proportion records expected inside range. default set 0.9 indicating 10% records likely outside range. distance_clip logical whether distance clipped maximum distance (Default: FALSE). distance_function character specifying distance function used. Available linear (\"linear\"), negative exponential kernels (\"negexp\", default) five parameters logistic curve (code\"logcurve\") proposed Merow et al. 2017. field_occurrence numeric character location biodiversity point records. fraction optional SpatRaster object multiplied digitized raster layer. Can used example remove reduce expected value (Default: NULL). point optional sf layer points logical argument. case latter point data ignored (Default: FALSE). add logical specifying whether new offset added. Setting parameter FALSE replaces current offsets new one (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Specify a expert-based species range as offset — add_offset_range","text":"Adds range offset distribution object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Specify a expert-based species range as offset — add_offset_range","text":"output created function creates SpatRaster added provided distribution object. Offsets regression models likelihood specific added directly overall estimate `y^hat`. Note offsets created function default log-transformed export. Background values (e.g. beyond \"distance_max\") set small constant (1e-10).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Specify a expert-based species range as offset — add_offset_range","text":"Merow, C., Wilson, .M., Jetz, W., 2017. Integrating occurrence data expert maps improved species range predictions. Glob. Ecol. Biogeogr. 26, 243–258. https://doi.org/10.1111/geb.12539 Merow, C., Allen, J.M., Aiello-Lammens, M., Silander, J.., 2016. Improving niche range estimates Maxent point process models integrating spatially explicit information. Glob. Ecol. Biogeogr. 25, 1022–1036. https://doi.org/10.1111/geb.12453","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_offset_range.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Specify a expert-based species range as offset — add_offset_range","text":"","code":"if (FALSE) {  # Train a presence-only model with a simple offset  fit <- distribution(background) |>  add_biodiversity_poipo(virtual_points, field_occurrence = \"Observed\") |>  add_predictors(predictors) |>  add_offset_range(virtual_range, distance_max = 5,distance_function = \"logcurve\",  distance_clip = TRUE ) |>  engine_glm() |>  train() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":null,"dir":"Reference","previous_headings":"","what":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"Create lower upper limits elevational range add separate predictors","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"","code":"add_predictor_elevationpref(x, layer, lower, upper, transform = \"none\")  # S4 method for BiodiversityDistribution,ANY,numeric,numeric add_predictor_elevationpref(x, layer, lower, upper, transform = \"none\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"x distribution() (.e. BiodiversityDistribution) object. layer character stating elevational layer Distribution object SpatRaster object. lower numeric value lower elevational preference species. upper numeric value upper elevational preference species. transform character optional transformation applied. Usually needed (Default: \"none\").","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_elevationpref.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create lower and upper limits for an elevational range and add them as\nseparate predictors — add_predictor_elevationpref","text":"","code":"if (FALSE) { distribution(background) |>   add_predictor_elevationpref(elevation, lower = 200, upper = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":null,"dir":"Reference","previous_headings":"","what":"Add a range of a species as predictor to a distribution object — add_predictor_range","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"function allows add species range usually drawn experts separate process spatial explicit prior. sf SpatRaster-objects supported input. Users advised look \"bossMaps\" R-package presented part Merow et al. (2017), allows flexible calculation non-linear distance transforms boundary range. Outputs package added directly function. Note function adds range predictor offset. purpose separate function add_offset_range() exists. Additional options allow include range either \"binary\" \"distance\" transformed predictor. difference range either directly included presence-predictor alternatively linear distance transform range boundary. parameter \"distance_max\" can specified constrain distance transform.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"","code":"add_predictor_range(   x,   layer,   method = \"distance\",   distance_max = NULL,   fraction = NULL,   priors = NULL )  # S4 method for BiodiversityDistribution,SpatRaster add_predictor_range(   x,   layer,   method = \"precomputed_range\",   fraction = NULL,   priors = NULL )  # S4 method for BiodiversityDistribution,sf add_predictor_range(   x,   layer,   method = \"distance\",   distance_max = Inf,   fraction = NULL,   priors = NULL )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"x distribution() (.e. BiodiversityDistribution) object. layer sf SpatRaster object range target feature. method character describing range included (\"binary\" | \"distance\"). distance_max Numeric threshold maximum distance (Default: NULL). fraction optional SpatRaster object multiplied digitized raster layer. Can used example remove reduce expected value (Default: NULL). priors PriorList object. Default set NULL uses default prior assumptions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"Merow, C., Wilson, . M., & Jetz, W. (2017). Integrating occurrence data expert maps improved species range predictions. Global Ecology Biogeography, 26(2), 243–258. https://doi.org/10.1111/geb.12539","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictor_range.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add a range of a species as predictor to a distribution object — add_predictor_range","text":"","code":"if (FALSE) { distribution(background) |>   add_predictor_range(range, method = \"distance\", distance_max = 2) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":null,"dir":"Reference","previous_headings":"","what":"Add predictors to a Biodiversity distribution object — add_predictors","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"function allows add predictors distribution BiodiversityScenario objects. Predictors covariates spatial projection match geographic projection background layer distribution object. function furthermore allows transform create derivates provided predictors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"","code":"add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,SpatRasterCollection add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,SpatRaster add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,stars add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityScenario,SpatRaster add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityScenario,stars add_predictors(   x,   env,   names = NULL,   transform = \"scale\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   explode_factors = FALSE,   priors = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"x distribution() (.e. BiodiversityDistribution) object. env SpatRaster stars object. names vector character names describing environmental stack case renamed. transform vector stating whether predictors preprocessed way (Options: 'none','pca', 'scale', 'norm') derivates Boolean check whether derivate features considered (Options: 'none', 'thresh', 'hinge', 'quad') ) derivate_knots single numeric vector giving number knots derivate creation relevant (Default: 4). int_variables vector length greater equal 2 specifying covariates (Default: NULL). bgmask Check whether environmental data masked background layer (Default: TRUE). harmonize_na logical value indicating whether NA values harmonized among predictors (Default: FALSE). explode_factors logical whether factor variables split binary variables (one per class). (Default: FALSE). priors PriorList object. Default set NULL uses default prior assumptions. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"transformation takes provided rasters instance rescales transforms principal component analysis (prcomp). contrast, derivates leave original provided predictors alone, instead create new ones, instance transforming values quadratic hinge transformation. Note effectively increases number predictors object, generally requiring stronger regularization used Engine. transformations derivates can also combined. Available options transformation : 'none' - Leaves provided predictors original scale. 'pca' - Converts predictors principal components. Note results renaming variables principal component axes! 'scale' - Transforms predictors applying scale . 'norm' - Normalizes predictors transforming scale 0 1. 'windsor' - Applies windsorization target predictors. default effectively cuts predictors 0.05 0.95, thus helping remove extreme outliers. Available options creating derivates : 'none' - additional predictor derivates created. 'quad' - Adds quadratic transformed predictors. 'interaction' - Add interacting predictors. Interactions need specified (\"int_variables\")! 'thresh' - Add threshold transformed predictors. 'hinge' - Add hinge transformed predictors. 'bin' - Add predictors binned percentiles.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"Important: every Engine supported ibis.iSDM R-package allows missing data points among extracted covariates. Thus observation missing data generally removed prior model fitting. Thus ensure covariates appropriate -data settings (instance setting NA values 0 another range constant). every engine actually need covariates. instance perfectly legit fit model occurrence data spatial latent effect (add_latent_spatial). correspondents spatial kernel density estimate. Certain names \"offset\" forbidden predictor variable names. function return error message used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add predictors to a Biodiversity distribution object — add_predictors","text":"","code":"if (FALSE) {  obj <- distribution(background) |>         add_predictors(covariates, transform = 'scale')  obj }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":null,"dir":"Reference","previous_headings":"","what":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"customized function format add downscaled land-use shares Global Biosphere Management Model (GLOBIOM) distribution BiodiversityScenario ibis.iSDM. GLOBIOM partial-equilibrium model developed IIASA represents land-use sectors rich set environmental socio-economic parameters, instance agricultural forestry sector estimated dedicated process-based models. GLOBIOM outputs spatial explicit usually half-degree resolution globally. finer grain analyses GLOBIOM outputs can produced downscaled format customized statistical downscaling module. purpose script format GLOBIOM outputs DownScale use ibis.iSDM package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"","code":"add_predictors_globiom(   x,   fname,   names = NULL,   transform = \"none\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution,character add_predictors_globiom(   x,   fname,   names = NULL,   transform = \"none\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityScenario,character add_predictors_globiom(   x,   fname,   names = NULL,   transform = \"none\",   derivates = \"none\",   derivate_knots = 4,   int_variables = NULL,   bgmask = TRUE,   harmonize_na = FALSE,   priors = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"x BiodiversityDistribution BiodiversityScenario object. fname character pointing netCDF GLOBIOM data. names vector character names describing environmental stack case renamed (Default: NULL). transform vector stating whether predictors preprocessed way (Options: 'none','pca', 'scale', 'norm') derivates Boolean check whether derivate features considered (Options: 'none', 'thresh', 'hinge', 'quad') ) derivate_knots single numeric vector giving number knots derivate creation relevant (Default: 4). int_variables vector length greater equal 2 specifying covariates (Default: NULL). bgmask Check whether environmental data masked background layer (Default: TRUE) harmonize_na logical value indicating whether NA values harmonized among predictors (Default: FALSE) priors PriorList object. Default set NULL uses default prior assumptions. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"See add_predictors() additional parameters customizations. (manual) control function formatting GLOBIOM data can also called directly via formatGLOBIOM().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_globiom.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add GLOBIOM-DownScaleR derived predictors to a Biodiversity distribution\nobject — add_predictors_globiom","text":"","code":"if (FALSE) {  obj <- distribution(background) |>         add_predictors_globiom(fname = \"\", transform = 'none')  obj }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":null,"dir":"Reference","previous_headings":"","what":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"function convenience wrapper add output previous fitted DistributionModel another BiodiversityDistribution object. Obviously works prediction fitted model. Options instead add thresholds, transform / derivate model outputs also supported.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"","code":"add_predictors_model(   x,   model,   transform = \"scale\",   derivates = \"none\",   threshold_only = FALSE,   priors = NULL,   ... )  # S4 method for BiodiversityDistribution add_predictors_model(   x,   model,   transform = \"scale\",   derivates = \"none\",   threshold_only = FALSE,   priors = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"x distribution() (.e. BiodiversityDistribution) object. model DistributionModel object. transform vector stating whether predictors preprocessed way (Options: 'none','pca', 'scale', 'norm') derivates Boolean check whether derivate features considered (Options: 'none', 'thresh', 'hinge', 'quad') ) threshold_only logical flag indicating whether add thresholded layers fitted model (existing) instead (Default: FALSE). priors PriorList object. Default set NULL uses default prior assumptions. ... parameters passed ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"transformation takes provided rasters instance rescales transforms principal component analysis (prcomp). contrast, derivates leave original provided predictors alone, instead create new ones, instance transforming values quadratic hinge transformation. Note effectively increases number predictors object, generally requiring stronger regularization used Engine. transformations derivates can also combined. Available options transformation : 'none' - Leaves provided predictors original scale. 'pca' - Converts predictors principal components. Note results renaming variables principal component axes! 'scale' - Transforms predictors applying scale . 'norm' - Normalizes predictors transforming scale 0 1. 'windsor' - Applies windsorization target predictors. default effectively cuts predictors 0.05 0.95, thus helping remove extreme outliers. Available options creating derivates : 'none' - additional predictor derivates created. 'quad' - Adds quadratic transformed predictors. 'interaction' - Add interacting predictors. Interactions need specified (\"int_variables\")! 'thresh' - Add threshold transformed predictors. 'hinge' - Add hinge transformed predictors. 'bin' - Add predictors binned percentiles.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_predictors_model.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add predictors from a fitted model to a Biodiversity distribution object — add_predictors_model","text":"","code":"if (FALSE) {  # Fit first model  fit <- distribution(background) |>         add_predictors(covariates) |>         add_biodiversity_poipa(species) |>         engine_glmnet() |>         train()   # New model object  obj <- distribution(background) |>         add_predictors_model(fit)  obj }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Add priors to an existing distribution object — add_priors","title":"Add priors to an existing distribution object — add_priors","text":"function simply allows add priors existing distribution object. supplied priors must PriorList object created calling priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add priors to an existing distribution object — add_priors","text":"","code":"add_priors(x, priors = NULL, ...)  # S4 method for BiodiversityDistribution add_priors(x, priors = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add priors to an existing distribution object — add_priors","text":"x distribution (.e. BiodiversityDistribution) object. priors PriorList object containing multiple priors. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add priors to an existing distribution object — add_priors","text":"Alternatively priors environmental predictors can also directly added parameter via add_predictors","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add priors to an existing distribution object — add_priors","text":"","code":"if (FALSE) {  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":null,"dir":"Reference","previous_headings":"","what":"Add pseudo-absence points to a point data set — add_pseudoabsence","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"engines, background pseudo-absence points necessary. distinction lies absence data handled. poisson distributed responses, absence points considered background points intensity sampling (lambda) integrated (classical Poisson point-process model). contrast binomial distributed responses, absence information assumed adequate representation true absences treated model ... advised specify absence points way represent potential true absence, example targeted background sampling sampling within/outside given range.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"","code":"add_pseudoabsence(   df,   field_occurrence = \"observed\",   template = NULL,   settings = getOption(\"ibis.pseudoabsence\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"df sf, data.frame tibble object containing point data. field_occurrence character name column containing presence information (Default: observed). template SpatRaster object aligned predictors (Default: NULL). set NULL, background pseudoabs_settings() SpatRaster object. settings pseudoabs_settings() objects. Absence settings taken ibis_options otherwise (Default).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"data.frame containing newly created pseudo absence points.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"pseudoabs_settings() object can added setup absence points sampled. bias parameter can set specify bias layer sample , instance layer accessibility. Note modelling several datasets, might make sense check across datasets whether certain areas truly absent. default, pseudo-absence points sampled areas already presence points.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"method removes columns input df object field_occurrence column coordinate columns (created already present).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/add_pseudoabsence.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Add pseudo-absence points to a point data set — add_pseudoabsence","text":"Stolar, J., & Nielsen, S. E. (2015). Accounting spatially biased sampling effort presence‐species distribution modelling. Diversity Distributions, 21(5), 595-608. Bird, T.J., Bates, .E., Lefcheck, J.S., Hill, N.., Thomson, R.J., Edgar, G.J., Stuart-Smith, R.D., Wotherspoon, S., Krkosek, M., Stuart-Smith, J.F. Pecl, G.T., 2014. Statistical solutions error bias global citizen science datasets. Biological Conservation, 173, pp.144-154.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":null,"dir":"Reference","previous_headings":"","what":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"data projection template, alignment computed reprojection . data already projection, data set cropped aggregated prior resampling order reduce computation time.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"","code":"alignRasters(data, template, method = \"bilinear\", func = mean, cl = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"data SpatRaster object resampled. template SpatRaster sf object geometry can extracted. method method resampling (Options: \"near\" \"bilinear\"). func function resampling (Default: mean). cl logical value multicore computation used (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"New SpatRaster object aligned supplied template layer.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"Nearest Neighbour resampling (near) recommended discrete bilinear resampling recommended continuous data. See also help terra::resample options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/alignRasters.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Align a SpatRaster object to another by harmonizing geometry and\nextend. — alignRasters","text":"","code":"if (FALSE) {  # Align one raster to another  ras1 <- alignRasters( ras1, ras2, method = \"near\", cl = FALSE) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/as.Id.html","id":null,"dir":"Reference","previous_headings":"","what":"As Id — as.Id","title":"As Id — as.Id","text":"Id","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/as.Id.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"As Id — as.Id","text":"","code":"as.Id(x, ...)  # S3 method for character as.Id(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/as.Id.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"As Id — as.Id","text":"x character converted id. ... arguements","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":null,"dir":"Reference","previous_headings":"","what":"Bivariate plot wrapper for distribution objects — bivplot","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"Often intention display predictions made SDM, also uncertainty prediction. Uncertainty estimated either directly model calculating variation prediction values among set models. particular Bayesian engines can produce mean estimates fitted responses, also pixel-based estimates uncertainty posterior standard deviation (SD) coefficient variation given prediction. function makes use \"biscale\" R-package create bivariate plots fitted distribution object, allowing visualize two variables . mostly thought convenience function create bivariate plots quick visualization. Supported Inputs either single trained Bayesian DistributionModel uncertainty output ensemble() call. cases, users make sure \"xvar\" \"yvar\" set accordingly.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"","code":"bivplot(   mod,   xvar = \"mean\",   yvar = \"sd\",   plot = TRUE,   fname = NULL,   title = NULL,   col = \"BlueGold\",   ... )  # S4 method for ANY bivplot(   mod,   xvar = \"mean\",   yvar = \"sd\",   plot = TRUE,   fname = NULL,   title = NULL,   col = \"BlueGold\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"mod trained DistributionModel alternatively SpatRaster object prediction model within. xvar character denoting value x-axis (Default: 'mean'). yvar character denoting value y-axis (Default: 'sd'). plot logical indication whether result plotted (Default: TRUE)? fname character specifying output filename created figure written . title Allows respecify title character (Default:NULL). col character stating colour palette use. either predefined value vector colours. See \"biscale::bi_pal_manual\". Default: \"BlueGold\". ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"Saved bivariate plot 'fname' specified, otherwise plot.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/bivplot.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Bivariate plot wrapper for distribution objects — bivplot","text":"function requires biscale package installed. Although work around without package developed, deemed necessary point. See also gist.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":null,"dir":"Reference","previous_headings":"","what":"Check objects in the package for common errors or issues — check","title":"Check objects in the package for common errors or issues — check","text":"always enough data sufficient information robustly infer suitable habitat niche species. many SDM algorithms essentially regression models, similar assumptions model convergence, homogeneity residuals inferrence usually apply (although often ignored). function simply checks respective input object common issues mistakes.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Check objects in the package for common errors or issues — check","text":"","code":"check(obj, stoponwarning = FALSE)  # S4 method for ANY check(obj, stoponwarning = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Check objects in the package for common errors or issues — check","text":"obj BiodiversityDistribution, DistributionModel BiodiversityScenario object. stoponwarning logical check return stop warning raised? (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Check objects in the package for common errors or issues — check","text":"Message outputs","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Check objects in the package for common errors or issues — check","text":"Different checks implemented depending supplied object BiodiversityDistribution Checks less 200 observations TODO: Add rm_insufficient_covs link DistributionModel Check model convergence Check model found Check coefficients exist Check unusal outliers prediction (using 10median absolute deviation) Check threshold larger layer BiodiversityScenario","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Check objects in the package for common errors or issues — check","text":"function likely expanded additional checks future. ideas, please let know per issue.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/check.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Check objects in the package for common errors or issues — check","text":"","code":"if (FALSE) {  # Where mod is an estimated DistributionModel  check(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":null,"dir":"Reference","previous_headings":"","what":"Obtains the coefficients of a trained model — coef","title":"Obtains the coefficients of a trained model — coef","text":"Similar summary, helper function obtains coefficients given DistributionModel object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Obtains the coefficients of a trained model — coef","text":"","code":"# S3 method for DistributionModel coef(object, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Obtains the coefficients of a trained model — coef","text":"object prepared object. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/coef.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Obtains the coefficients of a trained model — coef","text":"models trained machine-learning approaches (e.g. engine_bart etc) function return variable importance estimates rather linear coefficients. Similar can said trained non-linear models.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":null,"dir":"Reference","previous_headings":"","what":"Create distribution modelling procedure — distribution","title":"Create distribution modelling procedure — distribution","text":"function creates object contains data, parameters settings building (integrated) species distribution model. Key functions add data add_biodiversity_poipo like, add_predictors, add_latent_spatial, engine_glmnet similar, add_priors add_offset. creates prototype BiodiversityDistribution object functions. setting input data parameters, model predictions can created via train function predictions created. Additionally, possible specify \"limit\" predictions conducted background. can instance buffered layer certain dispersal distance (Cooper Soberon, 2018) categorical layer representing biomes soil conditions. Another option create constraint constructing minimum convex polygon (MCP) using supplied biodiversity data. option can enabled setting \"limits_method\" \"mcp\". also possible provide small buffer constructed MCP way. See frequently asked question (FAQ) section homepage information. See Details description internal functions available modify summarize data within created object. Note model requires minimum single added biodiversity dataset well specified engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create distribution modelling procedure — distribution","text":"","code":"distribution(   background,   limits = NULL,   limits_method = \"none\",   mcp_buffer = 0,   limits_clip = FALSE )  # S4 method for SpatRaster distribution(   background,   limits = NULL,   limits_method = \"none\",   mcp_buffer = 0,   limits_clip = FALSE )  # S4 method for sf distribution(   background,   limits = NULL,   limits_method = \"none\",   mcp_buffer = 0,   limits_clip = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create distribution modelling procedure — distribution","text":"background Specification modelling background. Must SpatRaster sf object. limits SpatRaster sf object limits prediction surface intersected input data (Default: NULL). limits_method character method used hard limiting projection. Available options \"none\" (Default), \"zones\" \"mcp\". mcp_buffer numeric distance buffer mcp (Default 0). used \"mcp\" used. limits_clip logical limits clip predictors fitting model (TRUE) just prediction (FALSE, default).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create distribution modelling procedure — distribution","text":"BiodiversityDistribution object containing data building biodiversity distribution modelling problem.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create distribution modelling procedure — distribution","text":"function creates BiodiversityDistribution object contains functions stores parameters (pre-)processed data. full list functions available can queried via \"names(object)\". functions intended manipulated directly, rather convenience functions (e.g. \"object$set_predictors()\"). Similarly objects stored BiodiversityDistribution object functions well can queried (e.g. \"names(object)\"). list functions see reference documentation. default, datasets set, \"Waiver\" object returned instead. following objects can stored: object$biodiversity BiodiversityDatasetCollection object added biodiversity data. object$engine \"engine\" object (e.g. engine_inlabru()) function depended added engine. object$predictors PredictorDataset object set predictions. object$priors PriorList object specified priors. object$log Log object captures. Useful high-level functions address objects instance: object$show() generic summary BiodiversityDistribution object contents. Can also called via print. object$get_biodiversity_equations() Lists equations used biodiversity dataset given id. Defaults predictors. object$get_biodiversity_types() Lists type specified biodiversity dataset given id. object$get_extent() Outputs terra::ext modelling region. object$show_background_info() Returns list terra::ext terra::crs. object$get_extent_dimensions() Outputs terra::ext dimension calling \"extent_dimensions()\" function. object$get_predictor_names() Returns character vector names added predictors. object$get_prior_variables() Returns description priors added. functions well better accessed respective wrapper functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create distribution modelling procedure — distribution","text":"Fletcher, R.J., Hefley, T.J., Robertson, E.P., Zuckerberg, B., McCleery, R.., Dorazio, R.M., (2019) practical guide combining data model species distributions. Ecology 100, e02710. https://doi.org/10.1002/ecy.2710 Cooper, Jacob C., Jorge Soberón. \"Creating individual accessible area hypotheses improves stacked species distribution model performance.\" Global Ecology Biogeography 27, . 1 (2018): 156-165.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/distribution.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create distribution modelling procedure — distribution","text":"","code":"# Load background raster background <- terra::rast(system.file(\"extdata/europegrid_50km.tif\",package = \"ibis.iSDM\")) # Define model x <- distribution(background) #> [Setup] 2024-02-06 14:28:51.72418 | Creating distribution object... x #>  #> Background extent:  #>      xmin: -16.064, xmax: 36.322, #>      ymin: 34.95, ymax: 71.535 #>    projection: +proj=longlat +datum=WGS84 +no_defs #>  ---------  #> Biodiversity data: #>    None #>  ---------  #>   predictors:     None #>   priors:          #>   latent:         None #>   log:             #>   engine:         "},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":null,"dir":"Reference","previous_headings":"","what":"Plot effects of trained model — effects","title":"Plot effects of trained model — effects","text":"functions handy wrapper calls default plotting functions model specific engine. Equivalent calling effects fitted distribution function.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Plot effects of trained model — effects","text":"","code":"# S3 method for DistributionModel effects(object, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Plot effects of trained model — effects","text":"object fitted distribution object. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Plot effects of trained model — effects","text":"None.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Plot effects of trained model — effects","text":"models, default coefficients plots available, function attempt generate partial dependency plots instead.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/effects.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Plot effects of trained model — effects","text":"","code":"if (FALSE) { # Where mod is an estimated distribution model mod$effects() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":null,"dir":"Reference","previous_headings":"","what":"Create an empty SpatRaster based on a template — emptyraster","title":"Create an empty SpatRaster based on a template — emptyraster","text":"function creates empty copy provided SpatRaster object. primarily used package create outputs predictions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create an empty SpatRaster based on a template — emptyraster","text":"","code":"emptyraster(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create an empty SpatRaster based on a template — emptyraster","text":"x SpatRaster* object corresponding. ... arguments can passed terra","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create an empty SpatRaster based on a template — emptyraster","text":"empty SpatRaster, .e. cells NA.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/emptyraster.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create an empty SpatRaster based on a template — emptyraster","text":"","code":"require(terra) #> Loading required package: terra #> terra 1.7.71 r <- rast(matrix(1:100, 5, 20)) emptyraster(r) #> class       : SpatRaster  #> dimensions  : 5, 20, 1  (nrow, ncol, nlyr) #> resolution  : 1, 1  (x, y) #> extent      : 0, 20, 0, 5  (xmin, xmax, ymin, ymax) #> coord. ref. :"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Bayesian regression approach sum complementary trees shrink said fit tree regularization prior. BART models provide non-linear highly flexible estimation shown compare favourable among machine learning algorithms (Dorie et al. 2019). Default prior preference trees small (terminal nodes) shrinkage towards 0. package requires \"dbarts\" R-package installed. Many functionalities engine inspired \"embarcadero\" R-package. Users therefore advised cite make heavy use BART.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"","code":"engine_bart(x, iter = 1000, nburn = 250, chains = 4, type = \"response\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"x distribution() (.e. BiodiversityDistribution) object. iter numeric estimate number trees used sum--trees formulation (Default: 1000). nburn numeric estimate burn samples (Default: 250). chains number number chains used (Default: 4). type mode used creating posterior predictions. Either \"link\" \"response\" (Default: \"response\"). ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Prior distributions can furthermore set : probability tree stops node given depth (yet implemented) probability given variable chosen splitting rule probability splitting variable particular value (yet implemented)","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"Carlson, CJ. embarcadero: Species distribution modelling Bayesian additive regression trees r. Methods Ecol Evol. 2020; 11: 850– 858. https://doi.org/10.1111/2041-210X.13389 Dorie, V., Hill, J., Shalit, U., Scott, M., & Cervone, D. (2019). Automated versus --methods causal inference: Lessons learned data analysis competition. Statistical Science, 34(1), 43-68. Vincent Dorie (2020). dbarts: Discrete Bayesian Additive Regression Trees Sampler. R package version 0.9-19. https://CRAN.R-project.org/package=dbarts","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_bart.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for use of Bayesian Additive Regression Trees (BART) — engine_bart","text":"","code":"if (FALSE) { # Add BART as an engine x <- distribution(background) |> engine_bart(iter = 100) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for Bayesian regularized regression models — engine_breg","title":"Engine for Bayesian regularized regression models — engine_breg","text":"Efficient MCMC algorithm linear regression models makes use 'spike--slab' priors modest regularization amount posterior probability subset coefficients.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for Bayesian regularized regression models — engine_breg","text":"","code":"engine_breg(   x,   iter = 10000,   nthread = getOption(\"ibis.nthread\"),   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for Bayesian regularized regression models — engine_breg","text":"x distribution() (.e. BiodiversityDistribution) object. iter numeric number MCMC iterations run (Default: 10000). nthread numeric number CPU-threads use data augmentation. type mode used creating posterior predictions. Either making \"link\" \"response\" (Default: \"response\"). ... none specified parameters passed model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for Bayesian regularized regression models — engine_breg","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for Bayesian regularized regression models — engine_breg","text":"engine provides efficient Bayesian predictions Boom R-package. However note link models functions supported certain functionalities offsets generally available. engines allows estimation linear non-linear effects via \"only_linear\" option specified train.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for Bayesian regularized regression models — engine_breg","text":"Nguyen, K., Le, T., Nguyen, V., Nguyen, T., & Phung, D. (2016, November). Multiple kernel learning data augmentation. Asian Conference Machine Learning (pp. 49-64). PMLR. Steven L. Scott (2021). BoomSpikeSlab: MCMC Spike Slab Regression. R package version 1.2.4. https://CRAN.R-project.org/package=BoomSpikeSlab","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_breg.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for Bayesian regularized regression models — engine_breg","text":"","code":"if (FALSE) { # Add BREG as an engine x <- distribution(background) |> engine_breg(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":null,"dir":"Reference","previous_headings":"","what":"Use of Gradient Descent Boosting for model estimation — engine_gdb","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"Gradient descent boosting efficient way optimize loss function generalized linear additive model (GAMs available \"mgcv\" R-package). furthermore automatically regularizes fit, thus resulting model contains covariates whose baselearners influence response. Depending type add_biodiversity data, either poisson process models logistic regressions estimated. \"only_linear\" term train set FALSE, splines added estimation, thus providing non-linear additive inference.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"","code":"engine_gdb(   x,   iter = 2000,   learning_rate = 0.1,   empirical_risk = \"inbag\",   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"x distribution() (.e. BiodiversityDistribution) object. iter integer giving number boosting iterations (Default: 2e3L). learning_rate bounded numeric value 0 1 defining shrinkage parameter. empirical_risk method empirical risk calculation. Available options 'inbag', 'oobag' 'none'. (Default: 'inbag'). type mode used creating posterior predictions. Either making \"link\", \"response\" \"class\" (Default: \"response\"). ... variables control parameters","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":": package requires \"mboost\" R-package installed. philosophy somewhat related engine_xgboost \"XGBoost\" R-package, however providing additional desirable features make estimation quicker particularly useful spatial projections. instance ability specifically add spatial baselearners via add_latent_spatial specification monotonically constrained priors via GDBPrior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"Hofner, B., Mayr, ., Robinzonov, N., & Schmid, M. (2014). Model-based boosting R: hands-tutorial using R package mboost. Computational statistics, 29(1-2), 3-35. Hofner, B., Müller, J., Hothorn, T., (2011). Monotonicity-constrained species distribution models. Ecology 92, 1895–901. Mayr, ., Hofner, B. Schmid, M. (2012). importance knowing stop - sequential stopping rule component-wise gradient boosting. Methods Information Medicine, 51, 178–186.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_gdb.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use of Gradient Descent Boosting for model estimation — engine_gdb","text":"","code":"if (FALSE) { # Add GDB as an engine x <- distribution(background) |> engine_gdb(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for Generalized linear models (GLM) — engine_glm","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"engine implements basic generalized linear modle (GLM) creating species distribution models. main purpose engine support basic, dependency-free method inference projection can used within package examples vignettes. said, engine fully functional engine. basic implementation GLMs part general class oflinear models - exception offsets - minimal options integrate sources information priors joint integration. general recommendation engine_glmnet() instead regularization support. However basic GLMs can cases useful quick projections ensemble() small models (practice common rare species).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"","code":"engine_glm(x, control = NULL, type = \"response\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"x distribution() (.e. BiodiversityDistribution) object. control list containing parameters controlling fitting process (Default: NULL). type mode used creating posterior predictions. Either making \"link\" \"response\" (Default: \"response\"). ... parameters passed stats::glm().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"engine essentially wrapper stats::glm.fit(), however customized settings support offsets weights.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"Hastie, T. J. Pregibon, D. (1992) Generalized linear models. Chapter 6 Statistical Models S eds J. M. Chambers T. J. Hastie, Wadsworth & Brooks/Cole.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glm.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for Generalized linear models (GLM) — engine_glm","text":"","code":"# Load background background <- terra::rast(system.file('extdata/europegrid_50km.tif', package='ibis.iSDM',mustWork = TRUE))  # Add GLM as an engine x <- distribution(background) |> engine_glm() #> [Setup] 2024-02-06 14:28:52.694211 | Creating distribution object..."},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for regularized regression models — engine_glmnet","title":"Engine for regularized regression models — engine_glmnet","text":"engine allows estimation linear coefficients using either ridge, lasso elastic net regressions techniques. Backbone engine glmnet R-package commonly used SDMs, including popular 'maxnet' (e.g. Maxent) package. Ultimately engine equivalent engine_breg, \"frequentist\" setting. user aim emulate model closely resembles maxent within ibis.iSDM modelling framework, package best way . Compared 'maxnet' R-package, number efficiency settings implemented particular cross-validation alpha lambda values. Limited amount prior information can specified engine, specifically via offsets GLMNETPrior, allow specify priors regularization constants.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for regularized regression models — engine_glmnet","text":"","code":"engine_glmnet(   x,   alpha = 0,   nlambda = 100,   lambda = NULL,   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for regularized regression models — engine_glmnet","text":"x distribution() (.e. BiodiversityDistribution) object. alpha numeric giving elasticnet mixing parameter, 0 1. alpha=1 lasso penalty, alpha=0 ridge penalty (Default: 0). nlambda numeric giving number lambda values used (Default: 100). lambda numeric user supplied estimate lambda. Usually best let parameter determined deterministically (Default: NULL). type mode used creating posterior predictions. Either making \"link\" \"response\" (Default: \"response\"). ... parameters passed glmnet.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for regularized regression models — engine_glmnet","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for regularized regression models — engine_glmnet","text":"Regularized regressions effectively GLMs fitted ridge, lasso elastic-net regularization. chosen critical dependent alpha value: * alpha equal 0 ridge regularization used. Ridge regularization property remove variables entirely, instead sets coefficients 0. * alpha equal 1 lasso regularization used. Lassos tend remove coefficients fully final model improve loss function. * alpha values 0 1 elastic-net regularization used, essentially combination two. optimal lambda parameter can determined via cross-validation. option set \"varsel\" train() \"reg\".","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for regularized regression models — engine_glmnet","text":"Jerome Friedman, Trevor Hastie, Robert Tibshirani (2010). Regularization Paths Generalized Linear Models via Coordinate Descent. Journal Statistical Software, 33(1), 1-22. URL https://www.jstatsoft.org/v33/i01/. Renner, .W., Elith, J., Baddeley, ., Fithian, W., Hastie, T., Phillips, S.J., Popovic, G. Warton, D.., 2015. Point process models presence‐analysis. Methods Ecology Evolution, 6(4), pp.366-379. Fithian, W. & Hastie, T. (2013) Finite-sample equivalence statistical models presence-data. Annals Applied Statistics 7, 1917–1939","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_glmnet.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for regularized regression models — engine_glmnet","text":"","code":"if (FALSE) { # Add GLMNET as an engine x <- distribution(background) |> engine_glmnet(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":null,"dir":"Reference","previous_headings":"","what":"Use INLA as engine — engine_inla","title":"Use INLA as engine — engine_inla","text":"Allows full Bayesian analysis linear additive models using Integrated Nested Laplace approximation. Engine largely superceded engine_inlabru package users advised us one, unless specific options required.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use INLA as engine — engine_inla","text":"","code":"engine_inla(   x,   optional_mesh = NULL,   optional_projstk = NULL,   max.edge = NULL,   offset = NULL,   cutoff = NULL,   proj_stepsize = NULL,   timeout = NULL,   strategy = \"auto\",   int.strategy = \"eb\",   barrier = FALSE,   type = \"response\",   area = \"gpc2\",   nonconvex.bdry = FALSE,   nonconvex.convex = -0.15,   nonconvex.concave = -0.05,   nonconvex.res = 40,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use INLA as engine — engine_inla","text":"x distribution() (.e. BiodiversityDistribution) object. optional_mesh directly supplied \"INLA\" mesh (Default: NULL) optional_projstk directly supplied projection stack. Useful projection stack identical multiple species (Default: NULL) max.edge largest allowed triangle edge length, must scale units coordinates. Default educated guess (Default: NULL). offset interpreted numeric factor relative approximate data diameter. Default educated guess (Default: NULL). cutoff minimum allowed distance points mesh. Default educated guess (Default: NULL). proj_stepsize stepsize coordinate units cells projection grid (Default: NULL). timeout Specify timeout INLA models sec. Afterwards passed. strategy approximation use joint posterior. Options \"auto\" (\"default\"), \"adaptative\", \"gaussian\", \"simplified.laplace\" & \"laplace\". int.strategy Integration strategy. Options \"auto\",\"grid\", \"eb\" (\"default\") & \"ccd\". See also https://groups.google.com/g/r-inla-discussion-group/c/hDboQsJ1Mls barrier barrier model added model? type mode used creating posterior predictions. Either summarizing linear \"predictor\" \"response\" (Default: \"response\"). area Accepts character denoting type area calculation done mesh (Default: 'gpc2'). nonconvex.bdry Create non-convex boundary hulls instead (Default: FALSE) yet implemented nonconvex.convex Non-convex minimal extension radius convex curvature yet implemented nonconvex.concave Non-convex minimal extension radius concave curvature yet implemented nonconvex.res Computation resolution nonconvex.hulls yet implemented ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use INLA as engine — engine_inla","text":"engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use INLA as engine — engine_inla","text":"INLA engines require specification mesh needs provided \"optional_mesh\" parameter. Otherwise mesh created based best guesses data spread. good mesh needs triangles regular possible size shape: equilateral. * \"max.edge\": largest allowed triangle edge length, must scale units coordinates Lower bounds affect density triangles * \"offset\": automatic extension distance mesh positive: scale units. negative, interpreted factor relative approximate data diameter .e., value -0.10 add 10% data diameter outer extension. * \"cutoff\": minimum allowed distance points, means points closer distance supplied value replaced single vertex. critical points close , either point locations domain boundary. * \"proj_stepsize\": stepsize spatial predictions, affects spatial grain outputs created. Priors can set via INLAPrior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Use INLA as engine — engine_inla","text":"INLA Meshes generated, substantially influences prediction outcomes. See Dambly et al. (2023).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use INLA as engine — engine_inla","text":"Havard Rue, Sara Martino, Nicholas Chopin (2009), Approximate Bayesian Inference Latent Gaussian Models Using Integrated Nested Laplace Approximations (discussion), Journal Royal Statistical Society B, 71, 319-392. Finn Lindgren, Havard Rue, Johan Lindstrom (2011). Explicit Link Gaussian Fields Gaussian Markov Random Fields: Stochastic Partial Differential Equation Approach (discussion), Journal Royal Statistical Society B, 73(4), 423-498. Simpson, Daniel, Janine B. Illian, S. H. Sørbye, Håvard Rue. 2016. “Going Grid: Computationally Efficient Inference Log-Gaussian Cox Processes.” Biometrika 1 (103): 49–70. Dambly, L. ., Isaac, N. J., Jones, K. E., Boughey, K. L., & O'Hara, R. B. (2023). Integrated species distribution models fitted INLA sensitive mesh parameterisation. Ecography, e06391.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inla.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use INLA as engine — engine_inla","text":"","code":"if (FALSE) { # Add INLA as an engine (with a custom mesh) x <- distribution(background) |> engine_inla(mesh = my_mesh) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":null,"dir":"Reference","previous_headings":"","what":"Use inlabru as engine — engine_inlabru","title":"Use inlabru as engine — engine_inlabru","text":"Model components specified general inputs mapping methods latent variables, predictors specified via general R expressions, separate expressions observation likelihood model multi-likelihood models. inlabru engine - similar engine_inla function acts wrapper INLA, albeit \"inlabru\" number convenience functions implemented make particular predictions new data much straight forward (e.g. via posterior simulation instead fitting). Since recent versions \"inlabru\" also supports addition multiple likelihoods, therefore allowing full integrated inference.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use inlabru as engine — engine_inlabru","text":"","code":"engine_inlabru(   x,   optional_mesh = NULL,   max.edge = NULL,   offset = NULL,   cutoff = NULL,   proj_stepsize = NULL,   strategy = \"auto\",   int.strategy = \"eb\",   area = \"gpc2\",   timeout = NULL,   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"source","dir":"Reference","previous_headings":"","what":"Source","title":"Use inlabru as engine — engine_inlabru","text":"https://inlabru-org.github.io/inlabru/articles/","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use inlabru as engine — engine_inlabru","text":"x distribution() (.e. BiodiversityDistribution) object. optional_mesh directly supplied \"INLA\" mesh (Default: NULL) max.edge largest allowed triangle edge length, must scale units coordinates. Default educated guess (Default: NULL). offset interpreted numeric factor relative approximate data diameter. Default educated guess (Default: NULL). cutoff minimum allowed distance points mesh. Default educated guess (Default: NULL). proj_stepsize stepsize coordinate units cells projection grid (Default: NULL) strategy approximation use joint posterior. Options \"auto\" (\"default\"), \"adaptative\", \"gaussian\", \"simplified.laplace\" & \"laplace\". int.strategy Integration strategy. Options \"auto\", \"grid\", \"eb\" (\"default\") & \"ccd\". area Accepts character denoting type area calculation done mesh (Default: 'gpc2'). timeout Specify timeout INLA models sec. Afterwards passed. type mode used creating posterior predictions. Either summarizing linear \"predictor\" \"response\" (Default:\"response\"). ... variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use inlabru as engine — engine_inlabru","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use inlabru as engine — engine_inlabru","text":"INLA engines require specification mesh needs provided \"optional_mesh\" parameter. Otherwise mesh created based best guesses data spread. good mesh needs triangles regular possible size shape: equilateral. * \"max.edge\": largest allowed triangle edge length, must scale units coordinates Lower bounds affect density triangles * \"offset\": automatic extension distance mesh positive: scale units. negative, interpreted factor relative approximate data diameter .e., value -0.10 add 10% data diameter outer extension. * \"cutoff\": minimum allowed distance points, means points closer distance supplied value replaced single vertex. critical points close , either point locations domain boundary. * \"proj_stepsize\": stepsize spatial predictions, affects spatial grain outputs created. Priors can set via INLAPrior.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Use inlabru as engine — engine_inlabru","text":"INLA Meshes generated, substantially influences prediction outcomes. See Dambly et al. (2023).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use inlabru as engine — engine_inlabru","text":"Bachl, F. E., Lindgren, F., Borchers, D. L., & Illian, J. B. (2019). inlabru: R package Bayesian spatial modelling ecological survey data. Methods Ecology Evolution, 10(6), 760-766. Simpson, Daniel, Janine B. Illian, S. H. Sørbye, Håvard Rue. 2016. “Going Grid: Computationally Efficient Inference Log-Gaussian Cox Processes.” Biometrika 1 (103): 49–70. Dambly, L. ., Isaac, N. J., Jones, K. E., Boughey, K. L., & O'Hara, R. B. (2023). Integrated species distribution models fitted INLA sensitive mesh parameterisation. Ecography, e06391.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_inlabru.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use inlabru as engine — engine_inlabru","text":"","code":"if (FALSE) { # Add inlabru as an engine x <- distribution(background) |> engine_inlabru() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":null,"dir":"Reference","previous_headings":"","what":"Use Stan as engine — engine_stan","title":"Use Stan as engine — engine_stan","text":"Stan probabilistic programming language can used specify types statistical linear non-linear regression models. Stan provides full Bayesian inference continuous-variable models Markov chain Monte Carlo methods -U-Turn sampler, adaptive form Hamiltonian Monte Carlo sampling. Stan code written separately function acts compiler build stan-model. Requires \"cmdstanr\" package installed!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Use Stan as engine — engine_stan","text":"","code":"engine_stan(   x,   chains = 4,   iter = 2000,   warmup = floor(iter/2),   init = \"random\",   cores = getOption(\"ibis.nthread\"),   algorithm = \"sampling\",   control = list(adapt_delta = 0.95),   type = \"response\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Use Stan as engine — engine_stan","text":"x distribution() (.e. BiodiversityDistribution) object. chains positive integer specifying number Markov chains (Default: 4 chains). iter positive integer specifying number iterations chain (including warmup). (Default: 2000). warmup positive integer specifying number warmup (aka burnin) iterations per chain. step-size adaptation (Default: TRUE), also controls number iterations adaptation run (hence warmup samples used inference). number warmup iterations smaller iter default iter/2. init Initial values parameters (Default: 'random'). Can also specified list (see: \"rstan::stan\") cores set NULL take values specified ibis option getOption('ibis.nthread'). algorithm Mode used sample posterior. Available options \"sampling\", \"optimize\", \"variational\". See \"cmdstanr\" package details. (Default: \"sampling\"). control See \"rstan::stan\" details specifying controls. type mode used creating posterior predictions. Either summarizing linear \"predictor\" \"response\" (Default: \"response\"). ... variables","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Use Stan as engine — engine_stan","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Use Stan as engine — engine_stan","text":"default posterior obtained sampling, however stan also supports approximate inference forms penalized maximum likelihood estimation (see Carpenter et al. 2017).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Use Stan as engine — engine_stan","text":"function obj$stancode() can used print stancode model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Use Stan as engine — engine_stan","text":"Jonah Gabry Rok Češnovar (2021). cmdstanr: R Interface 'CmdStan'. https://mc-stan.org/cmdstanr, https://discourse.mc-stan.org. Carpenter, B., Gelman, ., Hoffman, M. D., Lee, D., Goodrich, B., Betancourt, M., ... & Riddell, . (2017). Stan: probabilistic programming language. Journal statistical software, 76(1), 1-32. Piironen, J., & Vehtari, . (2017). Sparsity information regularization horseshoe shrinkage priors. Electronic Journal Statistics, 11(2), 5018-5051.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_stan.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Use Stan as engine — engine_stan","text":"","code":"if (FALSE) { # Add Stan as an engine x <- distribution(background) |> engine_stan(iter = 1000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":null,"dir":"Reference","previous_headings":"","what":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"Allows estimate eXtreme gradient descent boosting tree-based linear boosting regressions. XGBoost engine flexible, yet powerful engine many customization options, supporting multiple options perform single multi-class regression classification tasks. full list options users advised look xgboost::xgb.train help file https://xgboost.readthedocs.io.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"","code":"engine_xgboost(   x,   booster = \"gbtree\",   iter = 8000L,   learning_rate = 0.001,   gamma = 6,   reg_lambda = 0,   reg_alpha = 0,   max_depth = 2,   subsample = 0.75,   colsample_bytree = 0.4,   min_child_weight = 3,   nthread = getOption(\"ibis.nthread\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"x distribution() (.e. BiodiversityDistribution) object. booster character booster use. Either \"gbtree\" \"gblinear\" (Default: gblinear) iter numeric value giving maximum number boosting iterations cross-validation (Default: 8e3L). learning_rate numeric value indicating learning rate (eta). Lower values generally better also computationally costly. (Default: 1e-3) gamma numeric regularization parameter model. Lower values better estimates (Default: 3). Also see \"reg_lambda\" parameter L2 regularization weights reg_lambda numeric L2 regularization term weights (Default: 0). reg_alpha numeric L1 regularization term weights (Default: 0). max_depth numeric Maximum depth tree (Default: 3). subsample numeric ratio used subsampling prevent overfitting. Also used creating random tresting dataset (Default: 0.75). colsample_bytree numeric Sub-sample ratio columns constructing tree (Default: 0.4). min_child_weight numeric Broadly related number instances necessary node (Default: 3). nthread numeric number CPU-threads use. ... none specified parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"Engine.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"default parameters set relatively conservative reduce overfitting. XGBoost supports specification monotonic constraints certain variables. Within ibis possible via XGBPrior. However constraints available \"gbtree\" baselearners.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"'Machine learning statistics minus checking models assumptions‘ ~ Brian D. Ripley, useR! 2004, Vienna","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"Tianqi Chen Carlos Guestrin, \"XGBoost: Scalable Tree Boosting System\", 22nd SIGKDD Conference Knowledge Discovery Data Mining, 2016, https://arxiv.org/abs/1603.02754","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/engine_xgboost.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Engine for extreme gradient boosting (XGBoost) — engine_xgboost","text":"","code":"if (FALSE) { # Add xgboost as an engine x <- distribution(background) |> engine_xgboost(iter = 4000) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to create an ensemble of multiple fitted models — ensemble","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"Ensemble models calculated multiple models often shown outcompete single model comparative assessments (Valavi et al. 2022). function creates ensemble multiple provided distribution models fitted ibis.iSDM-package. model estimated predictions given method optional uncertainty form standard deviation similar. layer parameter can specified part prediction averaged ensemble. can instance mean prediction /standard deviation sd. See Details overview different methods. Also returns coefficient variation (cv) output ensemble, note interpreted measure model uncertainty capture parameter uncertainty individual models; rather reflects variation among predictions can due many factors including simply differences model complexity.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"","code":"ensemble(   ...,   method = \"mean\",   weights = NULL,   min.value = NULL,   layer = \"mean\",   normalize = FALSE,   uncertainty = \"cv\",   apply_threshold = TRUE )  # S4 method for ANY ensemble(   ...,   method = \"mean\",   weights = NULL,   min.value = NULL,   layer = \"mean\",   normalize = FALSE,   uncertainty = \"cv\",   apply_threshold = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"... Provided DistributionModel SpatRaster objects. method Approach ensemble created. See details available options (Default: 'mean'). weights (Optional) weights provided ensemble function weighted means constructed (Default: NULL). min.value optional numeric stating minimum value needs surpassed layer calculating ensemble (Default: NULL). layer character layer taken prediction (Default: 'mean'). set NULL ignore layer names ensembles SpatRaster objects. normalize logical whether inputs ensemble normalized scale 0-1 (Default: FALSE). uncertainty character indicating uncertainty among models calculated. Available options include \"none\", standard deviation (\"sd\"), average PCA axes except first \"pca\", coefficient variation (\"cv\", Default) range lowest highest value (\"range\"). apply_threshold logical flag (Default: TRUE) specifying whether threshold values also created via \"method\". applies works DistributionModel thresholds found.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"SpatRaster object containing ensemble provided predictions specified method coefficient variation across models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"Possible options creating ensemble includes: 'mean' - Calculates mean several predictions. 'median' - Calculates median several predictions. 'max' - maximum value across predictions. 'min' - minimum value across predictions. 'weighted.mean' - Calculates weighted mean. Weights supplied separately (e.g. TSS). 'min.sd' - Ensemble created minimizing uncertainty among predictions. 'threshold.frequency' - Returns ensemble based threshold frequency (simple count). Requires thresholds computed. 'pca' - Calculates PCA predictions algorithm extract first axis (one explaining variation). addition different ensemble methods, minimal threshold (min.value) can set needs surpassed averaging. default option used (Default: NULL). Note default band layer parameter composited. supported model summary statistics posterior (e.g. 'sd') can specified.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"list supplied, assumed entry list fitted DistributionModel object. Take care create ensemble models constructed different link functions, e.g. logistic vs log. case \"normalize\" parameter set.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"Valavi, R., Guillera‐Arroita, G., Lahoz‐Monfort, J. J., & Elith, J. (2022). Predictive performance presence‐species distribution models: benchmark study reproducible code. Ecological Monographs, 92(1), e01486.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to create an ensemble of multiple fitted models — ensemble","text":"","code":"# Method works for fitted models as well as as rasters r1 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,  xmax = 1.5, ymin = -1.5, ymax = 1.5, vals = rnorm(3600,mean = .5,sd = .1)) r2 <- terra::rast(nrows = 10, ncols = 10, res = 0.05, xmin = -1.5,  xmax = 1.5, ymin = -1.5, ymax = 1.5, vals = rnorm(3600,mean = .5,sd = .5)) names(r1) <- names(r2) <- \"mean\"  # Assumes previously computed predictions ex <- ensemble(r1, r2, method = \"mean\")  terra::plot(ex)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"Similar ensemble() function, function creates ensemble partial responses provided distribution models fitted ibis.iSDM-package. layer parameter can specified part partial prediction averaged ensemble (given). can instance mean prediction /standard deviation sd. Ensemble partial also called one input DistributionModel object provided partial. default ensemble partial responses created average across models uncertainty standard deviation responses.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"","code":"ensemble_partial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   normalize = TRUE )  # S4 method for ANY ensemble_partial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   normalize = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"... Provided DistributionModel objects partial responses can called. future provided data.frames might supported well. x.var character variable ensemble created. method Approach ensemble created. See details options (Default: 'mean'). layer character layer taken prediction (Default: 'mean'). set NULL ignore layer names ensembles SpatRaster objects. newdata optional data.frame SpatRaster object supplied model (DefaultL NULL). object needs identical names original predictors. normalize logical whether inputs ensemble normalized scale 0-1 (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"data.frame combined partial effects supplied models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"Possible options creating ensemble includes: 'mean' - Calculates mean several predictions. 'median' - Calculates median several predictions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"list supplied, assumed entry list fitted DistributionModel object. Take care create ensemble models constructed different link functions, e.g. logistic vs log. default response functions model normalized.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_partial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to create an ensemble of partial effects from multiple models — ensemble_partial","text":"","code":"if (FALSE) {  # Assumes previously computed models  ex <- ensemble_partial(mod1, mod2, mod3, method = \"mean\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"Similar ensemble() function, function creates ensemble partial responses provided distribution models fitted ibis.iSDM-package. layer parameter can specified part partial prediction averaged ensemble (given). can instance mean prediction /standard deviation sd. Ensemble partial also called one input DistributionModel object provided partial. default ensemble partial responses created average across models uncertainty standard deviation responses.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"","code":"ensemble_spartial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   min.value = NULL,   normalize = TRUE )  # S4 method for ANY ensemble_spartial(   ...,   x.var,   method = \"mean\",   layer = \"mean\",   newdata = NULL,   min.value = NULL,   normalize = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"... Provided DistributionModel objects partial responses can called. future provided data.frames might supported well. x.var character variable ensemble created. method Approach ensemble created. See details options (Default: 'mean'). layer character layer taken prediction (Default: 'mean'). set NULL ignore layer names ensembles SpatRaster objects. newdata optional data.frame SpatRaster object supplied model (DefaultL NULL). object needs identical names original predictors. min.value optional numeric stating minimum value needs surpassed layer calculating ensemble (Default: NULL). normalize logical whether inputs ensemble normalized scale 0-1 (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"SpatRaster object combined partial effects supplied models.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"Possible options creating ensemble includes: 'mean' - Calculates mean several predictions. 'median' - Calculates median several predictions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"list supplied, assumed entry list fitted DistributionModel object. Take care create ensemble models constructed different link functions, e.g. logistic vs log. default response functions model normalized.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ensemble_spartial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to create an ensemble of spartial effects from multiple models — ensemble_spartial","text":"","code":"if (FALSE) {  # Assumes previously computed models  ex <- ensemble_spartial(mod1, mod2, mod3, method = \"mean\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"function expects downscaled GLOBIOM output created BIOCLIMA project. Likely little use anyone outside IIASA.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"","code":"formatGLOBIOM(   fname,   oftype = \"raster\",   ignore = NULL,   period = \"all\",   template = NULL,   shares_to_area = FALSE,   use_gdalutils = FALSE,   verbose = getOption(\"ibis.setupmessages\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"fname filename character pointing GLOBIOM output netCDF format. oftype character denoting output type (Default: 'raster'). ignore vector variables ignored (Default: NULL). period character limiting period returned formatted data. Options include \"reference\" first entry, \"projection\" entries first, \"\" entries (Default: \"reference\"). template optional SpatRaster object towards projects transformed. shares_to_area logical whether shares corrected areas (identified). use_gdalutils (Deprecated) logical use gdalutils hack-around. verbose logical whether chatty.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"SpatRaster stack formatted GLOBIOM predictors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/formatGLOBIOM.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to format a prepared GLOBIOM netCDF file for use in Ibis.iSDM — formatGLOBIOM","text":"","code":"if (FALSE) { # Expects a filename pointing to a netCDF file. covariates <- formatGLOBIOM(fname) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":null,"dir":"Reference","previous_headings":"","what":"Small helper function to obtain predictions from an object — get_data","title":"Small helper function to obtain predictions from an object — get_data","text":"function short helper function return fitted data DistributionModel BiodiversityScenario object. can used easily obtain example estimated prediction model projected scenario scenario() object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Small helper function to obtain predictions from an object — get_data","text":"","code":"get_data(obj, what = NULL)  # S4 method for ANY get_data(obj, what = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Small helper function to obtain predictions from an object — get_data","text":"obj Provided DistributionModel BiodiversityScenario object. character specific layer returned existing (Default: NULL).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Small helper function to obtain predictions from an object — get_data","text":"SpatRaster \"stars\" object depending input.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Small helper function to obtain predictions from an object — get_data","text":"function essentially identical querying internal function x$get_data() object. However attempt lazy character matching supplied.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_data.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Small helper function to obtain predictions from an object — get_data","text":"","code":"if (FALSE) {  # Assumes previously computed model  get_data(fit) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"function performs nearest neighbour matching biodiversity observations independent predictors, operates directly provided data.frames. Note despite parallized function can rather slow large data volumes data!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"","code":"get_ngbvalue(   coords,   env,   longlat = TRUE,   field_space = c(\"x\", \"y\"),   cheap = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"coords matrix, data.frame sf object. env data.frame object predictors. longlat logical variable indicating whether projection long-lat. field_space vector highlight columns coordinates extracted (Default: c('x','y')). cheap logical variable whether dataset considered large faster computation help. ... options.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"data.frame extracted covariate data provided data point.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"Nearest neighbour matching done via geodist R-package (geodist::geodist).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"multiple values equal distance nearest neighbour check, results default averaged.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"Mark Padgham Michael D. Sumner (2021). geodist: Fast, Dependency-Free Geodesic Distance Calculations. R package version 0.0.7. https://CRAN.R-project.org/package=geodist","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_ngbvalue.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to extract nearest neighbour predictor values of provided points — get_ngbvalue","text":"","code":"if (FALSE) {  # Create matchup table tab <- get_ngbvalue( coords = coords, # Coordinates                      env = env # Data.frame with covariates and coordinates                   ) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Create priors from an existing distribution model — get_priors","title":"Create priors from an existing distribution model — get_priors","text":"Often can make sense fit additional model get grasp range values \"beta\" parameters can take. function takes existing BiodiversityDistribution object creates PriorList object . resulting object can used add instance priors new model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create priors from an existing distribution model — get_priors","text":"","code":"get_priors(mod, target_engine, ...)  # S4 method for ANY,character get_priors(mod, target_engine, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create priors from an existing distribution model — get_priors","text":"mod fitted DistributionModel object. instead BiodiversityDistribution object passed function, simply returns contained priors used estimation (). target_engine character priors created. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create priors from an existing distribution model — get_priors","text":"engines support priors similar ways. See vignettes help pages topic!","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create priors from an existing distribution model — get_priors","text":"","code":"if (FALSE) {  mod <- distribution(background) |>     add_predictors(covariates) |>     add_biodiversity_poipo(points) |>     engine_inlabru() |>     train()  get_priors(mod, target_engine = \"BART\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to extract directly the raster value of provided points — get_rastervalue","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"function simply extracts values provided SpatRaster, SpatRasterDataset SpatRasterCollection object. points NA values extracted small buffer applied try obtain remaining values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"","code":"get_rastervalue(coords, env, ngb_fill = TRUE, rm.na = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"coords data.frame, matrix sf object. env SpatRaster object provided predictors. ngb_fill logical whether cells interpolated neighbouring values. rm.na logical parameter - set - removes rows missing data point (NA) result.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"data.frame extracted covariate data provided data point.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"essentially wrapper terra::extract.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/get_rastervalue.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to extract directly the raster value of provided points — get_rastervalue","text":"","code":"if (FALSE) { # Extract values vals <- get_rastervalue(coords, env) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis.iSDM.html","id":null,"dir":"Reference","previous_headings":"","what":"ibis.iSDM — ibis.iSDM","title":"ibis.iSDM — ibis.iSDM","text":"Integrated framework modelling distribution species ecosystems suitability framing. package allows estimation integrated species distribution models (iSDM) based several sources evidence provided presence-presence-absence datasets. makes heavy use point-process models estimating habitat suitability allows include spatial latent effects priors estimation. 'ibis.iSDM' supports number engines Bayesian non-parametric machine learning estimation. , 'ibis.iSDM' specifically customized support spatial-temporal projections habitat suitability future.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis.iSDM.html","id":"author","dir":"Reference","previous_headings":"","what":"Author","title":"ibis.iSDM — ibis.iSDM","text":"Maintainer: Martin Jung jung@iiasa.ac.(ORCID) [copyright holder] contributors: Maximilian H.K. Hesselbarth hesselbarth@iiasa.ac.(ORCID) [contributor]","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":null,"dir":"Reference","previous_headings":"","what":"Install ibis dependencies — ibis_dependencies","title":"Install ibis dependencies — ibis_dependencies","text":"dependencies (R-Packages) ibis.iSDM relies intention added Description file keep number mandatory dependencies small enable package run even systems might libraries pre-installed. function provides convenience wrapper install missing dependencies needed. furthermore checks packages require updating updates needed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Install ibis dependencies — ibis_dependencies","text":"","code":"ibis_dependencies(deps = getOption(\"ibis.dependencies\"), update = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Install ibis dependencies — ibis_dependencies","text":"deps vector names packages installed (Default: \"ibis.dependencies\" ibis_options). update logical flag whether (installed) packages also checked updates (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Install ibis dependencies — ibis_dependencies","text":"Nothing. Packages installed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Install ibis dependencies — ibis_dependencies","text":"INLA handled special way available via cran.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_dependencies.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Install ibis dependencies — ibis_dependencies","text":"","code":"if (FALSE) {   # Install and update all dependencies   ibis_dependencies() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":null,"dir":"Reference","previous_headings":"","what":"Options to set up ibis for parallel processing with future — ibis_future","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"Options set ibis parallel processing future","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"","code":"ibis_future(   cores = getOption(\"ibis.nthread\"),   strategy = getOption(\"ibis.futurestrategy\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"cores numeric number stating number cores use. strategy character denoting strategy used future. See help future options. (Default: \"multisession\").","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"None","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_future.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Options to set up ibis for parallel processing with future — ibis_future","text":"","code":"if (FALSE) { # Starts future job ibis_future(cores = 4) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":null,"dir":"Reference","previous_headings":"","what":"Print ibis options — ibis_options","title":"Print ibis options — ibis_options","text":"number hidden options can specified ibis.iSDM. Currently supported : 'ibis.runparallel' : logical value whether processing run parallel. 'ibis.nthread' : numeric value many cores used default. 'ibis.setupmessages' : logical value indicating whether message object creation shown. 'ibis.engines' : Returns vector valid engines. 'ibis.use_future' : logical whether future package used parallel computing.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Print ibis options — ibis_options","text":"","code":"ibis_options()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Print ibis options — ibis_options","text":"output getOptions ibis related variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/ibis_options.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Print ibis options — ibis_options","text":"","code":"ibis_options() #> $ibis.cleannames #> [1] TRUE #>  #> $ibis.corPred #> [1] 0.7 #>  #> $ibis.dependencies #>  [1] \"pdp\"           \"scales\"        \"biscale\"       \"modEvA\"        #>  [5] \"dplyr\"         \"geodist\"       \"geosphere\"     \"progress\"      #>  [9] \"glmnet\"        \"glmnetUtils\"   \"xgboost\"       \"BoomSpikeSlab\" #> [13] \"INLA\"          \"inlabru\"       \"gnlm\"          \"cubelyr\"       #> [17] \"matrixStats\"   \"Boruta\"        \"abess\"         \"gdalUtilities\" #> [21] \"dbarts\"        \"mboost\"        \"rstan\"         \"cmdstanr\"      #> [25] \"biscale\"       \"poems\"         \"BiocManager\"   #>  #> $ibis.engines #> [1] \"GDB-Model\"     \"BART-Model\"    \"INLABRU-Model\" \"BREG-Model\"    #> [5] \"GLMNET-Model\"  \"GLM-Model\"     \"INLA-Model\"    \"STAN-Model\"    #> [9] \"XGBOOST-Model\" #>  #> $ibis.futurestrategy #> [1] \"multisession\" #>  #> $ibis.nthread #> [1] 3 #>  #> $ibis.priors #> [1] \"INLAPrior\"   \"BARTPrior\"   \"GDBPrior\"    \"GLMNETPrior\" \"XGBPrior\"    #> [6] \"BREGPrior\"   \"STANPrior\"   #>  #> $ibis.pseudoabsence #> Background Settings: 5 parameters #>  #> $ibis.runparallel #> [1] FALSE #>  #> $ibis.seed #> [1] 11283 #>  #> $ibis.setupmessages #> [1] TRUE #>"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":null,"dir":"Reference","previous_headings":"","what":"Approximate missing time steps between dates — interpolate_gaps","title":"Approximate missing time steps between dates — interpolate_gaps","text":"function linearly approximates shares time steps, gaps instance 2010 2020 filled data 2010, 2011, 2012, etc.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Approximate missing time steps between dates — interpolate_gaps","text":"","code":"interpolate_gaps(env, date_interpolation = \"annual\")"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Approximate missing time steps between dates — interpolate_gaps","text":"env stars object. date_interpolation character missing dates events interpolated. See project().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Approximate missing time steps between dates — interpolate_gaps","text":"logical indicating two SpatRaster objects ","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/interpolate_gaps.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Approximate missing time steps between dates — interpolate_gaps","text":"","code":"if (FALSE) {   # Interpolate stars stack   sc <- interpolate_gaps( stack, \"annual\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":null,"dir":"Reference","previous_headings":"","what":"Check whether a provided object is truly of a specific type — is.Id","title":"Check whether a provided object is truly of a specific type — is.Id","text":"Check whether provided object truly specific type","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Check whether a provided object is truly of a specific type — is.Id","text":"","code":"is.Id(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Check whether a provided object is truly of a specific type — is.Id","text":"x provided Id object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Id.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Check whether a provided object is truly of a specific type — is.Id","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":null,"dir":"Reference","previous_headings":"","what":"Tests if an input is a SpatRaster object. — is.Raster","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"Tests input SpatRaster object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"","code":"is.Raster(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"x R Object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Raster.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Tests if an input is a SpatRaster object. — is.Raster","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":null,"dir":"Reference","previous_headings":"","what":"Is the provided object of type waiver? — is.Waiver","title":"Is the provided object of type waiver? — is.Waiver","text":"provided object type waiver?","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Is the provided object of type waiver? — is.Waiver","text":"","code":"is.Waiver(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Is the provided object of type waiver? — is.Waiver","text":"x provided Waiver object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.Waiver.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Is the provided object of type waiver? — is.Waiver","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":null,"dir":"Reference","previous_headings":"","what":"Check whether a formula is valid — is.formula","title":"Check whether a formula is valid — is.formula","text":"Check whether formula valid","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Check whether a formula is valid — is.formula","text":"","code":"is.formula(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Check whether a formula is valid — is.formula","text":"x character object","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.formula.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Check whether a formula is valid — is.formula","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":null,"dir":"Reference","previous_headings":"","what":"Tests if an input is a stars object. — is.stars","title":"Tests if an input is a stars object. — is.stars","text":"Tests input stars object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Tests if an input is a stars object. — is.stars","text":"","code":"is.stars(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Tests if an input is a stars object. — is.stars","text":"x R Object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/is.stars.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Tests if an input is a stars object. — is.stars","text":"Boolean evaluation logical output.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":null,"dir":"Reference","previous_headings":"","what":"Identify local limiting factor — limiting","title":"Identify local limiting factor — limiting","text":"Calculates SpatRaster locally limiting factors given projected model. calculate first spartial effect individual covariate model calculated. effect estimated variable responsible decreasing suitability cell. decrease suitability calculated, predictor turn, relative thesuitability achieved predictor took value equal mean predictor associated largest decrease suitability limiting factor.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Identify local limiting factor — limiting","text":"","code":"limiting(mod, plot = TRUE)  # S4 method for ANY limiting(mod, plot = TRUE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Identify local limiting factor — limiting","text":"mod fitted 'DistributionModel' object limited factors identified. plot result plotted? (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Identify local limiting factor — limiting","text":"terra object important variable given grid cell.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Identify local limiting factor — limiting","text":"Elith, J., Kearney, M. Phillips, S. (2010), art modelling range-shifting species. Methods Ecology Evolution, 1: 330-342. doi: 10.1111/j.2041-210X.2010.00036.x","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/limiting.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Identify local limiting factor — limiting","text":"","code":"if (FALSE) { o <- limiting(fit) plot(o) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":null,"dir":"Reference","previous_headings":"","what":"Load a pre-computed model — load_model","title":"Load a pre-computed model — load_model","text":"load_model function (opposed write_model) loads previous saved DistributionModel. essentially wrapper readRDS. models loaded, briefly checked validity presence necessary components.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Load a pre-computed model — load_model","text":"","code":"load_model(fname, verbose = getOption(\"ibis.setupmessages\"))  # S4 method for character load_model(fname, verbose = getOption(\"ibis.setupmessages\"))"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Load a pre-computed model — load_model","text":"fname character depicting output filename. verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Load a pre-computed model — load_model","text":"DistributionModel object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/load_model.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Load a pre-computed model — load_model","text":"","code":"if (FALSE) { # Load model mod <- load_model(\"testmodel.rds\")  summary(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":null,"dir":"Reference","previous_headings":"","what":"Mask data with an external layer — mask","title":"Mask data with an external layer — mask","text":"helper function takes existing object created ibis.iSDM package external layer, intersects . currently takes either DistributionModel, BiodiversityDatasetCollection, PredictorDataset BiodiversityScenario input. mask either sf SpatRaster object can chosen. mask converted internally depending object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Mask data with an external layer — mask","text":"","code":"mask.DistributionModel(x, mask, inverse = FALSE, ...)  mask.BiodiversityDatasetCollection(x, mask, inverse = FALSE, ...)  mask.PredictorDataset(x, mask, inverse = FALSE, ...)  mask.BiodiversityScenario(x, mask, inverse = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Mask data with an external layer — mask","text":"x object belonging DistributionModel, BiodiversityDatasetCollection, PredictorDataset BiodiversityScenario. mask sf SpatRaster object. inverse logical flag whether take inverse mask instead (Default: FALSE). ... Passed arguments","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Mask data with an external layer — mask","text":"respective object input type.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/mask.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Mask data with an external layer — mask","text":"","code":"if (FALSE) { # Build and train a model mod <- distribution(background) |>   add_biodiversity_poipo(species) |>   add_predictors(predictors) |>   engine_glmnet() |>   train()  # Constrain the prediction by another object mod <- mask(mod, speciesrange)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":null,"dir":"Reference","previous_headings":"","what":"Custom messaging function for scripts — myLog","title":"Custom messaging function for scripts — myLog","text":"functions prints message custom header colour.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Custom messaging function for scripts — myLog","text":"","code":"myLog(title = \"[Processing]\", col = \"green\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Custom messaging function for scripts — myLog","text":"title title log output col character indicating text colour used. Supported 'green' / 'yellow' / 'red' ... additional outputs words display","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/myLog.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Custom messaging function for scripts — myLog","text":"","code":"if (FALSE) { myLog(\"[Setup]\", \"red\", \"Some error occurred during data preparation.\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":null,"dir":"Reference","previous_headings":"","what":"Identifier — new_id","title":"Identifier — new_id","text":"Generate new unique identifier.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Identifier — new_id","text":"","code":"new_id()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Identifier — new_id","text":"\"Id\" object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Identifier — new_id","text":"Identifiers made using uuid::UUIDgenerate().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_id.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Identifier — new_id","text":"","code":"# create new id i <- new_id()  # print id print(i) #> id: f6b8a01a-e065-4252-bae7-00c58d8d941c  # convert to character as.character(i) #> [1] \"f6b8a01a-e065-4252-bae7-00c58d8d941c\"  # check if it is an Id object is.Id(i) #> [1] TRUE"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":null,"dir":"Reference","previous_headings":"","what":"Waiver — new_waiver","title":"Waiver — new_waiver","text":"Create waiver object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Waiver — new_waiver","text":"","code":"new_waiver()"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Waiver — new_waiver","text":"Object class Waiver.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Waiver — new_waiver","text":"object used represent user manually specified setting, defaults used. explicitly using new_waiver(), means NULL objects can valid setting. use \"waiver\" object inspired ggplot2 prioritizr package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/new_waiver.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Waiver — new_waiver","text":"","code":"# create new waiver object w <- new_waiver()  # print object print(w) #> list() #> attr(,\"class\") #> [1] \"Waiver\"  # is it a waiver object? is.Waiver(w) #> [1] TRUE"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":null,"dir":"Reference","previous_headings":"","what":"Obtain partial effects of trained model — partial","title":"Obtain partial effects of trained model — partial","text":"Create partial response effect plot trained model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Obtain partial effects of trained model — partial","text":"","code":"partial(   mod,   x.var = NULL,   constant = NULL,   variable_length = 100,   values = NULL,   newdata = NULL,   plot = FALSE,   type = \"response\",   ... )  # S4 method for ANY partial(   mod,   x.var = NULL,   constant = NULL,   variable_length = 100,   values = NULL,   newdata = NULL,   plot = FALSE,   type = \"response\",   ... )  partial.DistributionModel(mod, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Obtain partial effects of trained model — partial","text":"mod trained DistributionModel object fit_best model within. x.var character indicating variable partial effect calculated. constant numeric constant inserted variables. Default calculates mean per variable. variable_length numeric interpolation depth (nr. points) used (Default: 100). values numeric Directly specified values compute partial effects . parameter set anything NULL, parameter \"variable_length\" ignored (Default: NULL). newdata optional data.frame provided data partial estimation (Default: NULL). plot logical indication whether result plotted? type specified type, either 'response' 'predictor'. Can missing. ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Obtain partial effects of trained model — partial","text":"data.frame created partial response.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Obtain partial effects of trained model — partial","text":"default mean calculated across parameters x.var. Instead constant can set (instance 0) applied output.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Obtain partial effects of trained model — partial","text":"","code":"if (FALSE) {  # Do a partial calculation of a trained model  partial(fit, x.var = \"Forest.cover\", plot = TRUE) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":null,"dir":"Reference","previous_headings":"","what":"Visualize the density of the data over the environmental data — partial_density","title":"Visualize the density of the data over the environmental data — partial_density","text":"Based fitted model, plot density observations estimated variable environmental space. Opposed partial spartial functions, rather low-level interfaces, function provides detail light data. also able contrast different variables show used data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Visualize the density of the data over the environmental data — partial_density","text":"","code":"partial_density(mod, x.var, df = FALSE, ...)  # S4 method for ANY,character partial_density(mod, x.var, df = FALSE, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Visualize the density of the data over the environmental data — partial_density","text":"mod trained DistributionModel object. Requires fitted model inferred prediction. x.var character indicating variable investigated. Can vector length 1 2. df logical plotting data returned instead (Default: FALSE). ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Visualize the density of the data over the environmental data — partial_density","text":"ggplot2 object showing marginal response light data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Visualize the density of the data over the environmental data — partial_density","text":"functions calculates observed density presence absence points whole surface specific variable. can used visually inspect fit model data.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Visualize the density of the data over the environmental data — partial_density","text":"default variables x.var hold constant mean.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Visualize the density of the data over the environmental data — partial_density","text":"Warren, D.L., Matzke, N.J., Cardillo, M., Baumgartner, J.B., Beaumont, L.J., Turelli, M., Glor, R.E., Huron, N.., Simões, M., Iglesias, T.L. Piquet, J.C., Dinnage, R. 2021. ENMTools 1.0: R package comparative ecological biogeography. Ecography, 44(4), pp.504-511.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/partial_density.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Visualize the density of the data over the environmental data — partial_density","text":"","code":"if (FALSE) {  # Do a partial calculation of a trained model  partial_density(fit, x.var = \"Forest.cover\")  # Or with two variables  partial_density(fit, x.var = c(\"Forest.cover\", \"bio01\")) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":null,"dir":"Reference","previous_headings":"","what":"Plot wrappers — plot","title":"Plot wrappers — plot","text":"Plots information given object plotting object available.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Plot wrappers — plot","text":"","code":"# S3 method for DistributionModel plot(x, what = \"mean\", ...)  # S3 method for BiodiversityDatasetCollection plot(x, ...)  # S3 method for PredictorDataset plot(x, ...)  # S3 method for Engine plot(x, ...)  # S3 method for BiodiversityScenario plot(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Plot wrappers — plot","text":"x object belonging DistributionModel, BiodiversityDatasetCollection, PredictorDataset BiodiversityScenario. case SpatRaster supplied, parameter specifies layer shown (Default: \"mean\"). ... arguments passed x$plot.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Plot wrappers — plot","text":"Graphical output","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Plot wrappers — plot","text":"plotted outputs vary depending object plotted. example fitted DistributionModel output usually fitted spatial prediction (Default: 'mean').","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/plot.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Plot wrappers — plot","text":"","code":"if (FALSE) { # Build and train a model mod <- distribution(background) |>   add_biodiversity_poipo(species) |>   add_predictors(predictors) |>   engine_glmnet() |>   train() # Plot the resulting model plot(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"function simulates posterior created stan model, therefore providing fast efficient way project coefficients obtained Bayesian models new/novel contexts.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"","code":"posterior_predict_stanfit(   obj,   form,   newdata,   mode = \"predictor\",   family = NULL,   offset = NULL,   draws = NULL )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"obj \"stanfit\" object (used rstan). form formula object created DistributionModel. newdata data.frame new data used prediction. mode character whether linear predictor response summarized. family character giving family simulating linear response values (Default: NULL) offset vector optionally specified offset. draws numeric indicating whether specific number draws taken.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/posterior_predict_stanfit.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Create a posterior prediction from a rstanfit object — posterior_predict_stanfit","text":"https://medium.com/@alex.pavlakis/making-predictions--stan-models--r-3e349dfac1ed. brms R-package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":null,"dir":"Reference","previous_headings":"","what":"Create spatial derivative of raster stacks — predictor_derivate","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"function creates derivatives existing covariates returns Raster format. Derivative variables can machine learning literature commonly understood one aspect feature engineering. can particularly powerful introducing non-linearities otherwise linear models, example often done popular Maxent framework.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"","code":"predictor_derivate(   env,   option,   nknots = 4,   deriv = NULL,   int_variables = NULL,   method = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"env SpatRaster object. option vector stating whether predictors preprocessed way (Options: 'none', 'quadratic', 'hinge', 'thresh', 'bin'). nknots number knots used transformation (Default: 4). deriv vector character specific derivates create (Default: NULL). int_variables vector length greater equal 2 specifying covariates  (Default: NULL). method 'option' intuitive method setting. Can left empty (case option set). ... options (Non specified).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"Returns derived adjusted SpatRaster objects identical resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"Available options : 'none' - original layer(s) returned. 'quadratic' - quadratic transformation (\\(x^{2}\\)) created provided layers. 'hinge' - Creates hinge transformation covariates, set values lower set threshold 0 others range \\([0,1]\\). number thresholds thus new derivates specified via parameter 'nknots' (Default: 4). 'interaction' - Creates interactions variables. Target variables specified via \"int_variables\". 'thresh' - threshold transformation covariates, sets values lower set threshold 0 larger 1. number thresholds thus new derivates specified via parameter 'nknots' (Default: 4). 'bin' - Creates factor representation covariates cutting range covariates percentiles. number percentile cuts thus new derivates specified via parameter 'nknots' (Default: 4).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_derivate.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create spatial derivative of raster stacks — predictor_derivate","text":"","code":"if (FALSE) { # Create a hinge transformation of one or multiple SpatRaster. predictor_derivate(covs, option = \"hinge\", knots = 4) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":null,"dir":"Reference","previous_headings":"","what":"Filter a set of correlated predictors to fewer ones — predictor_filter","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"function helps remove highly correlated variables set predictors. supports multiple options require environmental predictors observations, others predictors. options require different packages pre-installed, ranger Boruta.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"","code":"predictor_filter(env, keep = NULL, method = \"pearson\", ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"env data.frame matrix extracted environmental covariates given species. keep vector variables keep regardless. usually variables prior information known. method method use constructing correlation matrix (Options: 'pearson' (Default), 'spearman'| 'kendal'), \"abess\", \"boruta\". ... options specific method","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"character  vector variable names excluded. function fails due reason return NULL.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"Available options : \"none\" prior variable removal performed (Default). \"pearson\", \"spearman\" \"kendall\" Makes use pairwise comparisons identify remove highly collinear predictors (Pearson's r >= 0.7). \"abess\" -priori adaptive best subset selection covariates via abess package (see References). Note effectively fits separate generalized linear model reduce number covariates. \"boruta\" Uses Boruta package identify non-informative features.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"Using function predictors effectively means separate model fitted data assumptions come (e.g. linearity, appropriateness response, normality, etc).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_filter.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Filter a set of correlated predictors to fewer ones — predictor_filter","text":"","code":"if (FALSE) {  # Remove highly correlated predictors  env <- predictor_filter( env, option = \"pearson\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":null,"dir":"Reference","previous_headings":"","what":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"method allows homogenization missing data across set environmental predictors. default called predictors added BiodiversityDistribution object. grid cells NAs contain values raster layers homogenized. Additional parameters allow instead homogenization fill missing data neighbouring values","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"","code":"predictor_homogenize_na(   env,   fill = FALSE,   fill_method = \"ngb\",   return_na_cells = FALSE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"env SpatRaster object predictors. fill logical value indicating whether missing data filled (Default: FALSE). fill_method character method filling gaps used (Default: 'ngb'). return_na_cells logical value whether ids grid cells NA values returned instead (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"SpatRaster object number layers input.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_homogenize_na.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Homogenize NA values across a set of predictors. — predictor_homogenize_na","text":"","code":"if (FALSE) {  # Harmonize predictors  env <- predictor_homogenize_na(env) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":null,"dir":"Reference","previous_headings":"","what":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"function allows transformation provided environmental predictors (SpatRaster format). common use case instance standardization (scaling) predictors prior model fitting. function works SpatRaster well stars objects.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"","code":"predictor_transform(   env,   option,   windsor_props = c(0.05, 0.95),   pca.var = 0.8,   method = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"env SpatRaster object. option vector stating whether predictors preprocessed way (Options: 'none', 'scale', 'norm', 'windsor', 'windsor_thresh', 'percentile' 'pca', 'revjack'). See Details. windsor_props numeric vector specifying proportions clipped windsorization (Default: c(.05,.95)). pca.var numeric value >0 1 stating minimum amount variance covered (Default: 0.8). method 'option' intuitive method setting. Can left empty (case option set). ... options (Non specified).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"Returns adjusted SpatRaster object identical resolution.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"Available options : 'none' original layer(s) returned. 'scale' run scale() function default settings (1 Standard deviation) across predictors. sensible default model fitting. 'norm' normalizes predictors range 0-1. 'windsor' applies 'windsorization' existing raster layer setting lowest, respectively largest values value certain percentage level (e.g. 95%). can set via parameter \"windsor_props\". 'windsor_thresh' option 'windsor', however case values clamped thresholds rather certain percentages calculated data. 'percentile' converts bins values percentiles, e.g. top 10% lowest 10% values . 'pca' option runs principal component decomposition predictors (via prcomp()). returns new predictors resembling components order important ones. Can useful reduce collinearity, however note changes predictor names 'PCX', X number component. parameter 'pca.var' can modified specify minimum variance covered axes. 'revjack' Removes outliers supplied stack via reverse jackknife procedure. Identified outliers default set NA.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/predictor_transform.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Spatial adjustment of environmental predictors and raster stacks — predictor_transform","text":"","code":"if (FALSE) { # Where x is a SpatRaster new_x <- predictor_transform(x, option = 'scale') }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":null,"dir":"Reference","previous_headings":"","what":"Print — print","title":"Print — print","text":"Display information object created ibis.iSDM R-package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Print — print","text":"","code":"# S3 method for distribution print(x, ...)  # S3 method for BiodiversityDistribution print(x, ...)  # S3 method for BiodiversityDatasetCollection print(x, ...)  # S3 method for BiodiversityDataset print(x, ...)  # S3 method for PredictorDataset print(x, ...)  # S3 method for DistributionModel print(x, ...)  # S3 method for BiodiversityScenario print(x, ...)  # S3 method for Prior print(x, ...)  # S3 method for PriorList print(x, ...)  # S3 method for Engine print(x, ...)  # S3 method for Settings print(x, ...)  # S3 method for Log print(x, ...)  # S3 method for Id print(x, ...)  # S4 method for Id print(x, ...)  # S4 method for tbl_df print(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Print — print","text":"x object created package. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Print — print","text":"Object specific.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/print.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Print — print","text":"","code":"if (FALSE) { # Where mod is fitted object mod print(mod) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Creates a new PriorList object — priors","title":"Creates a new PriorList object — priors","text":"PriorList object essentially list contains individual Prior objects. order use priors engines, respective Prior identified (e.g. INLAPrior) embedded PriorList object. Afterwards objects can added distribution object add_priors function. PriorList object essentially list contains individual Prior objects. order use priors engines, respective Prior identified (e.g. INLAPrior) embedded PriorList object. Afterwards objects can added distribution object add_priors function.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Creates a new PriorList object — priors","text":"","code":"priors(x, ...)  # S4 method for ANY priors(x, ...)  priors(x, ...)  # S4 method for ANY priors(x, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Creates a new PriorList object — priors","text":"x Prior object added list. ... One multiple additional Prior object added list.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Creates a new PriorList object — priors","text":"PriorList object. PriorList object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Creates a new PriorList object — priors","text":"","code":"p1 <- GDBPrior(variable = \"Forest\", hyper = \"positive\") p2 <- GDBPrior(variable = \"Urban\", hyper = \"decreasing\") priors(p1, p2) #> Set priors: 2  if (FALSE) { p1 <- INLAPrior(variable = \"Forest\",type = \"normal\", hyper = c(1,1e4)) p2 <- INLAPrior(variable = \"Urban\",type = \"normal\", hyper = c(0,1e-2)) priors(p1, p2) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":null,"dir":"Reference","previous_headings":"","what":"Project a fitted model to a new environment and covariates — project","title":"Project a fitted model to a new environment and covariates — project","text":"Equivalent train, function acts wrapper project model stored BiodiversityScenario object newly supplied (future) covariates. Supplied predictors usually spatial-temporal predictors prepared via add_predictors() (e.g. transformations derivates) way initial modelling distribution(). constrains specified scenario object applied projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Project a fitted model to a new environment and covariates — project","text":"","code":"project.BiodiversityScenario(x, ...)  # S4 method for BiodiversityScenario project(   x,   date_interpolation = \"none\",   stabilize = FALSE,   stabilize_method = \"loess\",   layer = \"mean\",   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Project a fitted model to a new environment and covariates — project","text":"x BiodiversityScenario object set predictors. Note constrains MigClim can still simulate future change without projections. ... passed parameters. date_interpolation character whether dates interpolated. Options include \"none\" (Default), \"annual\", \"monthly\", \"daily\". stabilize logical value indicating whether suitability projection stabilized (Default: FALSE). stabilize_method character stating stabilization method applied. Currently supported `loess`. layer character specifying layer projected (Default: \"mean\"). verbose Setting logical value TRUE prints information model fitting (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Project a fitted model to a new environment and covariates — project","text":"Saves stars objects obtained predictions mod.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Project a fitted model to a new environment and covariates — project","text":"background function x$project() respective model object called, x fitted model object. specifics constraints, see relevant constrain functions, respectively: add_constraint() generic wrapper add available constrains. add_constraint_dispersal() specifying dispersal constraint temporal projections step. add_constraint_MigClim() Using MigClim R-package simulate dispersal projections. add_constraint_connectivity() Apply connectivity constraint projection, instance adding barrier prevents migration. add_constraint_minsize() Adds constraint minimum area given thresholded patch , assuming smaller areas fact suitable. add_constraint_adaptability() Apply adaptability constraint projection, instance constraining speed species able adapt new conditions. add_constraint_boundary() artificially limit distribution change. Similar specifying projection limits, can used specifically constrain projection within certain area (e.g. species range island). Many constrains also requires thresholds calculated. Adding threshold() BiodiversityScenario object enables computation thresholds every step based threshold used main model (threshold values taken ). also possible make complementary simulation steps package, can provided via simulate_population_steps() BiodiversityScenario object. Similar thresholds, estimates values added outputs. Finally function also allows temporal stabilization across prediction steps via enabling parameter stabilize checking stablize_method argument. Stabilization can instance helpful situations environmental variables quite dynamic, changes projected suitability expected abruptly increase decrease. thus way smoothen outliers projection. Options far instance 'loess' fits loess() model per pixel time step. conducted processing steps thresholds recalculated afterwards.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/project.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Project a fitted model to a new environment and covariates — project","text":"","code":"if (FALSE) { # Fit a model fit <- distribution(background) |>         add_biodiversity_poipa(surveydata) |>         add_predictors(env = predictors) |>         engine_breg() |>         train()  # Fit a scenario sc <- scenario(fit) |>         add_predictors(env = future_predictors) |>         project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":null,"dir":"Reference","previous_headings":"","what":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"function defines settings pseudo-absence sampling background. many engines points necessary model Poisson (Binomial) distributed point process data. Specifically call absence points Binomial (Bernoulli really) distributed responses 'pseudo-absence' absence data Poisson responses 'background' points. details read Renner et al. (2015). function 'add_pseudoabsence' allows add absence points sf object. See Details additional parameter description examples 'turn' presence-dataset presence-(pseudo-)absence.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"","code":"pseudoabs_settings(   background = NULL,   nrpoints = 10000,   min_ratio = 0.25,   method = \"random\",   buffer_distance = 10000,   inside = FALSE,   layer = NULL,   bias = NULL,   ... )  # S4 method for ANY pseudoabs_settings(   background = NULL,   nrpoints = 10000,   min_ratio = 0.25,   method = \"random\",   buffer_distance = 10000,   inside = FALSE,   layer = NULL,   bias = NULL,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"background SpatRaster sf object background points can sampled. Default NULL (Default) background added sampling first called. nrpoints numeric given number absence points created. larger 0 normally points created excess number cells background (Default: 10000). min_ratio numeric minimum ratio background points relative presence points. Setting value 1 generates equal amount absence points relative presence points. Usually ignored unless ratio exceeds nrpoints parameters (Default: 0.25). method character denoting sampling done. See details options (Default: \"random\"). buffer_distance numeric distance observations pseudo-absence points generated. Note units follow units projection (e.g. m °). used method = \"buffer\". inside logical value whether absence points sampled outside (Default) inside minimum convex polygon range provided respective method chosen (parameter method = \"mcp\" method = \"range\"). layer sf SpatRaster (case method 'zones') object indicating range species. used method = \"range\" method = \"zones\" (Default: NULL). bias SpatRaster extent projection background. Absence points preferentially sampled areas higher (!) bias. (Default: NULL). ... settings added pseudoabs settings.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"multiple methods available sampling biased background layer. Possible parameters method : 'random' Absence points generated randomly background (Default), 'buffer' Absence points generated within buffered distance existing points. option requires specification parameter buffer_distance. 'mcp' Can used generate absence points within outside minimum convex polygon presence points. parameter inside specifies whether points sampled inside outside (Default) minimum convex polygon. 'range' Absence points created either inside outside provided additional layer indicates example range species (controlled parameter inside). 'zones' ratified (e.g. type factor) SpatRaster layer depicting zones absence points sampled. method checks points fall within zones samples absence points either within outside zones exclusively. 'layer' 'inside' set option. 'target' Make use target background sampling absence points. SpatRaster object provided parameter 'layer'. Absence points sampled exclusively within target areas grid cells non-zero values.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"Renner IW, Elith J, Baddeley , Fithian W, Hastie T, Phillips SJ, Popovic G, Warton DI. 2015. Point process models presence-analysis. Methods Ecology Evolution 6:366–379. DOI: 10.1111/2041-210X.12352. Renner, . W., & Warton, D. . (2013). Equivalence MAXENT Poisson point process models species distribution modeling ecology. Biometrics, 69(1), 274-281.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/pseudoabs_settings.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Settings for specifying pseudo-absence points within the model background — pseudoabs_settings","text":"","code":"if (FALSE) { # This setting generates 10000 pseudo-absence points outside the # minimum convex polygon of presence points ass1 <- pseudoabs_settings(nrpoints = 10000, method = 'mcp', inside = FALSE)  # This setting would match the number of presence-absence points directly. ass2 <- pseudoabs_settings(nrpoints = 0, min_ratio = 1)  # These settings can then be used to add pseudo-absence data to a # presence-only dataset. This effectively adds these simulated absence # points to the resulting model all_my_points <- add_pseudoabsence(                      df = virtual_points,                       field_occurrence = 'observed',                       template = background,                       settings = ass1) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":null,"dir":"Reference","previous_headings":"","what":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"Remove particular dataset () distribution object BiodiversityDatasetCollection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"","code":"rm_biodiversity(x, name, id)  # S4 method for BiodiversityDistribution rm_biodiversity(x, name, id)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"x distribution() (.e. BiodiversityDistribution) object. name character name biodiversity dataset. id character id biodiversity dataset.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_biodiversity.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Remove specific BiodiversityDataset from a distribution object — rm_biodiversity","text":"","code":"if (FALSE) { distribution(background) |>  add_biodiversity_poipa(species, \"Duckus communus\")  rm_biodiversity(names = \"Duckus communus\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to remove a latent effect — rm_latent","title":"Function to remove a latent effect — rm_latent","text":"just wrapper function removing specified offsets BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to remove a latent effect — rm_latent","text":"","code":"rm_latent(x)  # S4 method for BiodiversityDistribution rm_latent(x)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to remove a latent effect — rm_latent","text":"x distribution() (.e. BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to remove a latent effect — rm_latent","text":"Removes latent spatial effect distribution object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_latent.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to remove a latent effect — rm_latent","text":"","code":"if (FALSE) {  rm_latent(model) -> model }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":null,"dir":"Reference","previous_headings":"","what":"Function to remove an offset — rm_offset","title":"Function to remove an offset — rm_offset","text":"just wrapper function removing specified offsets BiodiversityDistribution) object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Function to remove an offset — rm_offset","text":"","code":"rm_offset(x, layer = NULL)  # S4 method for BiodiversityDistribution rm_offset(x, layer = NULL)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Function to remove an offset — rm_offset","text":"x distribution() (.e. BiodiversityDistribution) object. layer character pointing specific layer removed. set NULL, offsets removed object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Function to remove an offset — rm_offset","text":"Removes offset distribution object.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_offset.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Function to remove an offset — rm_offset","text":"","code":"if (FALSE) {  rm_offset(model) -> model }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":null,"dir":"Reference","previous_headings":"","what":"Remove specific predictors from a distribution object — rm_predictors","title":"Remove specific predictors from a distribution object — rm_predictors","text":"Remove particular variable distribution object PredictorDataset. See Examples.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Remove specific predictors from a distribution object — rm_predictors","text":"","code":"rm_predictors(x, names)  # S4 method for BiodiversityDistribution,character rm_predictors(x, names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Remove specific predictors from a distribution object — rm_predictors","text":"x distribution() (.e. BiodiversityDistribution) object. names vector Vector character names describing environmental stack.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_predictors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Remove specific predictors from a distribution object — rm_predictors","text":"","code":"if (FALSE) { distribution(background) |>  add_predictors(my_covariates) |>  rm_predictors(names = \"Urban\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Remove existing priors from an existing distribution object — rm_priors","title":"Remove existing priors from an existing distribution object — rm_priors","text":"function allows remove priors existing distribution object. order remove set prior, name prior specified.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Remove existing priors from an existing distribution object — rm_priors","text":"","code":"rm_priors(x, names = NULL, ...)  # S4 method for BiodiversityDistribution rm_priors(x, names = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Remove existing priors from an existing distribution object — rm_priors","text":"x distribution (.e. BiodiversityDistribution) object. names vector character object priors removed. ... parameters passed ","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/rm_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Remove existing priors from an existing distribution object — rm_priors","text":"","code":"if (FALSE) {  # Add prior  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  # Remove again  x <- x |> rm_priors(\"forest\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":null,"dir":"Reference","previous_headings":"","what":"Fit cmdstanr model and convert to rstan object — run_stan","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"function fits stan model using light-weight interface provided cmdstanr. code adapted McElreath rethinking package.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"","code":"run_stan(   model_code,   data = list(),   algorithm = \"sampling\",   chains = 4,   cores = getOption(\"ibis.nthread\"),   threads = 1,   iter = 1000,   warmup = floor(iter/2),   control = list(adapt_delta = 0.95),   cpp_options = list(),   force = FALSE,   path = base::getwd(),   save_warmup = TRUE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"model_code character pointing stan modelling code. data list parameters required run model_code stan. algorithm character giving algorithm use. Either 'sampling' (Default), 'optimize' 'variational' penalized likelihood estimation. chains numeric indicating number chains use estimation. cores Number threads sampling. Default set 'getOption(\"ibis.nthread\")'. See ibis_options(). threads numeric giving number threads run per chain. specified accordance cores. iter numeric value giving number MCMC samples generate. warmup numeric number warm-samples MCMC. Default set 1/2 iter. control list control options stan. cpp_options list options Cpp compiling. force logical indication whether force recompile model (Default: FALSE). path character indicating path made available stan compiler. save_warmup logical flag whether save warmup samples. ... non-specified parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/run_stan.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Fit cmdstanr model and convert to rstan object — run_stan","text":"rstan object","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":null,"dir":"Reference","previous_headings":"","what":"Sanitize variable names — sanitize_names","title":"Sanitize variable names — sanitize_names","text":"Prepared covariates often special characters variable names can can used formulas cause errors certain engines. function converts special characters variable names format","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Sanitize variable names — sanitize_names","text":"","code":"sanitize_names(names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Sanitize variable names — sanitize_names","text":"names vector character vectors sanitized.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Sanitize variable names — sanitize_names","text":"vector sanitized character.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sanitize_names.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Sanitize variable names — sanitize_names","text":"","code":"# Correct variable names vars <- c(\"Climate-temperature2015\", \"Elevation__sealevel\", \"Landuse.forest..meanshare\") sanitize_names(vars) #> [1] \"Climate_temperature2015\"   \"Elevation_sealevel\"        #> [3] \"Landuse.forest..meanshare\""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a new scenario based on trained model parameters — scenario","title":"Create a new scenario based on trained model parameters — scenario","text":"function creates new BiodiversityScenario object contains projections model.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a new scenario based on trained model parameters — scenario","text":"","code":"scenario(fit, limits = NULL, reuse_limits = FALSE, copy_model = FALSE)  # S4 method for ANY scenario(fit, limits = NULL, reuse_limits = FALSE, copy_model = FALSE)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a new scenario based on trained model parameters — scenario","text":"fit BiodiversityDistribution object containing trained model. limits SpatRaster sf object limits projection surface intersected prediction data (Default: NULL). can instance set expert-delineated constrain limit spatial projections. reuse_limits logical whether reuse limits found trained BiodiversityDistribution object (Default: FALSE). See also notes! copy_model logical whether model object copied scenario object. Note setting option TRUE can increase required amount memory (Default: FALSE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Create a new scenario based on trained model parameters — scenario","text":"limit defined already train(), example adding extrapolation limit add_control_extrapolation(), zonal layer can reused projections. Note: effectively fixes projections certain areas.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/scenario.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a new scenario based on trained model parameters — scenario","text":"","code":"if (FALSE) {   scenario(fit, limits = island_area) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":null,"dir":"Reference","previous_headings":"","what":"Select specific predictors from a distribution object — sel_predictors","title":"Select specific predictors from a distribution object — sel_predictors","text":"function allows - character vector names already added PredictorDataset object - select particular set predictors. See Examples.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Select specific predictors from a distribution object — sel_predictors","text":"","code":"sel_predictors(x, names)  # S4 method for BiodiversityDistribution,character sel_predictors(x, names)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Select specific predictors from a distribution object — sel_predictors","text":"x distribution() (.e. BiodiversityDistribution) object. names vector Vector character names describing environmental stack.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/sel_predictors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Select specific predictors from a distribution object — sel_predictors","text":"","code":"if (FALSE) { distribution(background) |>  add_predictors(my_covariates) |>  sel_predictors(names = c(\"Forest\", \"Elevation\")) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":null,"dir":"Reference","previous_headings":"","what":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"function simply allows add priors existing distribution object. supplied priors must PriorList object created calling priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"","code":"# S4 method for BiodiversityDistribution set_priors(x, priors = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"x distribution (.e. BiodiversityDistribution) object. priors PriorList object containing multiple priors. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"Alternatively priors environmental predictors can also directly added parameter via add_predictors","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors-BiodiversityDistribution-method.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add priors to an existing distribution object — set_priors,BiodiversityDistribution-method","text":"","code":"if (FALSE) {  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":null,"dir":"Reference","previous_headings":"","what":"Add priors to an existing distribution object — set_priors","title":"Add priors to an existing distribution object — set_priors","text":"function simply allows add priors existing distribution object. supplied priors must PriorList object created calling priors.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Add priors to an existing distribution object — set_priors","text":"","code":"set_priors(x, priors = NULL, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Add priors to an existing distribution object — set_priors","text":"x distribution (.e. BiodiversityDistribution) object. priors PriorList object containing multiple priors. ... parameters passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Add priors to an existing distribution object — set_priors","text":"Alternatively priors environmental predictors can also directly added parameter via add_predictors","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/set_priors.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Add priors to an existing distribution object — set_priors","text":"","code":"if (FALSE) {  pp <-  GLMNETPrior(\"forest\")  x <- distribution(background) |>   add_priors(pp)  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":null,"dir":"Reference","previous_headings":"","what":"Calculate environmental similarity of reference datasets to predictors. — similarity","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"Calculate environmental similarity provided covariates respect reference dataset. Currently supported Multivariate Environmental Similarity index multivariate combination novelty index (NT2) based Mahalanobis divergence (see references).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"","code":"similarity(   obj,   ref,   ref_type = \"poipo\",   method = \"mess\",   predictor_names = NULL,   full = FALSE,   plot = TRUE,   ... )  # S4 method for BiodiversityDistribution similarity(   obj,   ref,   ref_type = \"poipo\",   method = \"mess\",   predictor_names = NULL,   full = FALSE,   plot = TRUE,   ... )  # S4 method for SpatRaster similarity(   obj,   ref,   ref_type = \"poipo\",   method = \"mess\",   predictor_names = NULL,   full = FALSE,   plot = TRUE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"obj BiodiversityDistribution, DistributionModel alternatively SpatRaster object. ref BiodiversityDistribution, DistributionModel alternatively data.frame extracted values (corresponding given obj). ref_type character specifying type biodiversity use obj BiodiversityDistribution. method specifc method similarity calculation. Currently supported: 'mess', 'nt'. predictor_names optional character specifying covariates used (Default: NULL). full similarity values returned variables (Default:FALSE)? plot result plotted? Otherwise return output list (Default: TRUE). ... options (Non specified).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"function returns list containing: similarity: SpatRaster object multiple layers giving environmental similarities variable x (included \"full=TRUE\"); mis: SpatRaster layer giving minimum similarity value across variables location (.e. MESS); exip: SpatRaster layer indicating whether model interpolate extrapolate location based environmental surface; mod: factor SpatRaster layer indicating variable dissimilar reference range (.e. MoD map, Elith et al. 2010); mos: factor SpatRaster layer indicating variable similar reference range.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"similarity implements MESS algorithm described Appendix S3 Elith et al. (2010) well Mahalanobis dissimilarity described Mesgaran et al. (2014).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"Elith, J., Kearney, M., Phillips, S. (2010) \"art modelling range-shifting species\". Methods Ecology Evolution, 1: 330-342. https://doi.org/10.1111/j.2041-210X.2010.00036.x Mesgaran, M.B., Cousens, R.D. Webber, B.L. (2014) \"dragons: tool quantifying novelty due covariate range correlation change projecting species distribution models\". Diversity Distributions, 20: 1147-1159. https://doi.org/10.1111/ddi.12209","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/similarity.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Calculate environmental similarity of reference datasets to predictors. — similarity","text":"","code":"if (FALSE) { plot(   similarity(x) # Where x is a distribution or Raster object )  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":null,"dir":"Reference","previous_headings":"","what":"Simulate population dynamics following the steps approach — simulate_population_steps","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"function adds flag BiodiversityScenario object indicate species abundances simulated based expected habitat suitability, well demography, density-dependence dispersal information. simulation done using steps package (Visintin et al. 2020) conducted habitat suitability projection created. steps spatially explicit population models coded mostly R. detailed description steps parameters, please see respective reference help files. Default assumptions underlying wrapper presented details","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"","code":"simulate_population_steps(   mod,   vital_rates,   replicates = 1,   carrying_capacity = NULL,   initial = NULL,   dispersal = NULL,   density_dependence = NULL,   include_suitability = TRUE )  # S4 method for BiodiversityScenario,matrix simulate_population_steps(   mod,   vital_rates,   replicates = 1,   carrying_capacity = NULL,   initial = NULL,   dispersal = NULL,   density_dependence = NULL,   include_suitability = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"mod BiodiversityScenario object specified predictors. vital_rates symmetrical demographic matrix. column row names equivalent vital stages estimated. replicates numeric vector number replicates (Default: 1). carrying_capacity Either SpatRaster numeric estimate maximum carrying capacity, e.g. many adult individual likely occur per grid cell. set numeric, carrying capacity estimated maximum set (Note: clever way use species-area relationship scaling. yet implemented). initial SpatRaster giving initial population size. provided, initial populations guessed (see details) projected suitability rasters (Default: NULL). dispersal dispersal object defined steps package (Default: NULL). density_dependence Specification density dependence defined steps package (Default: NULL). include_suitability logical flag whether projected suitability estimates used (Default: TRUE) initial conditions set first time step.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"Adds flag BiodiversityScenario object indicate simulations added projection.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"order function work steps package installed separately. Instructions can found github. initial population lifestages provided, estimated assuming linear scaling suitability, 50:50 split sexes 1:3 ratio adults juveniles. provision different parameters highly encouraged!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"steps package multiple options simulating species population possible options represented wrapper. Furthermore, package still makes use raster package much internal data processing. Since ibis.iSDM switched terra ago, can efficiency problems layers need translated packages.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"Visintin, C., Briscoe, N. J., Woolley, S. N., Lentini, P. E., Tingley, R., Wintle, B. ., & Golding, N. (2020). steps: Software spatially temporally explicit population simulations. Methods Ecology Evolution, 11(4), 596-603. https://doi.org/10.1111/2041-210X.13354","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/simulate_population_steps.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Simulate population dynamics following the steps approach — simulate_population_steps","text":"","code":"if (FALSE) { # Define vital rates vt <- matrix(c(0.0,0.5,0.75,                0.5,0.2,0.0,                0.0,0.5,0.9),                nrow = 3, ncol = 3, byrow = TRUE) colnames(vt) <- rownames(vt) <- c('juvenile','subadult','adult')  # Assumes that a trained 'model' object exists  mod <- scenario(model) |>   add_predictors(env = predictors, transform = 'scale',                  derivates = \"none\") |>   # Use Vital rates here, but note the other parameters!   simulate_population_steps(vital_rates = vt) |>   project() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":null,"dir":"Reference","previous_headings":"","what":"Obtain spatial partial effects of trained model — spartial","title":"Obtain spatial partial effects of trained model — spartial","text":"Similar partial function calculates partial response trained model given variable. Differently partial space. However result SpatRaster showing spatial magnitude partial response.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Obtain spatial partial effects of trained model — spartial","text":"","code":"spartial(mod, x.var, constant = NULL, newdata = NULL, plot = FALSE, ...)  # S4 method for ANY,character spartial(mod, x.var, constant = NULL, newdata = NULL, plot = FALSE, ...)  spartial.DistributionModel(mod, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Obtain spatial partial effects of trained model — spartial","text":"mod DistributionModel object trained model. x.var character indicating variable partial effect calculated. constant numeric constant inserted variables. Default calculates mean per variable. newdata data.frame calculate spartial . Can example created raster file (Default: NULL). plot logical indication whether result plotted? ... engine specific parameters.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Obtain spatial partial effects of trained model — spartial","text":"SpatRaster containing mapped partial response variable.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Obtain spatial partial effects of trained model — spartial","text":"default mean calculated across parameters x.var. Instead constant can set (instance 0) applied output.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/spartial.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Obtain spatial partial effects of trained model — spartial","text":"","code":"if (FALSE) {  # Create and visualize the spartial effect  spartial(fit, x.var = \"Forest.cover\", plot = TRUE) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":null,"dir":"Reference","previous_headings":"","what":"Show the stan code from a trained model — stancode","title":"Show the stan code from a trained model — stancode","text":"helper function shows code trained DistributionModel using engine_stan. function emulated similar functionality brms R-package. works models inferred stan!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Show the stan code from a trained model — stancode","text":"","code":"stancode(obj, ...)  stancode.DistributionModel(obj, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Show the stan code from a trained model — stancode","text":"obj prepared object. ... used.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/stancode.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Show the stan code from a trained model — stancode","text":"None.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":null,"dir":"Reference","previous_headings":"","what":"Summarises a trained model or predictor object — summary","title":"Summarises a trained model or predictor object — summary","text":"helper function summarizes given object, including DistributionModel, PredictorDataset PriorList objects others. can helpful way summarize contained within values specified models objects. unsure, usually good strategy run summary object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Summarises a trained model or predictor object — summary","text":"","code":"# S3 method for distribution summary(object, ...)  # S3 method for DistributionModel summary(object, ...)  # S3 method for PredictorDataset summary(object, ...)  # S3 method for BiodiversityScenario summary(object, ...)  # S3 method for PriorList summary(object, ...)  # S3 method for Settings summary(object, ...)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Summarises a trained model or predictor object — summary","text":"object prepared object. ... used.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/summary.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Summarises a trained model or predictor object — summary","text":"","code":"if (FALSE) { # Example with a trained model x <- distribution(background) |>         # Presence-absence data         add_biodiversity_poipa(surveydata) |>         # Add predictors and scale them         add_predictors(env = predictors) |>         # Use glmnet and lasso regression for estimation         engine_glmnet(alpha = 1)  # Train the model  mod <- train(x)  summary(mod)   # Example with a prior object  p1 <- BREGPrior(variable = \"forest\", hyper = 2, ip = NULL)  p2 <- BREGPrior(variable = \"cropland\", hyper = NULL, ip = 1)  pp <- priors(p1,p2)  summary(pp) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":null,"dir":"Reference","previous_headings":"","what":"Functionality for geographic and environmental thinning — thin_observations","title":"Functionality for geographic and environmental thinning — thin_observations","text":"species distribution modelling approaches assumed occurrence records unbiased, rarely case. model-based control can alleviate effects sampling bias, can often desirable account sampling biases spatial thinning (Aiello‐Lammens et al. 2015). approach based assumption -sampled grid cells contribute little bias, rather strengthening environmental responses. function provides methods apply spatial thinning approaches. Note effectively removes data prior estimation use considered care (see also Steen et al. 2021).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Functionality for geographic and environmental thinning — thin_observations","text":"","code":"thin_observations(   data,   background,   env = NULL,   method = \"random\",   remainpoints = 10,   mindistance = NULL,   zones = NULL,   probs = 0.75,   global = TRUE,   centers = NULL,   verbose = TRUE )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Functionality for geographic and environmental thinning — thin_observations","text":"data sf object observed occurrence points. methods threat presence-presence-absence occurrence points equally. background SpatRaster object background study region. Use assessing point density. env SpatRaster object environmental covariates. Needed method set \"environmental\" \"bias\" (Default: NULL). method character method applied (Default: \"random\"). remainpoints numeric giving number data points minimum remain (Default: 10). mindistance numeric minimum distance neighbouring observations (Default: NULL). zones SpatRaster supplied option \"zones\" chosen (Default: NULL). probs numeric used quantile threshold \"bias\" method. (Default: 0.75). global logical \"bias\" method global (entire env raster) local (extracted point locations) bias values used quantile threshold. (Default: TRUE). centers numeric used number centers \"environmental\" method. (Default: NULL). set, automatically set three nlayers - 1 (whatever bigger). verbose logical whether print statistics thinning outcome (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Functionality for geographic and environmental thinning — thin_observations","text":"methods remove points \"-sampled\" grid cells/areas. defined cells/areas either points remainpoints points global minimum point count per cell/area (whichever larger). Currently implemented thinning methods: \"random\": Samples random across -sampled grid cells returning \"remainpoints\" -sampled cells. account spatial environmental distance observations. \"bias\": option removes explicitly points considered biased (based \"env\"). Points thinned grid cells bias quantile (larger values equals greater bias). Thins observations returning \"remainpoints\" -sampled biased cell. \"zones\": Thins observations zone -sampled threshold returns  \"remainpoints\" zone. Careful: zones relatively wide can remove quite observations. \"environmental\": approach creates observation-wide clustering (k-means) assumption full environmental niche comprehensively sampled covered provided covariates env. -sampled cluster, obtain (\"remainpoints\") thinning points. \"spatial\": Calculates spatial distance observations. points removed iteratively minimum distance points crossed. \"mindistance\" parameter set function work.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Functionality for geographic and environmental thinning — thin_observations","text":"Aiello‐Lammens, M. E., Boria, R. ., Radosavljevic, ., Vilela, B., & Anderson, R. P. (2015). spThin: R package spatial thinning species occurrence records use ecological niche models. Ecography, 38(5), 541-545. Steen, V. ., Tingley, M. W., Paton, P. W., & Elphick, C. S. (2021). Spatial thinning class balancing: Key choices lead variation performance species distribution models citizen science data. Methods Ecology Evolution, 12(2), 216-226.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/thin_observations.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Functionality for geographic and environmental thinning — thin_observations","text":"","code":"if (FALSE) {  # Thin a certain number of observations  # At random  thin_points <- thin_observations(points, background, method = \"random\")  # using a bias layer  thin_points <- thin_observations(points, background, method = \"bias\", env = bias) }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":null,"dir":"Reference","previous_headings":"","what":"Threshold a continuous prediction to a categorical layer — threshold","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"common many applications species distribution modelling estimated continuous suitability surfaces converted discrete representations suitable habitat might might exist. called threshold'ing can done various ways described details. case SpatRaster provided input function obj, furthermore necessary provide sf object validation DistributionModel read information . Note: course also allows estimate threshold based withheld data, instance created -priori cross-validation procedure. BiodiversityScenario objects, adding function processing pipeline stores threshold attribute created scenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"","code":"threshold(   obj,   method = \"mtp\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE,   ... )  # S4 method for ANY threshold(   obj,   method = \"mtp\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE,   ... )  # S4 method for SpatRaster threshold(   obj,   method = \"fixed\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE )  # S4 method for BiodiversityScenario threshold(   obj,   method = \"mtp\",   value = NULL,   point = NULL,   field_occurrence = \"observed\",   format = \"binary\",   return_threshold = FALSE,   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"obj BiodiversityScenario object existing threshold added. method specifc method thresholding. See details available options. value numeric value specifying specific threshold scenarios (Default: NULL Grab object). point sf object containing observational data used model training. field_occurrence character location biodiversity point records. format character indication whether \"binary\", \"normalize\" \"percentile\" formatted thresholds created (Default: \"binary\"). Also see Muscatello et al. (2021). return_threshold threshold value returned instead (Default: FALSE) ... parameter. Used fetch value set somehow.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"SpatRaster SpatRaster object input. Otherwise threshold added respective DistributionModel BiodiversityScenario object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"following options currently implemented: 'fixed' = applies single pre-determined threshold. Requires value set. 'mtp' = minimum training presence used find set lowest predicted suitability occurrence point. 'percentile' = percentile threshold. value parameter set . 'min.cv' = Threshold raster minimize coefficient variation (cv) posterior. Uses lowest tercile cv space. feasible Bayesian engines. 'TSS' = Determines optimal TSS (True Skill Statistic). Requires \"modEvA\" package installed. 'kappa' = Determines optimal kappa value (Kappa). Requires \"modEvA\" package installed. 'F1score' = Determines optimal F1score (also known Sorensen similarity). Requires \"modEvA\" package installed. 'F1score' = Determines optimal sensitivity presence records. Requires \"modEvA\" package installed. 'Sensitivity' = Determines optimal sensitivity presence records. Requires \"modEvA\" package installed. 'Specificity' = Determines optimal sensitivity presence records. Requires \"modEvA\" package installed. 'AUC' = Determines optimal AUC presence records. Requires \"modEvA\" package installed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"Lawson, C.R., Hodgson, J.., Wilson, R.J., Richards, S.., 2014. Prevalence, thresholds performance presence-absence models. Methods Ecol. Evol. 5, 54–64. https://doi.org/10.1111/2041-210X.12123 Liu, C., White, M., Newell, G., 2013. Selecting thresholds prediction species occurrence presence-data. J. Biogeogr. 40, 778–789. https://doi.org/10.1111/jbi.12058 Muscatello, ., Elith, J., Kujala, H., 2021. decisions fitting species distribution models affect conservation outcomes. Conserv. Biol. 35, 1309–1320. https://doi.org/10.1111/cobi.13669","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/threshold.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Threshold a continuous prediction to a categorical layer — threshold","text":"","code":"if (FALSE) {  # Where mod is an estimated DistributionModel  tr <- threshold(mod)  tr$plot_threshold() }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":null,"dir":"Reference","previous_headings":"","what":"Train the model from a given engine — train","title":"Train the model from a given engine — train","text":"function trains distribution() model specified engine furthermore generic options apply engines (regardless type). See Details regards options. Users advised check help files individual engines advice estimation done.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Train the model from a given engine — train","text":"","code":"train(   x,   runname,   filter_predictors = \"none\",   optim_hyperparam = FALSE,   inference_only = FALSE,   only_linear = TRUE,   method_integration = \"predictor\",   aggregate_observations = TRUE,   clamp = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for BiodiversityDistribution train(   x,   runname,   filter_predictors = \"none\",   optim_hyperparam = FALSE,   inference_only = FALSE,   only_linear = TRUE,   method_integration = \"predictor\",   aggregate_observations = TRUE,   clamp = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Train the model from a given engine — train","text":"x distribution() (.e. BiodiversityDistribution) object). runname character name trained run. filter_predictors character defining highly correlated predictors removed prior model estimation. Available options : \"none\" prior variable removal performed (Default). \"pearson\", \"spearman\" \"kendall\" Makes use pairwise comparisons identify remove highly collinear predictors (Pearson's r >= 0.7). \"abess\" -priori adaptive best subset selection covariates via \"abess\" package (see References). Note effectively fits separate generalized linear model reduce number covariates. \"boruta\" Uses \"Boruta\" package identify non-informative features. optim_hyperparam Parameter tune model iterating input parameters selection predictors included iteration. Can set TRUE extra precision needed (Default: FALSE). inference_only default engine used create spatial prediction suitability surface, can take time. inferences strength relationship covariates observations required, parameter can set TRUE ignore spatial projection (Default: FALSE). only_linear Fit model linear baselearners functions. Depending engine setting option FALSE result non-linear relationships observations covariates, often increasing processing time (Default: TRUE). non-linearity captured depends used engine. method_integration character type integration applied one BiodiversityDataset object provided x. Particular relevant engines support integration one dataset. Integration methods generally sensitive order added BiodiversityDistribution object. Available options : \"predictor\" predicted output first (previously fitted) models added predictor stack thus predictors subsequent models (Default). \"offset\" predicted output first (previously fitted) models added spatial offsets subsequent models. Offsets back-transformed depending model family. option might supported every Engine. \"interaction\" Instead fitting several separate models, observations dataset combined incorporated prediction factor interaction \"weaker\" data source partialed prediction. first dataset added determines reference level (see Leung et al. 2019 description). \"prior\" option make use coefficients previous model define priors used next model. Might work engine! \"weight\" option works multiple biodiversity datasets type (e.g. \"poipo\"). Individual weight multipliers can determined setting model (Note: Default 1). Datasets combined estimation weighted respectively, thus giving example presence-records less weight survey records. Note parameter ignored engines support joint likelihood estimation. aggregate_observations logical whether observations covering grid cell aggregated (Default: TRUE). clamp logical whether predictions clamped range predictor values observed model fitting (Default: FALSE). verbose Setting logical value TRUE prints information model fitting (Default: FALSE). ... arguments passed .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Train the model from a given engine — train","text":"DistributionModel object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Train the model from a given engine — train","text":"function acts generic training function - based provided BiodiversityDistribution object creates new distribution model. resulting object contains \"fit_best\" object estimated model , inference_only FALSE SpatRaster object named \"prediction\" contains spatial prediction model. objects can requested via object$get_data(\"fit_best\"). parameters function: \"filter_predictors\" parameter can set various options remove highly correlated variables little additional information gain model prior estimation. Available options \"none\" (Default) \"pearson\" applying 0.7 correlation cutoff, \"abess\" regularization framework Zhu et al. (2020), \"RF\" \"randomforest\" removing least important variables according randomForest model. Note: function applied predictors prior provided (e.g. potentially non-informative ones). \"optim_hyperparam\" option allows make use hyper-parameter search several models, can improve prediction accuracy although substantial increase computational cost. \"method_integration\" relevant one BiodiversityDataset supplied engine support joint integration likelihoods. See also Miller et al. (2019) references details different types integration. course, users want control aspect, another option fit separate models make use add_offset, add_offset_range ensemble functionalities. \"clamp\" Boolean parameter support clamping projection predictors range values observed model training.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Train the model from a given engine — train","text":"silver bullets (correlative) species distribution modelling model analyst understand objective, workflow parameters can used modify outcomes. Different predictions can obtained data parameters necessarily make sense useful.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Train the model from a given engine — train","text":"Miller, D..W., Pacifici, K., Sanderlin, J.S., Reich, B.J., 2019. recent past promising future data integration methods estimate species’ distributions. Methods Ecol. Evol. 10, 22–37. https://doi.org/10.1111/2041-210X.13110 Zhu, J., Wen, C., Zhu, J., Zhang, H., & Wang, X. (2020). polynomial algorithm best-subset selection problem. Proceedings National Academy Sciences, 117(52), 33117-33123. Leung, B., Hudgins, E. J., Potapova, . & Ruiz‐Jaen, M. C. new baseline countrywide α‐diversity species distributions: illustration using >6,000 plant species Panama. Ecol. Appl. 29, 1–13 (2019).","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/train.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Train the model from a given engine — train","text":"","code":"# Load example data  background <- terra::rast(system.file('extdata/europegrid_50km.tif',  package='ibis.iSDM',mustWork = TRUE))  # Get test species  virtual_points <- sf::st_read(system.file('extdata/input_data.gpkg',  package='ibis.iSDM',mustWork = TRUE),'points',quiet = TRUE)   # Get list of test predictors  ll <- list.files(system.file('extdata/predictors/', package = 'ibis.iSDM',  mustWork = TRUE),full.names = TRUE)  # Load them as rasters  predictors <- terra::rast(ll);names(predictors) <- tools::file_path_sans_ext(basename(ll))   # Use a basic GLM to fit a SDM  x <- distribution(background) |>         # Presence-only data         add_biodiversity_poipo(virtual_points, field_occurrence = \"Observed\") |>         # Add predictors and scale them         add_predictors(env = predictors, transform = \"scale\", derivates = \"none\") |>         # Use GLM as engine         engine_glm() #> [Setup] 2024-02-06 14:29:04.125701 | Creating distribution object... #> [Setup] 2024-02-06 14:29:04.126564 | Adding poipo dataset... #> [Setup] 2024-02-06 14:29:04.202381 | Adding predictors... #> [Setup] 2024-02-06 14:29:04.282382 | Transforming predictors...   # Train the model, Also filter out co-linear predictors using a pearson threshold  mod <- train(x, only_linear = TRUE, filter_predictors = 'pearson') #> [Estimation] 2024-02-06 14:29:04.400893 | Collecting input parameters. #> [Estimation] 2024-02-06 14:29:04.465414 | Filtering predictors via pearson... #> [Estimation] 2024-02-06 14:29:04.472977 | Adding engine-specific parameters. #> [Estimation] 2024-02-06 14:29:04.474246 | Engine setup. #> [Estimation] 2024-02-06 14:29:04.671971 | Starting fitting: Species:  #> [Estimation] 2024-02-06 14:29:04.714102 | Starting prediction... #> [Done] 2024-02-06 14:29:04.840259 | Completed after 0.44 secs  mod #> Trained GLM-Model (Unnamed run) #>   Strongest summary effects: #>      Positive: CLC3_112_mean_50km, CLC3_132_mean_50km, CLC3_211_mean_50km, ... (7) #>      Negative: aspect_mean_50km, bio03_mean_50km, slope_mean_50km (3) #>   Prediction fitted: yes"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":null,"dir":"Reference","previous_headings":"","what":"Validation of a fitted distribution object — validate","title":"Validation of a fitted distribution object — validate","text":"function conducts model evaluation based either fitted point data supplied independent. Currently supporting point datasets. validation integrated models work needed.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Validation of a fitted distribution object — validate","text":"","code":"validate(   mod,   method = \"continuous\",   layer = \"mean\",   point = NULL,   point_column = \"observed\",   ... )  # S4 method for ANY validate(   mod,   method = \"continuous\",   layer = \"mean\",   point = NULL,   point_column = \"observed\",   ... )  # S4 method for SpatRaster validate(   mod,   method = \"continuous\",   layer = NULL,   point = NULL,   point_column = \"observed\",   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Validation of a fitted distribution object — validate","text":"mod fitted BiodiversityDistribution object set predictors. Alternatively one can also provide directly SpatRaster, however case point layer also needs provided. method validation conducted continious prediction (previously calculated) thresholded layer binary format? Note depending method different metrics can computed. See Details. layer case multiple layers exist, one use? (Default: 'mean'). point sf object type POINT MULTIPOINT. point_column character vector name column containing independent observations. (Default: 'observed'). ... parameters passed . Currently unused.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Validation of a fitted distribution object — validate","text":"Return tidy tibble validation results.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Validation of a fitted distribution object — validate","text":"'validate' function calculates different validation metrics depending output type. output metrics type defined follows: Continuous: 'n' = Number observations. 'rmse' = Root Mean Square Error, $$ \\sqrt {\\frac{1}{N} \\sum_{=1}^{N} (\\hat{y_{}} - y_{})^2} $$ 'mae' = Mean Absolute Error, $$ \\frac{ \\sum_{=1}^{N} y_{} - x_{} }{n} $$ 'logloss' = Log loss, TBD 'normgini' = Normalized Gini index, TBD 'cont.boyce' = Continuous Boyce index, TBD Discrete: 'n' = Number observations. 'auc' = Area curve, TBD 'overall.accuracy' = Overall Accuracy, TBD 'true.presence.ratio' = True presence ratio Jaccard index, TBD 'precision' = Precision, TBD 'sensitivity' = Sensitivity, TBD 'specificity' = Specifivity, TBD 'tss' = True Skill Statistics, TBD 'f1' = F1 Score Positive predictive value, $$ \\frac{2TP}{2TP + FP + FN} $$ 'logloss' = Log loss, TBD 'expected.accuracy' = Expected Accuracy, $$ \\frac{TP + FP}{N} x \\frac{TP + FN}{N} + \\frac{TN + FN}{N} x \\frac{TN + FP}{N} $$ 'kappa' = Kappa value, $$ \\frac{2 (TP x TN - FN x FP)}{(TP + FP) x (FP + TN) + (TP + FN) x (FN + TN) } $$, 'brier.score' = Brier score, $$ \\frac{ \\sum_{=1}^{N} (y_{} - x_{})^{2} }{n} $$, $y_i$ predicted presence absence $x_i$ observed. TP true positive, TN true negative, FP false positive FN false negative.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Validation of a fitted distribution object — validate","text":"use Boyce Index, please cite original Hirzel et al. (2006) paper.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"references","dir":"Reference","previous_headings":"","what":"References","title":"Validation of a fitted distribution object — validate","text":"Liu, C., White, M., Newell, G., 2013. Selecting thresholds prediction species occurrence presence-data. J. Biogeogr. 40, 778–789. https://doi.org/10.1111/jbi.12058 Hirzel, . H., Le Lay, G., Helfer, V., Randin, C., & Guisan, . (2006). Evaluating ability habitat suitability models predict species presences. Ecological modelling, 199(2), 142-152.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/validate.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Validation of a fitted distribution object — validate","text":"","code":"if (FALSE) {  # Assuming that mod is a distribution object and has a thresholded layer  mod <- threshold(mod, method = \"TSS\")  validate(mod, method = \"discrete\")  }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":null,"dir":"Reference","previous_headings":"","what":"Wrap a list with stan model code — wrap_stanmodel","title":"Wrap a list with stan model code — wrap_stanmodel","text":"engine_stan builds list stan model code. function concatenates together.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Wrap a list with stan model code — wrap_stanmodel","text":"","code":"wrap_stanmodel(sm_code)"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Wrap a list with stan model code — wrap_stanmodel","text":"sm_code list object exactly 7 entries.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/wrap_stanmodel.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Wrap a list with stan model code — wrap_stanmodel","text":"character object.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":null,"dir":"Reference","previous_headings":"","what":"Save a model for later use — write_model","title":"Save a model for later use — write_model","text":"write_model function (opposed write_output) generic wrapper writing DistributionModel disk. essentially wrapper saveRDS. Models can loaded via load_model function.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Save a model for later use — write_model","text":"","code":"write_model(   mod,   fname,   slim = FALSE,   verbose = getOption(\"ibis.setupmessages\") )  # S4 method for ANY write_model(   mod,   fname,   slim = FALSE,   verbose = getOption(\"ibis.setupmessages\") )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Save a model for later use — write_model","text":"mod Provided DistributionModel object. fname character depicting output filename. slim logical option whether unnecessary entries model object deleted. deletes example predictions non-model content object (Default: FALSE). verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Save a model for later use — write_model","text":"R-output created. file written target direction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Save a model for later use — write_model","text":"default output files overwritten already existing!","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_model.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Save a model for later use — write_model","text":"","code":"if (FALSE) { x <- distribution(background) |>  add_biodiversity_poipo(virtual_points, field_occurrence = 'observed', name = 'Virtual points') |>  add_predictors(pred_current, transform = 'scale',derivates = 'none') |>  engine_xgboost(nrounds = 2000) |> train(varsel = FALSE, only_linear = TRUE) write_model(x, \"testmodel.rds\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":null,"dir":"Reference","previous_headings":"","what":"Generic function to write spatial outputs — write_output","title":"Generic function to write spatial outputs — write_output","text":"write_output function generic wrapper writing output files (e.g. projections) created ibis.iSDM-package. possible write outputs fitted DistributionModel, BiodiversityScenario individual terra stars objects. case data.frame supplied, output written csv file. creating summaries distribution scenario parameters performance, see write_summary()","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Generic function to write spatial outputs — write_output","text":"","code":"write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for ANY,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for BiodiversityScenario,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for SpatRaster,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for data.frame,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for stars,character write_output(   mod,   fname,   dt = \"FLT4S\",   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Generic function to write spatial outputs — write_output","text":"mod Provided DistributionModel, BiodiversityScenario, terra stars object. fname character depicting output filename. dt character output datatype. Following terra::writeRaster options (Default: 'FLT4S'). verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE). ... arguments passed individual functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Generic function to write spatial outputs — write_output","text":"R-output created. file written target direction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Generic function to write spatial outputs — write_output","text":"default output files overwritten already existing!","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_output.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Generic function to write spatial outputs — write_output","text":"","code":"if (FALSE) { x <- distribution(background)  |>  add_biodiversity_poipo(virtual_points, field_occurrence = 'observed', name = 'Virtual points') |>  add_predictors(pred_current, transform = 'scale',derivates = 'none') |>  engine_xgboost(nrounds = 2000) |> train(varsel = FALSE, only_linear = TRUE) write_output(x, \"testmodel.tif\") }"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":null,"dir":"Reference","previous_headings":"","what":"Generic function to write summary outputs from created models. — write_summary","title":"Generic function to write summary outputs from created models. — write_summary","text":"write_summary function wrapper function create summaries fitted DistributionModel BiodiversityScenario objects. function extract parameters statistics used data input object writes output either 'rds' 'rdata' file. Alternative, open file formats consideration.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Generic function to write summary outputs from created models. — write_summary","text":"","code":"write_summary(   mod,   fname,   partial = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )  # S4 method for ANY,character write_summary(   mod,   fname,   partial = FALSE,   verbose = getOption(\"ibis.setupmessages\"),   ... )"},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Generic function to write summary outputs from created models. — write_summary","text":"mod Provided DistributionModel BiodiversityScenario object. fname character depicting output filename. suffix determines file type output (Options: 'rds', 'rdata'). partial logical value determining whether partial variable contributions calculated added model summary. Note can rather slow (Default: FALSE). verbose logical indicating whether messages shown. Overwrites getOption(\"ibis.setupmessages\") (Default: TRUE). ... arguments passed individual functions.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Generic function to write summary outputs from created models. — write_summary","text":"R-output created. file written target direction.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"note","dir":"Reference","previous_headings":"","what":"Note","title":"Generic function to write summary outputs from created models. — write_summary","text":"predictions tabular data saved function. Use write_output() save .","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/reference/write_summary.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Generic function to write summary outputs from created models. — write_summary","text":"","code":"if (FALSE) { x <- distribution(background) |>  add_biodiversity_poipo(virtual_points, field_occurrence = 'observed', name = 'Virtual points')  |>  add_predictors(pred_current, transform = 'scale',derivates = 'none') |>  engine_xgboost(nrounds = 2000) |> train(varsel = FALSE, only_linear = TRUE) write_summary(x, \"testmodel.rds\") }"},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-1-2","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.1.2 (current dev branch)","text":"Switched object structure R6 throughout improved data memory handling #44 Implemented convenience function ro remove biodiversity datasets (rm_biodiversity()).","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-1-2","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.1.2 (current dev branch)","text":"Added logical parameter ensemble() enabling compositing thresholds set #84 Support multi-band rasters ensemble() convenience. Fix bug threshold() supplied point data improved error messages. Cleaner docs structure","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-1-1","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.1.1","text":"Added default engine_glm() dependency-free inference projection. Harmonized controls settings added option contrain extrapolation add_control_extrapolation() Adding function temporal interpolation predictors #52","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-1-1","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.1.1","text":"Minor corrective fixes additions add_offset(). Switch engine_glm() many unittests better coverage. Several bug fixes improvements thin_observations() global, probs, centers argument better control thin_observations() Harmonization parameters spartial() addressing #80","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-1-0","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.1.0","text":"Added small convenience wrapper add model outputs another model add_predictors_model() Started adding mechanistic SDM vignette #67 Wrapper steps implemented via simulate_population_steps() #68","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-1-0","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.1.0","text":"Added R-universe installation option alternative github #38 Minor bug fixes scenario() object, MigClim Kissmig wrappers. Bug fix related CRS classes sp sf Bug fix related blas.num.threads Bug fix crashed write_summary() outputs prediction made. Bug fix related CRS engine_inla() Bug fix engine_stan() related background layer Class biodiversity data identical PO PA Bug fix built_formula_glmnet() response Bug fix built_formula_gdb() response model$biodiversity stores predictors current ID Bug fix built_formula_inla() INLABRU","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-9","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.9","text":"Added new vignette available functions data preparation #67 Addition small mask() function emulates terra.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-9","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.9","text":"Small fix ensemble() ensembles future scenarios use correct standardization. Small fix threshold() now returning threshold values correctly. Bug fix error catching distribution() ensemble_partial(),ensemble_spartial() checks added check() #45 Small fix alignRasters(). Small fix harmonize field_column throughout. Improved error messages handling formula’s.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-8","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.8","text":"Implemented min size constraint (add_constraint_minsize()) #56 Added function estimating partial effects ensembles ensemble_spartial().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-8","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.8","text":"Added warnings checks missing crs supplied layers #65 Smaller bug code harmonizations ensemble_partial(), partial() spartial(). Smaller bug fixes threshold() scenario() projections. Improved error messages several functions. documentation fixes towards CRAN submission #38 Allow specify location biodiversity point records threshold().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-7","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.7","text":"Added method proximity add_control_bias() place lower weights points closer another. Added helper functions get_data() option apply threshold() directly BiodiversityScenarios. Added centroid function BiodiversityScenarios DistributionModels #29","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-7","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.7","text":"Add Error message background data different units easier understand. Added warning message threshold creation use independent data possible. Fixed min.cv bug threshold() introduced #17 Fixed add_offset() function now also allowing sf objects input. Fixed bug writing outputs write_output() Fixed bug prediction limits work correctly (distribution(...,lim = x))","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-6","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.6","text":"partial_density() function implemented #57 Re-specification limits implementation minimum convex polygon limits distribution(). Added check() function assessing assumptions fits various objects #45 Added minor internal helper functions duplicate stars objects via st_rep. Implemented local limiting factor function (limiting()) #37","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-6","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.6","text":"smaller documentation fixes towards CRAN submission #38 Bug fix method buffer pseudo-absence settings. Minor bug fixes ensemble() uncertainty calculations.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-5","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.5","text":"Addition 5 parameter logistic curve offsets parameter search add_offset().","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-5","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.5","text":"smaller documentation fixes towards CRAN submission #38 Bug write_model(), now converting terra objects data.frame import/export. Smaller bug fixes, example similarity(), addition variable name sanitization predictors default.","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-4","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.4","text":"Smaller bug fixes regards writing outputs adding pseudo-absences. Added short convenience function convert prediction outputs #48 Converted raster terra #17 Updated added unit checks tests","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"new-features-0-0-3","dir":"Changelog","previous_headings":"","what":"New features","title":"ibis.iSDM 0.0.3","text":"Aded Boruta iterative feature selection predictor variables.","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-3","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.3","text":"Removed Magittr dependency #41 Smaller improvements documentation removing CRAN preventing function calls. Made separation hyperparameter search functions clearer added new option filter highly correlated covariates via train().","code":""},{"path":[]},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"minor-improvements-and-bug-fixes-0-0-2","dir":"Changelog","previous_headings":"","what":"Minor improvements and bug fixes","title":"ibis.iSDM 0.0.2","text":"Smaller documentation fixes, including make sure examples returns exported function documentations. Preparation cran release #38, including fixing common issues checks. smaller bug fixes validate() make Boyce robust. Change logo. Thanks @elliwoto Added warning validate call users aware non-independent validation. fixes github actions tests @mhesselbarth","code":""},{"path":"https://iiasa.github.io/ibis.iSDM/news/index.html","id":"ibisisdm-001","dir":"Changelog","previous_headings":"","what":"ibis.iSDM 0.0.1","title":"ibis.iSDM 0.0.1","text":"Initial public release version! Finding fixing bugs…","code":""}]