diff --git a/public/2023-08-usgs/images/R_RStudio.png b/public/2023-08-usgs/images/R_RStudio.png new file mode 100644 index 00000000..a3651726 Binary files /dev/null and b/public/2023-08-usgs/images/R_RStudio.png differ diff --git a/public/2023-08-usgs/images/install-pkg-success.png b/public/2023-08-usgs/images/install-pkg-success.png new file mode 100644 index 00000000..defeca28 Binary files /dev/null and b/public/2023-08-usgs/images/install-pkg-success.png differ diff --git a/public/2023-08-usgs/images/rstudio-logo.png b/public/2023-08-usgs/images/rstudio-logo.png new file mode 100644 index 00000000..28d3ad2c Binary files /dev/null and b/public/2023-08-usgs/images/rstudio-logo.png differ diff --git a/public/2023-08-usgs/index.html b/public/2023-08-usgs/index.html index f42a3520..a2c43064 100644 --- a/public/2023-08-usgs/index.html +++ b/public/2023-08-usgs/index.html @@ -2,7 +2,7 @@ - + @@ -47,7 +47,13 @@ "collapse-after": 3, "panel-placement": "start", "type": "textbox", - "limit": 20, + "limit": 50, + "keyboard-shortcut": [ + "f", + "/", + "s" + ], + "show-item-context": false, "language": { "search-no-results-text": "No results", "search-matching-documents-text": "matching documents", @@ -56,6 +62,7 @@ "search-more-match-text": "more match in this document", "search-more-matches-text": "more matches in this document", "search-clear-button-title": "Clear", + "search-text-placeholder": "", "search-detached-cancel-button-title": "Cancel", "search-submit-button-title": "Submit", "search-label": "Search" @@ -72,12 +79,12 @@
-
+
+
+

Overview

-

+

-

+

@@ -349,10 +398,9 @@

About this book

// clear code selection e.clearSelection(); }); - function tippyHover(el, contentFn) { + function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) { const config = { allowHTML: true, - content: contentFn, maxWidth: 500, delay: 100, arrow: false, @@ -362,8 +410,17 @@

About this book

interactive: true, interactiveBorder: 10, theme: 'quarto', - placement: 'bottom-start' + placement: 'bottom-start', }; + if (contentFn) { + config.content = contentFn; + } + if (onTriggerFn) { + config.onTrigger = onTriggerFn; + } + if (onUntriggerFn) { + config.onUntrigger = onUntriggerFn; + } window.tippy(el, config); } const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]'); @@ -377,6 +434,125 @@

About this book

const note = window.document.getElementById(id); return note.innerHTML; }); + } + const xrefs = window.document.querySelectorAll('a.quarto-xref'); + const processXRef = (id, note) => { + // Strip column container classes + const stripColumnClz = (el) => { + el.classList.remove("page-full", "page-columns"); + if (el.children) { + for (const child of el.children) { + stripColumnClz(child); + } + } + } + stripColumnClz(note) + if (id === null || id.startsWith('sec-')) { + // Special case sections, only their first couple elements + const container = document.createElement("div"); + if (note.children && note.children.length > 2) { + container.appendChild(note.children[0].cloneNode(true)); + for (let i = 1; i < note.children.length; i++) { + const child = note.children[i]; + if (child.tagName === "P" && child.innerText === "") { + continue; + } else { + container.appendChild(child.cloneNode(true)); + break; + } + } + if (window.Quarto?.typesetMath) { + window.Quarto.typesetMath(container); + } + return container.innerHTML + } else { + if (window.Quarto?.typesetMath) { + window.Quarto.typesetMath(note); + } + return note.innerHTML; + } + } else { + // Remove any anchor links if they are present + const anchorLink = note.querySelector('a.anchorjs-link'); + if (anchorLink) { + anchorLink.remove(); + } + if (window.Quarto?.typesetMath) { + window.Quarto.typesetMath(note); + } + // TODO in 1.5, we should make sure this works without a callout special case + if (note.classList.contains("callout")) { + return note.outerHTML; + } else { + return note.innerHTML; + } + } + } + for (var i=0; i res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.getElementById(id); + if (note !== null) { + const html = processXRef(id, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + } else { + // See if we can fetch a full url (with no hash to target) + // This is a special case and we should probably do some content thinning / targeting + fetch(url) + .then(res => res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.querySelector('main.content'); + if (note !== null) { + // This should only happen for chapter cross references + // (since there is no id in the URL) + // remove the first header + if (note.children.length > 0 && note.children[0].tagName === "HEADER") { + note.children[0].remove(); + } + const html = processXRef(null, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + }, function(instance) { + }); } let selectedAnnoteEl; const selectorForAnnotation = ( cell, annotation) => { @@ -419,6 +595,7 @@

About this book

} div.style.top = top - 2 + "px"; div.style.height = height + 4 + "px"; + div.style.left = 0; let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter"); if (gutterDiv === null) { gutterDiv = window.document.createElement("div"); @@ -444,6 +621,32 @@

About this book

}); selectedAnnoteEl = undefined; }; + // Handle positioning of the toggle + window.addEventListener( + "resize", + throttle(() => { + elRect = undefined; + if (selectedAnnoteEl) { + selectCodeLines(selectedAnnoteEl); + } + }, 10) + ); + function throttle(fn, ms) { + let throttle = false; + let timer; + return (...args) => { + if(!throttle) { // first call gets through + fn.apply(this, args); + throttle = true; + } else { // all the others get throttled + if(timer) clearTimeout(timer); // cancel #2 + timer = setTimeout(() => { + fn.apply(this, args); + timer = throttle = false; + }, ms); + } + }; + } // Attach click handler to the DT const annoteDls = window.document.querySelectorAll('dt[data-target-cell]'); for (const annoteDlNode of annoteDls) { @@ -507,7 +710,7 @@

About this book

- + 1  Successful Synthesis Science
@@ -516,4 +719,5 @@

About this book

+ \ No newline at end of file diff --git a/public/2023-08-usgs/search.json b/public/2023-08-usgs/search.json index f4c1352e..3d2e8d8b 100644 --- a/public/2023-08-usgs/search.json +++ b/public/2023-08-usgs/search.json @@ -4,181 +4,422 @@ "href": "index.html", "title": "NCEAS openS for the Climate Adaptation Postdoctoral (CAP) Fellows: Future of Aquatic Flows Cohort", "section": "", - "text": "Overview" + "text": "Overview", + "crumbs": [ + "Overview" + ] }, { "objectID": "index.html#about-this-training", "href": "index.html#about-this-training", "title": "NCEAS openS for the Climate Adaptation Postdoctoral (CAP) Fellows: Future of Aquatic Flows Cohort", "section": "About this training", - "text": "About this training\nThe NCEAS openS Program consists of three 1-week long workshops, geared towards early career researchers. Participants engage in a mix of lectures, exercises, and synthesis research activities to conduct synthesis science and implement best practices in open data science.\nopenS has been adapted to coincide with each USGS CAP training, for a total of four training sessions across 2 years." + "text": "About this training\nThe NCEAS openS Program consists of three 1-week long workshops, geared towards early career researchers. Participants engage in a mix of lectures, exercises, and synthesis research activities to conduct synthesis science and implement best practices in open data science.\nopenS has been adapted to coincide with each USGS CAP training, for a total of four training sessions across 2 years.", + "crumbs": [ + "Overview" + ] }, { "objectID": "index.html#why-nceas", "href": "index.html#why-nceas", "title": "NCEAS openS for the Climate Adaptation Postdoctoral (CAP) Fellows: Future of Aquatic Flows Cohort", "section": "Why NCEAS", - "text": "Why NCEAS\nThe National Center for Ecological Analysis and Synthesis (NCEAS), a research affiliate of the University of California, Santa Barbara, is a leading expert on interdisciplinary data science and works collaboratively to answer the world’s largest and most complex questions. The NCEAS approach leverages existing data and employs a team science philosophy to squeeze out all potential insights and solutions efficiently - this is called synthesis science.\nNCEAS has over 25 years of success with this model among working groups and environmental professionals, and we are excited to pass on this cumulative expertise to you." + "text": "Why NCEAS\nThe National Center for Ecological Analysis and Synthesis (NCEAS), a research affiliate of the University of California, Santa Barbara, is a leading expert on interdisciplinary data science and works collaboratively to answer the world’s largest and most complex questions. The NCEAS approach leverages existing data and employs a team science philosophy to squeeze out all potential insights and solutions efficiently - this is called synthesis science.\nNCEAS has over 25 years of success with this model among working groups and environmental professionals, and we are excited to pass on this cumulative expertise to you.", + "crumbs": [ + "Overview" + ] }, { "objectID": "index.html#week-one-successful-synthesis-and-data-management-best-practices", "href": "index.html#week-one-successful-synthesis-and-data-management-best-practices", "title": "NCEAS openS for the Climate Adaptation Postdoctoral (CAP) Fellows: Future of Aquatic Flows Cohort", "section": "Week One: Successful Synthesis and Data Management Best Practices", - "text": "Week One: Successful Synthesis and Data Management Best Practices\n\nLearning Objectives:\n\nImplement reproducible scientific workflows throughout all aspects of a project\nIncrease your familiarity and confidence with data science tools\nEffectively manage and wrangle data using tidy data practices\nAccessing, interpreting and developing metadata for synthesis research\nOrganize and initiate synthesis projects\n\n\n\nSchedule\n\n\n\n\n\n\n\n\n\nDate\nTime\nSession Title\nLead Facilitator\n\n\n\n\nMonday 08/21\nBlock 3\n1:45PM-3:15PM\nSuccessful Synthesis Science\nHalina Do-Linh, Data Training Program Manager\n\n\nTuesday 08/22\nBlock 2\n10:45AM-12:15PM\nPanel for PIs: Successful Mentorship in Synthesis Science\nHalina Do-Linh, Data Training Program Manager\n\n\nWednesday 08/23\nBlock 1\n9AM-10:30AM\nData Management Essentials\nCamila Vargas Poulsen, Data Training Coordinator" + "text": "Week One: Successful Synthesis and Data Management Best Practices\n\nLearning Objectives:\n\nImplement reproducible scientific workflows throughout all aspects of a project\nIncrease your familiarity and confidence with data science tools\nEffectively manage and wrangle data using tidy data practices\nAccessing, interpreting and developing metadata for synthesis research\nOrganize and initiate synthesis projects\n\n\n\nSchedule\n\n\n\n\n\n\n\n\n\nDate\nTime\nSession Title\nLead Facilitator\n\n\n\n\nMonday 08/21\nBlock 3\n1:45PM-3:15PM\nSuccessful Synthesis Science\nHalina Do-Linh, Data Training Program Manager\n\n\nTuesday 08/22\nBlock 2\n10:45AM-12:15PM\nPanel for PIs: Successful Mentorship in Synthesis Science\nHalina Do-Linh, Data Training Program Manager\n\n\nWednesday 08/23\nBlock 1\n9AM-10:30AM\nData Management Essentials\nCamila Vargas Poulsen, Data Training Coordinator", + "crumbs": [ + "Overview" + ] }, { "objectID": "index.html#code-of-conduct", "href": "index.html#code-of-conduct", "title": "NCEAS openS for the Climate Adaptation Postdoctoral (CAP) Fellows: Future of Aquatic Flows Cohort", "section": "Code of Conduct", - "text": "Code of Conduct\nBy participating in this activity you agree to abide by the NCEAS Code of Conduct." + "text": "Code of Conduct\nBy participating in this activity you agree to abide by the NCEAS Code of Conduct.", + "crumbs": [ + "Overview" + ] }, { "objectID": "index.html#about-this-book", "href": "index.html#about-this-book", "title": "NCEAS openS for the Climate Adaptation Postdoctoral (CAP) Fellows: Future of Aquatic Flows Cohort", "section": "About this book", - "text": "About this book\nThese written materials are the result of a continuous and collaborative effort at NCEAS with the support of DataONE, to help researchers make their work more transparent and reproducible. This work began in the early 2000’s, and reflects the expertise and diligence of many, many individuals. The primary authors for this version are listed in the citation below, with additional contributors recognized for their role in developing previous iterations of these or similar materials.\nThis work is licensed under a Creative Commons Attribution 4.0 International License.\nCitation: Halina Do-Linh, Camila Vargas Poulsen. 2023. openS for USGS Climate Adaptation Postdoctoral (CAP) Fellows Program. Week One. NCEAS Learning Hub & USGS Climate Adaptation Science Centers (CASCs).\nAdditional contributors: Ben Bolker, Julien Brun, Amber E. Budden, Jeanette Clark, Samantha Csik, Carmen Galaz García, Stephanie Hampton, Natasha Haycock-Chavez, Matthew B. Jones, Samanta Katz, Julie Lowndes, Erin McLean, Bryce Mecum, Deanna Pennington, Karthik Ram, Jim Regetz, Tracy Teal, Daphne Virlar-Knight, Leah Wasser.\nThis is a Quarto book. To learn more about Quarto books visit https://quarto.org/docs/books." + "text": "About this book\nThese written materials are the result of a continuous and collaborative effort at NCEAS with the support of DataONE, to help researchers make their work more transparent and reproducible. This work began in the early 2000’s, and reflects the expertise and diligence of many, many individuals. The primary authors for this version are listed in the citation below, with additional contributors recognized for their role in developing previous iterations of these or similar materials.\nThis work is licensed under a Creative Commons Attribution 4.0 International License.\nCitation: Halina Do-Linh, Camila Vargas Poulsen. 2023. openS for USGS Climate Adaptation Postdoctoral (CAP) Fellows Program. Week One. NCEAS Learning Hub & USGS Climate Adaptation Science Centers (CASCs).\nAdditional contributors: Ben Bolker, Julien Brun, Amber E. Budden, Jeanette Clark, Samantha Csik, Carmen Galaz García, Stephanie Hampton, Natasha Haycock-Chavez, Matthew B. Jones, Samanta Katz, Julie Lowndes, Erin McLean, Bryce Mecum, Deanna Pennington, Karthik Ram, Jim Regetz, Tracy Teal, Daphne Virlar-Knight, Leah Wasser.\nThis is a Quarto book. To learn more about Quarto books visit https://quarto.org/docs/books.", + "crumbs": [ + "Overview" + ] + }, + { + "objectID": "session_01.html", + "href": "session_01.html", + "title": "1  Successful Synthesis Science", + "section": "", + "text": "Learning Objectives", + "crumbs": [ + "Week 1", + "1  Successful Synthesis Science" + ] }, { "objectID": "session_01.html#learning-objectives", "href": "session_01.html#learning-objectives", "title": "1  Successful Synthesis Science", - "section": "Learning Objectives", - "text": "Learning Objectives\n\nIdentify synthesis science research and different synthesis science approaches\nImplement synthesis science approaches to your research" + "section": "", + "text": "Identify synthesis science research and different synthesis science approaches\nImplement synthesis science approaches to your research", + "crumbs": [ + "Week 1", + "1  Successful Synthesis Science" + ] }, { "objectID": "session_01.html#what-is-synthesis-science", "href": "session_01.html#what-is-synthesis-science", "title": "1  Successful Synthesis Science", "section": "1.1 What is Synthesis Science?", - "text": "1.1 What is Synthesis Science?\n\n\n\nGraphic by Judith Sitters\n\n\n\n\n\n\n\n\nSynthesis Science in Ecological and Environmental Sciences\n\n\n\nSynthesis science is the process of distilling existing data, ideas, theories, or methods drawn from many sources, across multiple fields of inquiry, to accelerate the generation of new scientific knowledge, often at a broad scale.\n\n\nTo break that down further, think of it this way: synthesis science utilizes existing data and knowledge to generate new insights. It’s like putting together puzzle pieces from different sources to create a bigger picture.\nSynthesis science is fundamentally different from other types of academic research in that it does not involve collecting new or original data to conduct research or to answer a research question.\nSince the ecological and environmental sciences are complex and often interdisciplinary, synthesis approaches are ideal for “understanding complexity across scales, leveraging data from various disciplines, facilitating the discovery of general patterns in natural systems, and informing policy” (Halpern et al. 2023) in the ecological and environmental sciences.\n\n1.1.1 The Value and Impact of Synthesis Research\n\n\n\nGraphic adapted from Engingeering Ideas newsletter on Substack\n\n\nData is everywhere and information is more accessible than ever, but how can we leverage both data and knowledge to further our understanding of a topic and turn those insights into meaningful action? This is where synthesis research shines.\nThere are many studies that value the importance of synthesis for varying reasons including:\n\nElevating scientific research as evidence that is influential in policy-making (Dicks, Walsh, and Sutherland 2014)\nAddressing the challenge of “information overload” (Hampton and Parker 2011)\nDelivering research products that enhance scientific knowledge in decision-making (Hampton and Parker 2011)\nProviding critical knowledge to solve environmental issues (Carpenter et al. 2009)\nInitiating new collaborations and new insights across disciplines and non-academic sectors (Hampton and Parker 2011)\n\nAs synthesis science and research synthesis approaches have been gaining prominence in the ecological and environmental fields, researchers have sought to understand the impacts of synthesis. In particular, Wyborn et al. (2018) identified the following types of impacts from research synthesis:\n\nKnowledge is used to change understanding of a system or phenomena\nKnowledge changes understanding of the interconnections between actors, sectors or systems\nKnowledge is used to support a particular view of a problem\nKnowledge is used as the prime source of information to inform policy change or reform\nKnowledge use is dependent on the capacity to understand or apply knowledge in a given context" + "text": "1.1 What is Synthesis Science?\n\n\n\nGraphic by Judith Sitters\n\n\n\n\n\n\n\n\nSynthesis Science in Ecological and Environmental Sciences\n\n\n\nSynthesis science is the process of distilling existing data, ideas, theories, or methods drawn from many sources, across multiple fields of inquiry, to accelerate the generation of new scientific knowledge, often at a broad scale.\n\n\nTo break that down further, think of it this way: synthesis science utilizes existing data and knowledge to generate new insights. It’s like putting together puzzle pieces from different sources to create a bigger picture.\nSynthesis science is fundamentally different from other types of academic research in that it does not involve collecting new or original data to conduct research or to answer a research question.\nSince the ecological and environmental sciences are complex and often interdisciplinary, synthesis approaches are ideal for “understanding complexity across scales, leveraging data from various disciplines, facilitating the discovery of general patterns in natural systems, and informing policy” (Halpern et al. 2023) in the ecological and environmental sciences.\n\n1.1.1 The Value and Impact of Synthesis Research\n\n\n\nGraphic adapted from Engingeering Ideas newsletter on Substack\n\n\nData is everywhere and information is more accessible than ever, but how can we leverage both data and knowledge to further our understanding of a topic and turn those insights into meaningful action? This is where synthesis research shines.\nThere are many studies that value the importance of synthesis for varying reasons including:\n\nElevating scientific research as evidence that is influential in policy-making (Dicks, Walsh, and Sutherland 2014)\nAddressing the challenge of “information overload” (Hampton and Parker 2011)\nDelivering research products that enhance scientific knowledge in decision-making (Hampton and Parker 2011)\nProviding critical knowledge to solve environmental issues (Carpenter et al. 2009)\nInitiating new collaborations and new insights across disciplines and non-academic sectors (Hampton and Parker 2011)\n\nAs synthesis science and research synthesis approaches have been gaining prominence in the ecological and environmental fields, researchers have sought to understand the impacts of synthesis. In particular, Wyborn et al. (2018) identified the following types of impacts from research synthesis:\n\nKnowledge is used to change understanding of a system or phenomena\nKnowledge changes understanding of the interconnections between actors, sectors or systems\nKnowledge is used to support a particular view of a problem\nKnowledge is used as the prime source of information to inform policy change or reform\nKnowledge use is dependent on the capacity to understand or apply knowledge in a given context", + "crumbs": [ + "Week 1", + "1  Successful Synthesis Science" + ] }, { "objectID": "session_01.html#research-synthesis-approaches", "href": "session_01.html#research-synthesis-approaches", "title": "1  Successful Synthesis Science", "section": "1.2 Research Synthesis Approaches", - "text": "1.2 Research Synthesis Approaches\nIn general, research synthesis approaches include utilizing existing research on a particular topic with the intention of integrating all the findings together.\nThere are multiple different types of approaches such as narrative reviews, vote counting (this quantitative method has been discredited, but you may find examples of it in your research), case studies, and more. However, systematic reviews and meta-analysis are considered by some to be the “gold standard” of research synthesis and are often used at NCEAS, which is why we’re highlighting them here.\n\n\n\n\n\n\n\nSystematic Review\nA form of synthesis to study a specific question or problem by following clear steps: finding and choosing studies, checking them carefully, and gathering information from them to create a reliable review.\nNote: Not all systematic reviews contain meta-analysis\n\n\nMeta-Analysis\nA form of synthesis that uses statistical and quantitative methods to integrate and compare (quantitatively) results from a large number of individual studies.\n\n\n\n\n1.2.1 What about data?\nData is essential to synthesis in ecological and environmental research. Synthesizing data can involve combining and analyzing data from multiple sources to address research questions, to conduct a systematic review or meta-analysis, to identify patterns, and draw meaningful conclusions that don’t appear in siloed approaches.\nAt NCEAS, our approach tends to include combining multiple datasets from various sources, then we leverage specific expertise from diverse disciplines and researchers, and together we use those two elements to unleash new insights to answer large-scale questions.\nWe often see this approach with working groups at NCEAS. Working groups are teams that include researchers, agencies and organizational practitioners, and more who come together (and typically at NCEAS, a neutral ground) for focused and intensive working sessions around their research questions." + "text": "1.2 Research Synthesis Approaches\nIn general, research synthesis approaches include utilizing existing research on a particular topic with the intention of integrating all the findings together.\nThere are multiple different types of approaches such as narrative reviews, vote counting (this quantitative method has been discredited, but you may find examples of it in your research), case studies, and more. However, systematic reviews and meta-analysis are considered by some to be the “gold standard” of research synthesis and are often used at NCEAS, which is why we’re highlighting them here.\n\n\n\n\n\n\n\nSystematic Review\nA form of synthesis to study a specific question or problem by following clear steps: finding and choosing studies, checking them carefully, and gathering information from them to create a reliable review.\nNote: Not all systematic reviews contain meta-analysis\n\n\nMeta-Analysis\nA form of synthesis that uses statistical and quantitative methods to integrate and compare (quantitatively) results from a large number of individual studies.\n\n\n\n\n1.2.1 What about data?\nData is essential to synthesis in ecological and environmental research. Synthesizing data can involve combining and analyzing data from multiple sources to address research questions, to conduct a systematic review or meta-analysis, to identify patterns, and draw meaningful conclusions that don’t appear in siloed approaches.\nAt NCEAS, our approach tends to include combining multiple datasets from various sources, then we leverage specific expertise from diverse disciplines and researchers, and together we use those two elements to unleash new insights to answer large-scale questions.\nWe often see this approach with working groups at NCEAS. Working groups are teams that include researchers, agencies and organizational practitioners, and more who come together (and typically at NCEAS, a neutral ground) for focused and intensive working sessions around their research questions.", + "crumbs": [ + "Week 1", + "1  Successful Synthesis Science" + ] }, { "objectID": "session_01.html#nceas-and-synthesis-science", "href": "session_01.html#nceas-and-synthesis-science", "title": "1  Successful Synthesis Science", "section": "1.3 NCEAS and Synthesis Science", - "text": "1.3 NCEAS and Synthesis Science\n\n\n\n\n\nIn 1995, the National Science Foundation (NSF) responded to the increasing calls by environmental researchers and professionals for interdisciplinary and transdisciplinary explanations, methods to connect science to applications, and ways to advance research technologies by creating NCEAS, the first synthesis center.\nThere are multiple other synthesis centers that have been established since, but each one has a foundational goal to use synthesis to “advance basic science, organize ecological information for decision makers concerned with pressing national issues, and make cost-effective use of the nation’s extant and accumulating database” (Hampton and Parker 2011).\nSynthesis centers are specifically designed to catalyze collaboration leading to breakthrough ideas, and one way NCEAS (among other synthesis centers) achieves this is through working groups. Since its inception, NCEAS has hosted hundreds of working groups and has supported them in varying ways including: structuring group size or composition, facilitating of working sessions, supplying computing and informatics support, offering training opportunities for data-focused team members, providing a neutral space for meetings and co-working, and more. In short, NCEAS lowers the “activation energy” for working group members so that they can focus on the cross-pollination of ideas, creative thinking, and emergent research (Rodrigo et al. 2013)." + "text": "1.3 NCEAS and Synthesis Science\n\n\n\n\n\nIn 1995, the National Science Foundation (NSF) responded to the increasing calls by environmental researchers and professionals for interdisciplinary and transdisciplinary explanations, methods to connect science to applications, and ways to advance research technologies by creating NCEAS, the first synthesis center.\nThere are multiple other synthesis centers that have been established since, but each one has a foundational goal to use synthesis to “advance basic science, organize ecological information for decision makers concerned with pressing national issues, and make cost-effective use of the nation’s extant and accumulating database” (Hampton and Parker 2011).\nSynthesis centers are specifically designed to catalyze collaboration leading to breakthrough ideas, and one way NCEAS (among other synthesis centers) achieves this is through working groups. Since its inception, NCEAS has hosted hundreds of working groups and has supported them in varying ways including: structuring group size or composition, facilitating of working sessions, supplying computing and informatics support, offering training opportunities for data-focused team members, providing a neutral space for meetings and co-working, and more. In short, NCEAS lowers the “activation energy” for working group members so that they can focus on the cross-pollination of ideas, creative thinking, and emergent research (Rodrigo et al. 2013).", + "crumbs": [ + "Week 1", + "1  Successful Synthesis Science" + ] }, { "objectID": "session_01.html#working-groups-at-nceas", "href": "session_01.html#working-groups-at-nceas", "title": "1  Successful Synthesis Science", "section": "1.4 Working Groups at NCEAS", - "text": "1.4 Working Groups at NCEAS\n\n1.4.1 Ocean Health Index (OHI)\n\n\n\n\n\nThe Ocean Health Index brought together a diverse group of experts including marine scientists, economists, policy experts, and more. This collaborative effort aimed to comprehensively assess the health of oceans worldwide by integrating data from various sources, including physical, biological, and socioeconomic factors.\nThe success of the Ocean Health Index highlights several key aspects of effective synthesis science in working groups:\n\nInterdisciplinary Collaboration: The working group included experts from different disciplines, fostering a holistic understanding of ocean health that goes beyond individual scientific perspectives.\nData Integration: The Index integrated data from multiple sources and scales, ranging from local to global, to provide a comprehensive view of ocean health.\nStandardized Metrics: The working group developed standardized metrics that allowed for consistent assessment and comparison of ocean health across regions and over time.\nPolicy Relevance: The synthesis findings were designed to inform policy and management decisions, demonstrating the practical applications of synthesis science in addressing real-world challenges.\nCommunication and Outreach: The Index effectively communicated its findings to a wide range of stakeholders, raising awareness about ocean health and fostering engagement in conservation efforts.\n\n\n\n1.4.2 State of Alaska’s Salmon and People (SASAP)\n\n\n\n\n\nThe SASAP project was a partnership between NCEAS and Anchorage-based Nautilus Impact Investing to create an equitable decision-making platform for salmon management through information synthesis, collaboration, and stakeholder engagement.\nThe project sought to address the need for accessible, up-to-date, and complete information about salmon and the factors shaping their future. It convened eight collaborative working groups consisting of leading experts at the University of Alaska and other universities, local indigenous leaders, and specialists across resource sectors – an intentional integration of western scientific perspectives and indigenous knowledge." + "text": "1.4 Working Groups at NCEAS\n\n1.4.1 Ocean Health Index (OHI)\n\n\n\n\n\nThe Ocean Health Index brought together a diverse group of experts including marine scientists, economists, policy experts, and more. This collaborative effort aimed to comprehensively assess the health of oceans worldwide by integrating data from various sources, including physical, biological, and socioeconomic factors.\nThe success of the Ocean Health Index highlights several key aspects of effective synthesis science in working groups:\n\nInterdisciplinary Collaboration: The working group included experts from different disciplines, fostering a holistic understanding of ocean health that goes beyond individual scientific perspectives.\nData Integration: The Index integrated data from multiple sources and scales, ranging from local to global, to provide a comprehensive view of ocean health.\nStandardized Metrics: The working group developed standardized metrics that allowed for consistent assessment and comparison of ocean health across regions and over time.\nPolicy Relevance: The synthesis findings were designed to inform policy and management decisions, demonstrating the practical applications of synthesis science in addressing real-world challenges.\nCommunication and Outreach: The Index effectively communicated its findings to a wide range of stakeholders, raising awareness about ocean health and fostering engagement in conservation efforts.\n\n\n\n1.4.2 State of Alaska’s Salmon and People (SASAP)\n\n\n\n\n\nThe SASAP project was a partnership between NCEAS and Anchorage-based Nautilus Impact Investing to create an equitable decision-making platform for salmon management through information synthesis, collaboration, and stakeholder engagement.\nThe project sought to address the need for accessible, up-to-date, and complete information about salmon and the factors shaping their future. It convened eight collaborative working groups consisting of leading experts at the University of Alaska and other universities, local indigenous leaders, and specialists across resource sectors – an intentional integration of western scientific perspectives and indigenous knowledge.", + "crumbs": [ + "Week 1", + "1  Successful Synthesis Science" + ] }, { "objectID": "session_01.html#priorities-of-synthesis-here-now-and-beyond", "href": "session_01.html#priorities-of-synthesis-here-now-and-beyond", "title": "1  Successful Synthesis Science", "section": "1.5 Priorities of Synthesis Here, Now, and Beyond", - "text": "1.5 Priorities of Synthesis Here, Now, and Beyond\nIn February 2021, NCEAS hosted a virtual workshop where 127 ecologists, environmental and natural scientists convened to discuss the future priorities of synthesis science. Participants across career stages, institutions, backgrounds, and geographies were in attendance and together they identified seven research topics, and two pressing needs for conducting research synthesis practices.\nLater in January 2023, dozens of scientists authored and published Priorities for synthesis research in ecology and environmental science the results of the workshop. We’ve summarized these results in the tables below.\n\n\n\n\n\n\n\nResearch Topic\nDescription\n\n\n\n\nDiversity, Equity, Inclusion, and Justice (DEIJ)\nEnvironmental justice shows the link between nature and fairness for people, especially those who are disadvantaged. Unequal distribution of nature due to factors like racism impacts cities and ecosystems. Integrating DEIJ into research can improve knowledge and involve underrepresented groups, while engaging diverse communities can make research more impactful and inclusive.\n\n\nHuman and Natural systems\nEnvironmental synthesis has given us valuable insights into environmental change, but it needs to also look at how human actions and decisions affect the environment. For example, decisions about things like population growth and greenhouse gas policies impact species and nature. Bringing together information from different fields is challenging, especially when considering different scales and practices. Synthesis science can help us better understand how humans and nature are connected, but it takes time and effort to combine ideas from different disciplines.\n\n\nActionable and Use-inspired science\nSynthesis science in ecology and environmental science is great for helping decision makers. Methods like systematic reviews and predictive models can simplify research for environmental policy. To be more effective, scientists need to work closely with practitioners and use different types of knowledge. Communication, teamwork, and using various knowledge sources can improve how decisions are made and carried out based on scientific findings.\n\n\nScale\nUnderstanding ecosystems across different sizes and time periods is hard for social-ecological research. Synthesis helps by combining information and methods from different scales, and connecting these findings to policy decisions. The challenges come from not having enough long-term data, difficulty mixing different information for analysis, and lack of skills and cooperation across scales. To overcome these challenges, more efforts are needed to collect, organize, and combine data over long periods and big areas.\n\n\nGenerality\nScience looks for common rules to explain how things work, but sometimes it’s hard to find them. Synthesis science can help find these general rules and figure out when they apply. Two problems are not having enough similar studies to compare and bias in what gets studied and reported. To fix this, scientists can share their work openly, use the same rules for reporting, and make sure all types of results are published. Working together across different areas can also help find these general rules.\n\n\nComplexity and Resilience\nEcosystems are very complicated, especially when considering things like society and economics. This complexity can make systems strong or weak. Using this complex view helps solve problems like water and food. But putting all this information together (synthesis) is hard because it depends on the situation, and finding general rules is tough. To make it work better, more scientists need to learn to work together across different areas and share their data. The goal is to understand how complexity affects ecosystems and find ways to help both people and the environment.\n\n\nPredictability\nThis time of big changes in the environment makes it important to predict how ecosystems will be in the future and how they’ll affect people. Predicting things in the short term (like months or years) is common in some fields but not in ecology. Some people worry that the predictions might not be perfect, but even imperfect predictions can help us learn and make better decisions. To make predictions better in ecology, scientists can work together, use standardized methods and data, and talk to the people who use the predictions. This will help us manage natural resources more wisely.\n\n\n\n\n\n\n\n\n\n\nPressing Need\nDescription\n\n\n\n\nNeed for increased participant diversity and inclusive research practices\nSynthesis science is most effective when it combines data, perspectives, and insights from different regions and ecosystems. By including diverse participants and creating inclusive research environments, we can better address important questions and find fair solutions to challenges. Ignoring diversity and inclusion can lead to biased syntheses and unfair outcomes. The large scope of synthesis science calls for involving people, ideas, and data from various backgrounds and languages. Efforts should be made to ensure representation, provide support, and promote open dialogue to increase diversity and inclusivity in synthesis research, ultimately fostering better understanding and more equitable outcomes.\n\n\nIncreased and improved data flow, access, and skill-building\nThe amount of data for synthesis science is increasing, and there are efforts to organize and combine data from various sources to answer ecological questions. Funding is needed to manage and store data properly. It’s important to think about ethical issues when using different datasets, especially if some people can’t share their data openly. Some data may be hard to access due to language or quality issues, and including diverse types of data, like traditional knowledge, can be challenging. Tools like machine learning can help make sense of different data sources. To improve data synthesis, global collaboration among diverse groups is essential.\n\n\n\n\n\n\n\nCarpenter, Stephen R., E. Virginia Armbrust, Peter W. Arzberger, F. Stuart Chapin, James J. Elser, Edward J. Hackett, Anthony R. Ives, et al. 2009. “Accelerate Synthesis in Ecology and Environmental Sciences.” BioScience 59 (8): 699–701. https://doi.org/10.1525/bio.2009.59.8.11.\n\n\nDicks, Lynn V., Jessica C. Walsh, and William J. Sutherland. 2014. “Organising Evidence for Environmental Management Decisions: A ‘4S’ Hierarchy.” Trends in Ecology & Evolution 29 (11): 607–13. https://doi.org/10.1016/j.tree.2014.09.004.\n\n\nHalpern, Benjamin S., Carl Boettiger, Michael C. Dietze, Jessica A. Gephart, Patrick Gonzalez, Nancy B. Grimm, Peter M. Groffman, et al. 2023. “Priorities for Synthesis Research in Ecology and Environmental Science.” Ecosphere 14 (1). https://doi.org/10.1002/ecs2.4342.\n\n\nHampton, Stephanie E., and John N. Parker. 2011. “Collaboration and Productivity in Scientific Synthesis.” BioScience 61 (11): 900–910. https://doi.org/10.1525/bio.2011.61.11.9.\n\n\nRodrigo, Allen, Susan Alberts, Karen Cranston, Joel Kingsolver, Hilmar Lapp, Craig McClain, Robin Smith, Todd Vision, Jory Weintraub, and Brian Wiegmann. 2013. “Science Incubators: Synthesis Centers and Their Role in the Research Ecosystem.” PLoS Biology 11 (1): e1001468. https://doi.org/10.1371/journal.pbio.1001468.\n\n\nWyborn, Carina, Elena Louder, Jerry Harrison, Jensen Montambault, Jasper Montana, Melanie Ryan, Angela Bednarek, et al. 2018. “Understanding the Impacts of Research Synthesis.” Environmental Science & Policy 86 (August): 72–84. https://doi.org/10.1016/j.envsci.2018.04.013." + "text": "1.5 Priorities of Synthesis Here, Now, and Beyond\nIn February 2021, NCEAS hosted a virtual workshop where 127 ecologists, environmental and natural scientists convened to discuss the future priorities of synthesis science. Participants across career stages, institutions, backgrounds, and geographies were in attendance and together they identified seven research topics, and two pressing needs for conducting research synthesis practices.\nLater in January 2023, dozens of scientists authored and published Priorities for synthesis research in ecology and environmental science the results of the workshop. We’ve summarized these results in the tables below.\n\n\n\n\n\n\n\nResearch Topic\nDescription\n\n\n\n\nDiversity, Equity, Inclusion, and Justice (DEIJ)\nEnvironmental justice shows the link between nature and fairness for people, especially those who are disadvantaged. Unequal distribution of nature due to factors like racism impacts cities and ecosystems. Integrating DEIJ into research can improve knowledge and involve underrepresented groups, while engaging diverse communities can make research more impactful and inclusive.\n\n\nHuman and Natural systems\nEnvironmental synthesis has given us valuable insights into environmental change, but it needs to also look at how human actions and decisions affect the environment. For example, decisions about things like population growth and greenhouse gas policies impact species and nature. Bringing together information from different fields is challenging, especially when considering different scales and practices. Synthesis science can help us better understand how humans and nature are connected, but it takes time and effort to combine ideas from different disciplines.\n\n\nActionable and Use-inspired science\nSynthesis science in ecology and environmental science is great for helping decision makers. Methods like systematic reviews and predictive models can simplify research for environmental policy. To be more effective, scientists need to work closely with practitioners and use different types of knowledge. Communication, teamwork, and using various knowledge sources can improve how decisions are made and carried out based on scientific findings.\n\n\nScale\nUnderstanding ecosystems across different sizes and time periods is hard for social-ecological research. Synthesis helps by combining information and methods from different scales, and connecting these findings to policy decisions. The challenges come from not having enough long-term data, difficulty mixing different information for analysis, and lack of skills and cooperation across scales. To overcome these challenges, more efforts are needed to collect, organize, and combine data over long periods and big areas.\n\n\nGenerality\nScience looks for common rules to explain how things work, but sometimes it’s hard to find them. Synthesis science can help find these general rules and figure out when they apply. Two problems are not having enough similar studies to compare and bias in what gets studied and reported. To fix this, scientists can share their work openly, use the same rules for reporting, and make sure all types of results are published. Working together across different areas can also help find these general rules.\n\n\nComplexity and Resilience\nEcosystems are very complicated, especially when considering things like society and economics. This complexity can make systems strong or weak. Using this complex view helps solve problems like water and food. But putting all this information together (synthesis) is hard because it depends on the situation, and finding general rules is tough. To make it work better, more scientists need to learn to work together across different areas and share their data. The goal is to understand how complexity affects ecosystems and find ways to help both people and the environment.\n\n\nPredictability\nThis time of big changes in the environment makes it important to predict how ecosystems will be in the future and how they’ll affect people. Predicting things in the short term (like months or years) is common in some fields but not in ecology. Some people worry that the predictions might not be perfect, but even imperfect predictions can help us learn and make better decisions. To make predictions better in ecology, scientists can work together, use standardized methods and data, and talk to the people who use the predictions. This will help us manage natural resources more wisely.\n\n\n\n\n\n\n\n\n\n\nPressing Need\nDescription\n\n\n\n\nNeed for increased participant diversity and inclusive research practices\nSynthesis science is most effective when it combines data, perspectives, and insights from different regions and ecosystems. By including diverse participants and creating inclusive research environments, we can better address important questions and find fair solutions to challenges. Ignoring diversity and inclusion can lead to biased syntheses and unfair outcomes. The large scope of synthesis science calls for involving people, ideas, and data from various backgrounds and languages. Efforts should be made to ensure representation, provide support, and promote open dialogue to increase diversity and inclusivity in synthesis research, ultimately fostering better understanding and more equitable outcomes.\n\n\nIncreased and improved data flow, access, and skill-building\nThe amount of data for synthesis science is increasing, and there are efforts to organize and combine data from various sources to answer ecological questions. Funding is needed to manage and store data properly. It’s important to think about ethical issues when using different datasets, especially if some people can’t share their data openly. Some data may be hard to access due to language or quality issues, and including diverse types of data, like traditional knowledge, can be challenging. Tools like machine learning can help make sense of different data sources. To improve data synthesis, global collaboration among diverse groups is essential.\n\n\n\n\n\n\n\nCarpenter, Stephen R., E. Virginia Armbrust, Peter W. Arzberger, F. Stuart Chapin, James J. Elser, Edward J. Hackett, Anthony R. Ives, et al. 2009. “Accelerate Synthesis in Ecology and Environmental Sciences.” BioScience 59 (8): 699–701. https://doi.org/10.1525/bio.2009.59.8.11.\n\n\nDicks, Lynn V., Jessica C. Walsh, and William J. Sutherland. 2014. “Organising Evidence for Environmental Management Decisions: A ‘4S’ Hierarchy.” Trends in Ecology & Evolution 29 (11): 607–13. https://doi.org/10.1016/j.tree.2014.09.004.\n\n\nHalpern, Benjamin S., Carl Boettiger, Michael C. Dietze, Jessica A. Gephart, Patrick Gonzalez, Nancy B. Grimm, Peter M. Groffman, et al. 2023. “Priorities for Synthesis Research in Ecology and Environmental Science.” Ecosphere 14 (1). https://doi.org/10.1002/ecs2.4342.\n\n\nHampton, Stephanie E., and John N. Parker. 2011. “Collaboration and Productivity in Scientific Synthesis.” BioScience 61 (11): 900–910. https://doi.org/10.1525/bio.2011.61.11.9.\n\n\nRodrigo, Allen, Susan Alberts, Karen Cranston, Joel Kingsolver, Hilmar Lapp, Craig McClain, Robin Smith, Todd Vision, Jory Weintraub, and Brian Wiegmann. 2013. “Science Incubators: Synthesis Centers and Their Role in the Research Ecosystem.” PLoS Biology 11 (1): e1001468. https://doi.org/10.1371/journal.pbio.1001468.\n\n\nWyborn, Carina, Elena Louder, Jerry Harrison, Jensen Montambault, Jasper Montana, Melanie Ryan, Angela Bednarek, et al. 2018. “Understanding the Impacts of Research Synthesis.” Environmental Science & Policy 86 (August): 72–84. https://doi.org/10.1016/j.envsci.2018.04.013.", + "crumbs": [ + "Week 1", + "1  Successful Synthesis Science" + ] + }, + { + "objectID": "session_02.html", + "href": "session_02.html", + "title": "2  Logic Model", + "section": "", + "text": "Learning Objectives", + "crumbs": [ + "Week 1", + "2  Logic Model" + ] }, { "objectID": "session_02.html#learning-objectives", "href": "session_02.html#learning-objectives", "title": "2  Logic Model", - "section": "Learning Objectives", - "text": "Learning Objectives\n\nBecome familiar with Logic Models\nApply the principles of Logic Models to synthesis development\nRefine synthesis group research question" + "section": "", + "text": "Become familiar with Logic Models\nApply the principles of Logic Models to synthesis development\nRefine synthesis group research question", + "crumbs": [ + "Week 1", + "2  Logic Model" + ] }, { "objectID": "session_02.html#logic-models", "href": "session_02.html#logic-models", "title": "2  Logic Model", "section": "2.1 Logic Models", - "text": "2.1 Logic Models\nLogic models are a planning tool that is designed to support program development by depicting the flow of resources and processes leading to a desired result. They are also used for outcomes-based evaluation of a program and are often requested as part of an evaluation planning process by funders or stakeholders.\nA simplified logic models comprise three main parts: Inputs, Outputs and Outcomes.\n\nInputs reflect what is invested, outputs are what is done and outcomes are the results of the program.\nIn a more detailed logic model, outputs and outcomes are further broken down. Outputs are often represented as ‘Activities’ and ‘Participants’. By including participation (or participants), the logic model is explicitly considering the intended audience, or stakeholders, impacted by the program. Engagement of this audience is an output. In the case of outcomes, these can be split into short, medium and long-term outcomes. Sometimes this last category may be labeled ‘Impact’\n\nDefining the inputs, outputs and outcomes early in a planning process enables teams to visualize the workflow from activity to results and can help mitigate potential challenges. Logic models can be thought of as having an ‘if this then that’ structure where inputs -> outputs -> outcomes.\n\nIn the example below we have constructed a simple logic model for a hypothetical project where training materials are being developed for a group of educators to implement at their respective institutions.\n\nLinkages are not always sequential and can be within categories, bi-directional and/or include feedback loops. Detailing this complexity of relationships, or theory of action, can be time-consuming but is a valuable part of the thought process for project planning. In exploring all relationships, logic modeling also allows for assessing program feasibility.\n\nThe above graphics include two sections within Outputs - Activities and Participants - and this is quite common. There is variation in logic model templates, including versions with a third type of output - “Products’. Sometimes description of these products is contained within the Activities section - for example, ‘develop curricula’, ‘produce a report’ - however calling these out explicitly is beneficial for teams focused on product development.\nProgram development (and logic modeling) occurs in response to a given ‘Situation’ or need, and exploring this is the first step in modeling. The situation defines the objective, or problem, that the program is designed to solve hence some logic models may omit the left-hand situation column but be framed with Problem and Solution statements. Finally, comprehensive logic modeling takes into consideration assumptions that are made with respect to the resources available, the people involved, or the way the program will work and also recognizes that there are external factors that can impact the program’s success.\n\nIn summary:\nLogic models support program development and evaluation and comprise three primary steps in the workflow:\n\nInputs: Resources, contributions, and investments required for a program;\nOutputs: Activities conducted, participants reached, and products produced; and\nOutcomes: Results or expected changes arising from the program structured as short-, medium- and long-term." + "text": "2.1 Logic Models\nLogic models are a planning tool that is designed to support program development by depicting the flow of resources and processes leading to a desired result. They are also used for outcomes-based evaluation of a program and are often requested as part of an evaluation planning process by funders or stakeholders.\nA simplified logic models comprise three main parts: Inputs, Outputs and Outcomes.\n\nInputs reflect what is invested, outputs are what is done and outcomes are the results of the program.\nIn a more detailed logic model, outputs and outcomes are further broken down. Outputs are often represented as ‘Activities’ and ‘Participants’. By including participation (or participants), the logic model is explicitly considering the intended audience, or stakeholders, impacted by the program. Engagement of this audience is an output. In the case of outcomes, these can be split into short, medium and long-term outcomes. Sometimes this last category may be labeled ‘Impact’\n\nDefining the inputs, outputs and outcomes early in a planning process enables teams to visualize the workflow from activity to results and can help mitigate potential challenges. Logic models can be thought of as having an ‘if this then that’ structure where inputs -> outputs -> outcomes.\n\nIn the example below we have constructed a simple logic model for a hypothetical project where training materials are being developed for a group of educators to implement at their respective institutions.\n\nLinkages are not always sequential and can be within categories, bi-directional and/or include feedback loops. Detailing this complexity of relationships, or theory of action, can be time-consuming but is a valuable part of the thought process for project planning. In exploring all relationships, logic modeling also allows for assessing program feasibility.\n\nThe above graphics include two sections within Outputs - Activities and Participants - and this is quite common. There is variation in logic model templates, including versions with a third type of output - “Products’. Sometimes description of these products is contained within the Activities section - for example, ‘develop curricula’, ‘produce a report’ - however calling these out explicitly is beneficial for teams focused on product development.\nProgram development (and logic modeling) occurs in response to a given ‘Situation’ or need, and exploring this is the first step in modeling. The situation defines the objective, or problem, that the program is designed to solve hence some logic models may omit the left-hand situation column but be framed with Problem and Solution statements. Finally, comprehensive logic modeling takes into consideration assumptions that are made with respect to the resources available, the people involved, or the way the program will work and also recognizes that there are external factors that can impact the program’s success.\n\nIn summary:\nLogic models support program development and evaluation and comprise three primary steps in the workflow:\n\nInputs: Resources, contributions, and investments required for a program;\nOutputs: Activities conducted, participants reached, and products produced; and\nOutcomes: Results or expected changes arising from the program structured as short-, medium- and long-term.", + "crumbs": [ + "Week 1", + "2  Logic Model" + ] }, { "objectID": "session_02.html#logic-models-for-synthesis-research", "href": "session_02.html#logic-models-for-synthesis-research", "title": "2  Logic Model", "section": "2.2 Logic Models for Synthesis Research", - "text": "2.2 Logic Models for Synthesis Research\nLogic models are one tool for program development and have sufficient flexibility for a variety of situations, including planning for synthesis research. While some logic model categories may feel less relevant, the process of articulating a research objective, associated resources and activities and proposed outcome(s) has value.\nBelow is a table of logic model elements and example questions for each element framed for both a typical logic model and synthesis research.\n\n\n\n\n\n\n\n\nLogic Model Element\nLogic Model Framing\nSynthesis Research Framing\n\n\n\n\nProblem Statement\nWhat is the problem? Why is this a problem? Who does this impact?\nWhat is the current state of knowledge? What gaps exists in understanding? Why is more information / synthesis important?\n\n\nInputs\nWhat resources are needed for the program (e.g. personnel, money, time, equipment, partnerships, etc.)?\nWhat is needed to undertake the synthesis research? For personnel, think in terms of the roles that are needed (e.g. data manager, statistician, writer, editor etc.) Consider the time frame. Condsider what data are needed and what already exists?\n\n\nOutputs - Activities\nWhat will be done (e.g. development, design, workshops, conferences, counseling, outreach, etc.)?\nWhat activities are needed to conduct the research?\nThis could be high level or it could be broken down into details such as the types of statistical approaches.\n\n\nOutputs - Participants\nWho will we reach (e.g. clients, participants, customers, etc.)?\nWho is the target audience? Who will be impacted by this work? Who is positioned to leverage this work?\n\n\nOutputs - Products\nWhat will you create (e.g. publications, websites, media communications, etc.)?\nWhat research products are planned or expected? Consider this in relation to the intended audience. Is a peer-reviewed publication, report or white paper most appropriate? How will derived data be handled? Will documentation, workflows, or code be published?\n\n\nOutcomes - Short-term\nWhat short-term outcomes are anticipated among participants?\nThese might include changes in awareness, knowledge, skills, attitudes, opinions or intent.\nWill this work represent a significant contribution to current understanding?\n\n\nOutcomes - Medium-term\nWhat medium-term outcomes are predicted among participants?\nThese might include changes in behaviors, decision-making and actions.\nWill this work promote increased research activity or open new avenues of inquiry?\n\n\nOutcomes - Long-term\nWhat long-term benefits, or impacts, are expected?\nThis might include changes in social, economic, civic, or environmental conditions.\nWill this work result in local, regional or national policy change? What will be the long-term impact of increased investment in the ecosystem?" + "text": "2.2 Logic Models for Synthesis Research\nLogic models are one tool for program development and have sufficient flexibility for a variety of situations, including planning for synthesis research. While some logic model categories may feel less relevant, the process of articulating a research objective, associated resources and activities and proposed outcome(s) has value.\nBelow is a table of logic model elements and example questions for each element framed for both a typical logic model and synthesis research.\n\n\n\n\n\n\n\n\nLogic Model Element\nLogic Model Framing\nSynthesis Research Framing\n\n\n\n\nProblem Statement\nWhat is the problem? Why is this a problem? Who does this impact?\nWhat is the current state of knowledge? What gaps exists in understanding? Why is more information / synthesis important?\n\n\nInputs\nWhat resources are needed for the program (e.g. personnel, money, time, equipment, partnerships, etc.)?\nWhat is needed to undertake the synthesis research? For personnel, think in terms of the roles that are needed (e.g. data manager, statistician, writer, editor etc.) Consider the time frame. Condsider what data are needed and what already exists?\n\n\nOutputs - Activities\nWhat will be done (e.g. development, design, workshops, conferences, counseling, outreach, etc.)?\nWhat activities are needed to conduct the research?\nThis could be high level or it could be broken down into details such as the types of statistical approaches.\n\n\nOutputs - Participants\nWho will we reach (e.g. clients, participants, customers, etc.)?\nWho is the target audience? Who will be impacted by this work? Who is positioned to leverage this work?\n\n\nOutputs - Products\nWhat will you create (e.g. publications, websites, media communications, etc.)?\nWhat research products are planned or expected? Consider this in relation to the intended audience. Is a peer-reviewed publication, report or white paper most appropriate? How will derived data be handled? Will documentation, workflows, or code be published?\n\n\nOutcomes - Short-term\nWhat short-term outcomes are anticipated among participants?\nThese might include changes in awareness, knowledge, skills, attitudes, opinions or intent.\nWill this work represent a significant contribution to current understanding?\n\n\nOutcomes - Medium-term\nWhat medium-term outcomes are predicted among participants?\nThese might include changes in behaviors, decision-making and actions.\nWill this work promote increased research activity or open new avenues of inquiry?\n\n\nOutcomes - Long-term\nWhat long-term benefits, or impacts, are expected?\nThis might include changes in social, economic, civic, or environmental conditions.\nWill this work result in local, regional or national policy change? What will be the long-term impact of increased investment in the ecosystem?", + "crumbs": [ + "Week 1", + "2  Logic Model" + ] }, { "objectID": "session_02.html#activity-synthesis-planning-with-logic-models", "href": "session_02.html#activity-synthesis-planning-with-logic-models", "title": "2  Logic Model", "section": "2.3 Activity: Synthesis Planning with Logic Models", - "text": "2.3 Activity: Synthesis Planning with Logic Models\n\n\n\n\n\n\nSetup\n\n\n\nBreakout into your research synthesis groups to refine your ideas for potential synthesis topics. Use either the Logic Model Template or a Mermaid Flowchart to create your logic model.\nThe goal for this activity is to develop one or more high-level logic models that:\n\nSummarize the synthesis research question\nDefine the inputs needed to approach the synthesis research question\nDefine the outputs including the activities, participants, and products needed to address the research question\nDefine at least the short-term outcomes and long-term outcomes of the research\n\nOften it is helpful to start by working backwards. Consider what outcomes are you trying to achieve, what outputs would help you get to those outcomes, and finally what inputs do you need to create those outputs.\n\n\n\nLogic Model Template\nUse our Logic Model Template to create your Logic Model. When you access the link, you must create your own copy to start editing.\n\n\n\nLogic Model Template\n\n\n\n\nMermaid Flowchart\nUse a Mermaid Flowchart to create your Logic Model. These is a tool that is embedded in Quarto documents.\n\n\n\n\nflowchart LR\n INPUTS --> ACTIVITIES --> OUTPUTS --> OUTCOMES/IMPACTS\n\n Scenario{{Accelerate synthesis via data science training}}\n\n R1[Instructor] & R2[Classroom space] & R3[Projector] --> B{Data Science Workshop}\n B --> C(Workshop Curriculum)\n B --> D(Presentations and Practice)\n \n C & D --> E[/Improved Delta management/] & F[/Increased analytic efficiency/]\n\n\n\n\n\nSource Code for Mermaid Flowhart Example (above):\n\n```{mermaid}\n\nflowchart LR\n INPUTS --> ACTIVITIES --> OUTPUTS --> OUTCOMES/IMPACTS\n\n Scenario{{Accelerate synthesis via data science training}}\n\n R1[Instructor] & R2[Classroom space] & R3[Projector] --> B{Data Science Workshop}\n B --> C(Workshop Curriculum)\n B --> D(Presentations and Practice)\n \n C & D --> E[/Improved Delta management/] & F[/Increased analytic efficiency/]\n```" + "text": "2.3 Activity: Synthesis Planning with Logic Models\n\n\n\n\n\n\nSetup\n\n\n\nBreakout into your research synthesis groups to refine your ideas for potential synthesis topics. Use either the Logic Model Template or a Mermaid Flowchart to create your logic model.\nThe goal for this activity is to develop one or more high-level logic models that:\n\nSummarize the synthesis research question\nDefine the inputs needed to approach the synthesis research question\nDefine the outputs including the activities, participants, and products needed to address the research question\nDefine at least the short-term outcomes and long-term outcomes of the research\n\nOften it is helpful to start by working backwards. Consider what outcomes are you trying to achieve, what outputs would help you get to those outcomes, and finally what inputs do you need to create those outputs.\n\n\n\nLogic Model Template\nUse our Logic Model Template to create your Logic Model. When you access the link, you must create your own copy to start editing.\n\n\n\nLogic Model Template\n\n\n\n\nMermaid Flowchart\nUse a Mermaid Flowchart to create your Logic Model. These is a tool that is embedded in Quarto documents.\n\n\n\n\n\nflowchart LR\n INPUTS --> ACTIVITIES --> OUTPUTS --> OUTCOMES/IMPACTS\n\n Scenario{{Accelerate synthesis via data science training}}\n\n R1[Instructor] & R2[Classroom space] & R3[Projector] --> B{Data Science Workshop}\n B --> C(Workshop Curriculum)\n B --> D(Presentations and Practice)\n \n C & D --> E[/Improved Delta management/] & F[/Increased analytic efficiency/]\n\n\n\n\n\n\nSource Code for Mermaid Flowhart Example (above):\n\n```{mermaid}\n\nflowchart LR\n INPUTS --> ACTIVITIES --> OUTPUTS --> OUTCOMES/IMPACTS\n\n Scenario{{Accelerate synthesis via data science training}}\n\n R1[Instructor] & R2[Classroom space] & R3[Projector] --> B{Data Science Workshop}\n B --> C(Workshop Curriculum)\n B --> D(Presentations and Practice)\n \n C & D --> E[/Improved Delta management/] & F[/Increased analytic efficiency/]\n```", + "crumbs": [ + "Week 1", + "2  Logic Model" + ] + }, + { + "objectID": "session_03.html", + "href": "session_03.html", + "title": "3  Data Management Essentials", + "section": "", + "text": "Learning Objectives", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#learning-objectives", "href": "session_03.html#learning-objectives", "title": "3  Data Management Essentials", - "section": "Learning Objectives", - "text": "Learning Objectives\n\nUnderstand the importance of data management for successfully preserving data\nReview the Data Life Cycle and how it can guide the data management in a project\nFamiliarize with data management plans and start thinking about one for your project\nLearn about metadata guidelines and best practices for reproducibility\nBecome familiar with environmental data repositories for accessing and publishing data" + "section": "", + "text": "Understand the importance of data management for successfully preserving data\nReview the Data Life Cycle and how it can guide the data management in a project\nFamiliarize with data management plans and start thinking about one for your project\nLearn about metadata guidelines and best practices for reproducibility\nBecome familiar with environmental data repositories for accessing and publishing data", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#the-big-idea", "href": "session_03.html#the-big-idea", "title": "3  Data Management Essentials", "section": "3.1 The Big Idea", - "text": "3.1 The Big Idea\nThis lesson aims to get you thinking about how are you going to manage your data. Even though you are in the early stages of defining you research project, we believe that when it comes to data management, the earlier you start thinking about it the better." + "text": "3.1 The Big Idea\nThis lesson aims to get you thinking about how are you going to manage your data. Even though you are in the early stages of defining you research project, we believe that when it comes to data management, the earlier you start thinking about it the better.", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#introduction", "href": "session_03.html#introduction", "title": "3  Data Management Essentials", "section": "3.2 Introduction", - "text": "3.2 Introduction\nData management is the process of handling, organizing, documenting, and preserving data used in a research project. This is particularly important in synthesis science given the nature of synthesis, which involves combining data and information from multiple sources to answer broader questions, generate knowledge and provide insights into a particular problem or phenomenon.\n\n3.2.1 Benefits of managing your data\nSuccessfully managing your data throughout a research project helps ensures its preservation for future use. It also facilitates collaboration within your team, and it helps advance your scientific outcomes.\nFrom a researcher perspective\n\nKeep yourself organized – be able to find your files (data inputs, analytic scripts, outputs at various stages of the analytic process, etc.)\nTrack your science processes for reproducibility – be able to match up your outputs with exact inputs and transformations that produced them\nBetter control versions of data – easily identify versions that can be periodically purged\nQuality control your data more efficiently\nTo avoid data loss (e.g. making backups)\nFormat your data for re-use (by yourself or others)\nBe prepared to document your data for your own recollection, accountability, and re-use (by yourself or others)\nGain credibility and recognition for your science efforts through data sharing!\n\nAdvancement of science\n\nData is a valuable asset – it is expensive and time consuming to collect\nMaximize the effective use and value of data and information assets\nContinually improve the quality including: data accuracy, integrity, integration, timeliness of data capture and presentation, relevance, and usefulness\nEnsure appropriate use of data and information\nFacilitate data sharing\nEnsure sustainability and accessibility in long term for re-use in science" + "text": "3.2 Introduction\nData management is the process of handling, organizing, documenting, and preserving data used in a research project. This is particularly important in synthesis science given the nature of synthesis, which involves combining data and information from multiple sources to answer broader questions, generate knowledge and provide insights into a particular problem or phenomenon.\n\n3.2.1 Benefits of managing your data\nSuccessfully managing your data throughout a research project helps ensures its preservation for future use. It also facilitates collaboration within your team, and it helps advance your scientific outcomes.\nFrom a researcher perspective\n\nKeep yourself organized – be able to find your files (data inputs, analytic scripts, outputs at various stages of the analytic process, etc.)\nTrack your science processes for reproducibility – be able to match up your outputs with exact inputs and transformations that produced them\nBetter control versions of data – easily identify versions that can be periodically purged\nQuality control your data more efficiently\nTo avoid data loss (e.g. making backups)\nFormat your data for re-use (by yourself or others)\nBe prepared to document your data for your own recollection, accountability, and re-use (by yourself or others)\nGain credibility and recognition for your science efforts through data sharing!\n\nAdvancement of science\n\nData is a valuable asset – it is expensive and time consuming to collect\nMaximize the effective use and value of data and information assets\nContinually improve the quality including: data accuracy, integrity, integration, timeliness of data capture and presentation, relevance, and usefulness\nEnsure appropriate use of data and information\nFacilitate data sharing\nEnsure sustainability and accessibility in long term for re-use in science", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#the-data-life-cycle", "href": "session_03.html#the-data-life-cycle", "title": "3  Data Management Essentials", "section": "3.3 The Data Life Cycle", - "text": "3.3 The Data Life Cycle\nThe Data Life Cycle gives you an overview of meaningful steps data goes through in a research project, from planning to archival. This step-by-step breakdown facilitates overseeing individual actions, operations and processes required at each stage. This is a visual tool that aims o help scientists plan and anticipate what will be the “data needs” for a specific project (Faundeen et al 2013) .\n\n\n\nSource: Adapted from Faundeen et al 2013, USGS & DataONE\n\n\n\n3.3.1 Primary Elements\n\n\n\n\n\n\n\n\nStep\nDescription\nTool\n\n\n\n\nPlan\nMap out the processes and resources for all activities related to the handling of the project’s data assets. Start with the project goals (desired outputs, outcomes, and impacts) and work backwards to build a data management plan, supporting data policies, and sustainability plans for each step.\nData Management Plan (DPM)\n\n\nAcquire & Discover\nActivities needed to collect new or existing data. You can structure the process of collecting data upfront to better implement data management. Consider data policies and best practices that maintain the provenance and integrity of the data.\nIdentifying data sources and mechanisms to access data\n\n\nProcess\nEvery step needed to prepare new or existing data to be able to use it as an input for synthesis. Consider the structure of the data, unit transformation, extrapolations, etc\nCleaning & Wrangling data skills\n\n\nIntegrate\nData from multiple sources are combined into a form that can be readily analyzed. Successful data integration depends on documentation of the integration process, clearly citing and making accessible the data you are using, and employing good data management practices throughout the Data Life Cycle.\nModeling & Interpretation\n\n\nAnalyze\nCreate analyses and visualizations to identify patterns, test hypotheses, and illustrate findings. During this process, record your methods, document data processing steps, and ensure your data are reproducible. Learn about these best practices and more.\nModeling, Interpretation & Statistics\n\n\nPreserve\nPlan on how you are going to store your data for long-term use and accessibility so others can access, interpret, and use the data in the future. Decide what data to preserve, where to preserve it, and what documentation needs to accompany the data.\nData packages & repositories\n\n\nPublish and Share\nPublication and distribution of your data through the web or in data catalogs, social media or other venues to increase the chances of your data being discovered. Data is a research product as publications are.\nDOIs and citations\n\n\n\n\n\n3.3.2 Cross-Cutting Elements\nThese elements are involved across all stages describes above. They need to constantly by addressed throughout all the Data Life Cycle, making sure effective data management is in place.\n\n\n\n\n\n\n\n\nStep\nDescription\nTool\n\n\n\n\nDescribe\nDocument data and each of the data stages by describing the why, who, what, when, where, and how of the data and processes. Metadata, or data about data, is key to data sharing and reuse. Documentation such as software code comments, data models, and workflows facilitate indexing, acquiring, understanding, and future uses of the data\nMetadata and documentation\n\n\nManage Quality\nEmploy quality assurance and quality control procedures that enhance the quality of data, making sure the measurements or outputs within expected values.Identify potential errors and techniques to address them.\nQuality Control and Quality Assurance techniques\n\n\nBackup and Secure\nPlan to preserve data in the short term to minimize potential losses (e.g., via software failure, human error, natural disaster). This avoids risk and ensures data is accessible to collaborators. This applies to raw and process data, original science plan, data management plan, data acquisition strategy, processing procedures, versioning, analysis methods, published products, and associated metadata\nServers, secure data sharing services" + "text": "3.3 The Data Life Cycle\nThe Data Life Cycle gives you an overview of meaningful steps data goes through in a research project, from planning to archival. This step-by-step breakdown facilitates overseeing individual actions, operations and processes required at each stage. This is a visual tool that aims o help scientists plan and anticipate what will be the “data needs” for a specific project (Faundeen et al 2013) .\n\n\n\nSource: Adapted from Faundeen et al 2013, USGS & DataONE\n\n\n\n3.3.1 Primary Elements\n\n\n\n\n\n\n\n\nStep\nDescription\nTool\n\n\n\n\nPlan\nMap out the processes and resources for all activities related to the handling of the project’s data assets. Start with the project goals (desired outputs, outcomes, and impacts) and work backwards to build a data management plan, supporting data policies, and sustainability plans for each step.\nData Management Plan (DPM)\n\n\nAcquire & Discover\nActivities needed to collect new or existing data. You can structure the process of collecting data upfront to better implement data management. Consider data policies and best practices that maintain the provenance and integrity of the data.\nIdentifying data sources and mechanisms to access data\n\n\nProcess\nEvery step needed to prepare new or existing data to be able to use it as an input for synthesis. Consider the structure of the data, unit transformation, extrapolations, etc\nCleaning & Wrangling data skills\n\n\nIntegrate\nData from multiple sources are combined into a form that can be readily analyzed. Successful data integration depends on documentation of the integration process, clearly citing and making accessible the data you are using, and employing good data management practices throughout the Data Life Cycle.\nModeling & Interpretation\n\n\nAnalyze\nCreate analyses and visualizations to identify patterns, test hypotheses, and illustrate findings. During this process, record your methods, document data processing steps, and ensure your data are reproducible. Learn about these best practices and more.\nModeling, Interpretation & Statistics\n\n\nPreserve\nPlan on how you are going to store your data for long-term use and accessibility so others can access, interpret, and use the data in the future. Decide what data to preserve, where to preserve it, and what documentation needs to accompany the data.\nData packages & repositories\n\n\nPublish and Share\nPublication and distribution of your data through the web or in data catalogs, social media or other venues to increase the chances of your data being discovered. Data is a research product as publications are.\nDOIs and citations\n\n\n\n\n\n3.3.2 Cross-Cutting Elements\nThese elements are involved across all stages describes above. They need to constantly by addressed throughout all the Data Life Cycle, making sure effective data management is in place.\n\n\n\n\n\n\n\n\nStep\nDescription\nTool\n\n\n\n\nDescribe\nDocument data and each of the data stages by describing the why, who, what, when, where, and how of the data and processes. Metadata, or data about data, is key to data sharing and reuse. Documentation such as software code comments, data models, and workflows facilitate indexing, acquiring, understanding, and future uses of the data\nMetadata and documentation\n\n\nManage Quality\nEmploy quality assurance and quality control procedures that enhance the quality of data, making sure the measurements or outputs within expected values.Identify potential errors and techniques to address them.\nQuality Control and Quality Assurance techniques\n\n\nBackup and Secure\nPlan to preserve data in the short term to minimize potential losses (e.g., via software failure, human error, natural disaster). This avoids risk and ensures data is accessible to collaborators. This applies to raw and process data, original science plan, data management plan, data acquisition strategy, processing procedures, versioning, analysis methods, published products, and associated metadata\nServers, secure data sharing services", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#data-management-plans", "href": "session_03.html#data-management-plans", "title": "3  Data Management Essentials", "section": "3.4 Data Management Plans", - "text": "3.4 Data Management Plans\nAs you can see there is a lot happening around the Data Life Cycle. This is why PLANNING is a key first step. It is advisable to initiate your data management planning at the beginning of your research process before any data has been collected or discovered.\nIn order to better plan and keep track of all the moving pieces when working with data, a good place to start is creating a Data Management Plan. However, this is not only the starting point. This is a “living” document that should be consulted and updated throughout the project.\nA Data Management Plan (DMP) is a document that describes how you will use your data during a research project, as well as what you will do with your data long after the project ends. DMPs should be updated as research plans change to ensure new data management practices are captured (Environmental Data Initiative).\nA well-thought-out plan means you are more likely to:\n\nstay organized\nwork efficiently\ntruly share data\nengage your team\nmeet funder requirements as DMPs are becoming common in the submission process for proposals\n\nA DMP is both a straightforward blueprint for how you manage your data, and provides guidelines for you and your team on policies, roles and responsibilities. While it is important to plan, it is equally important to recognize that no plan is perfect, as change is inevitable. To make your DMP as robust as possible, review it periodically with your team and adjust as the needs of the project change.\n\n\n\n\n\n\nHow to plan\n\n\n\n\nPlan early - information gets lost over time. Think about your data needs as you are starting your project.\nPlan in collaboration - engaging all the team makes your plan more resilient, including diverse expertise and perspectives.\nMake revision part of the process - adapt as needed, revising your plan helps you make sure your are on track.\nInclude a tidy data and data ethic lens \n\n\n\n\n\n3.4.1 Creating a Good Data management Plan\nThe article Ten Simple Rules for Creating a Good Data Management Plan (Michener (2015)) outlines big picture ideas to keep in mind when you start your “planning stage”. Here we summarize each point and provide useful resources or examples to help you achieve this “rules” and write an awesome DMP.\n\n3.4.1.1 Determine what are the organization and/or sponsor requirements\n\nGenerally, each organization or funding agency have specific expectations on how to manage and disseminate data. Even though a DMP is a good idea to keep you organize. It will save you significant time and effort by first understanding the specific requirements set by the organization you are working for. Each organization often provide templates on how to structure your DMP.\nResources\n\nThe DMPTool provides templates for different funding agencies plan requirements.\nUSGS has multiple resources on DMPs. Here the Data Policy and Guidance for the Climate Adaptation Science Centers\n\n\n\n\n3.4.1.2 Identify the desired/necessary data sets for the project\n\nData is the ultimate reason why we create a DMP. Identifying what data will be use is crucial to planning. Key aspects of the data to consider are:\n\nType (text, spatial, images, tabular, etc)\nSource (where does the data currently live?, is it proprietary data?)\nVolume (10 terabytes, 10 megabytes?)\nFormat (csv, xlsx, shapefiles, etc)\n\nResource\n\nHere is a template spreadsheet to collect all information about the data set you intent to use for your synthesis project. Please make a copy and adapt as needed.\n\n\n\n\n3.4.1.3 Define how the data will be organized\n\nOnce you know the data you will be using (rule #2) it is time to define how are you going to work with your data. Where will the raw data live? How are the different collaborators going to access the data? The needs vary widely from one project to another depending on the data. When drafting your DMP is helpful to focus on identifying what products and software you will be using. When collaborating with a team it is important to identify f there are any limitations to accessing any software or tool.\nResource\n\nHere is an example from the LTER Scientific Computing Support Team on working on NCEAS Server.\n\n\n\n\n3.4.1.4 Explain how the data will be documented\n\nWe know documenting data is very important. To successfully achieve this we need a plan in place. Three main steps to plan accordingly are:\n\nIdentifying the type of information you want/need to collect to document your data thoroughly\nDetermine if the is a metadata standard or schema (organized set of elements) you will follow (eg. EML, Dublin Core, ISO 19115, ect). In many cases this relates with what data repository you intend to archive your data.\nEstablish tools that can help you create and manage metadata content.\n\nResource\n\nExcel-to EML by Li Kui is a workflow that provides a spreadsheet template to collect metadata based on the Ecological Metadata Language Schema (EML)\nThe Environmental Data Repository (EDI) providees a tool called ezEML. A form-based web application that helps streamline the process of creating EML metadata.\n\n\n\n\n3.4.1.5 Describe how data quality will be assured\n\nQuality assurance and quality control (QA/QC) are the procedures taken to ensure data looks how we expect it to be. The ultimate goal is to improve the quality of the data products. Some fields of study, data types or funding organizations have specific set of guidelines for QA/QCing data. However, when writing your DMP it is important to describe what measures you plan to take to QA/QC the data (e.g: instrument calibration, verification tests, visualization approaches for error detection, etc.)\nResources\n\nEnvironmental Data Initiative (EDI) description and examples of Quality Assurance and Quality Control\n\n\n\n\n3.4.1.6 Have a data storage strategy (short and long term)\n\nPapers get lost, hardware disk crash, URLs break, different media format degrade. It’s inevitable! Plan ahead and think on where your data will live in the short and long-term to ensure the access and use of this data during and long after the project. It is important to have a backup mechanism in place during the project to avoid losing any information.\nResource\n\nRemote locations to store your data during your project are: institutional repositories or servers or commercial services such as Amazon, Dropbox, Google, Microsoft, Box, etc.\nLong-term storage: identify an appropriate and stable data repository for your research domain (See section 3.6 Data Preservation and Sharing)\n\n\n\n\n3.4.1.7 Define the project’s data policies\n\nMany organizations and institutions require to include an explicit policy statement about how data will be managed and shared. Including licensing or sharing arrangements and legal and ethical restrictions on access and use of human subject and other sensitive data. It is valuable to establish a shared agreement around handling of data when embarking on collaborative projects. Collaborative research brings together data from across research projects with different data management plans and can include publicly accessible data from repositories where no management plan is available. For these reasons, a discussion and agreement around the handling of data brought into and resulting from the collaboration is warranted, and management of this new data may benefit from going through a data management planning process.\nResource\n\nTemplate provided by the Arctic Data Center, including sections for individual data not in the public domain, individual data with public access, derived data resulting from the project.\n\n\n\n\n3.4.1.8 What data products will be made available and how?\n\nThis portion of the DMP tries to ensure that the data products of your project will be disseminated. This can be achieved by stating how, when and where these products will be available. We encourage open data practices, this means making data extensively available and with the least restrictions possible.\nExamples\n\nPublishing the data in an open repository or archive\nSubmitting the data (or subsets thereof) as appendices or supplements to journal articles\nPublishing the data, metadata, and relevant code as a “data paper”\n\n\n\n\n3.4.1.9 Assign roles and responsibilities\n\nIt is important to clearly determine the roles and responsibilities of each group member of the project. Roles may include data collection, data entry, QA/QC, metadata creation and management, backup, data preparation and submission to an archive, and systems administration.\n\n\n\n3.4.1.10 Prepare a realistic budget\n\nGenerally overlooked, but preparing a realistic budget it’s an important part when planning for your data management. Data management takes time and it may have cost associates to it for example access to software, hardware, and personnel. Make sure you plan considers budget to support people involved as well as software or data fees or other services as needed." + "text": "3.4 Data Management Plans\nAs you can see there is a lot happening around the Data Life Cycle. This is why PLANNING is a key first step. It is advisable to initiate your data management planning at the beginning of your research process before any data has been collected or discovered.\nIn order to better plan and keep track of all the moving pieces when working with data, a good place to start is creating a Data Management Plan. However, this is not only the starting point. This is a “living” document that should be consulted and updated throughout the project.\nA Data Management Plan (DMP) is a document that describes how you will use your data during a research project, as well as what you will do with your data long after the project ends. DMPs should be updated as research plans change to ensure new data management practices are captured (Environmental Data Initiative).\nA well-thought-out plan means you are more likely to:\n\nstay organized\nwork efficiently\ntruly share data\nengage your team\nmeet funder requirements as DMPs are becoming common in the submission process for proposals\n\nA DMP is both a straightforward blueprint for how you manage your data, and provides guidelines for you and your team on policies, roles and responsibilities. While it is important to plan, it is equally important to recognize that no plan is perfect, as change is inevitable. To make your DMP as robust as possible, review it periodically with your team and adjust as the needs of the project change.\n\n\n\n\n\n\nHow to plan\n\n\n\n\nPlan early - information gets lost over time. Think about your data needs as you are starting your project.\nPlan in collaboration - engaging all the team makes your plan more resilient, including diverse expertise and perspectives.\nMake revision part of the process - adapt as needed, revising your plan helps you make sure your are on track.\nInclude a tidy data and data ethic lens \n\n\n\n\n\n3.4.1 Creating a Good Data management Plan\nThe article Ten Simple Rules for Creating a Good Data Management Plan (Michener (2015)) outlines big picture ideas to keep in mind when you start your “planning stage”. Here we summarize each point and provide useful resources or examples to help you achieve this “rules” and write an awesome DMP.\n\n3.4.1.1 Determine what are the organization and/or sponsor requirements\n\nGenerally, each organization or funding agency have specific expectations on how to manage and disseminate data. Even though a DMP is a good idea to keep you organize. It will save you significant time and effort by first understanding the specific requirements set by the organization you are working for. Each organization often provide templates on how to structure your DMP.\nResources\n\nThe DMPTool provides templates for different funding agencies plan requirements.\nUSGS has multiple resources on DMPs. Here the Data Policy and Guidance for the Climate Adaptation Science Centers\n\n\n\n\n3.4.1.2 Identify the desired/necessary data sets for the project\n\nData is the ultimate reason why we create a DMP. Identifying what data will be use is crucial to planning. Key aspects of the data to consider are:\n\nType (text, spatial, images, tabular, etc)\nSource (where does the data currently live?, is it proprietary data?)\nVolume (10 terabytes, 10 megabytes?)\nFormat (csv, xlsx, shapefiles, etc)\n\nResource\n\nHere is a template spreadsheet to collect all information about the data set you intent to use for your synthesis project. Please make a copy and adapt as needed.\n\n\n\n\n3.4.1.3 Define how the data will be organized\n\nOnce you know the data you will be using (rule #2) it is time to define how are you going to work with your data. Where will the raw data live? How are the different collaborators going to access the data? The needs vary widely from one project to another depending on the data. When drafting your DMP is helpful to focus on identifying what products and software you will be using. When collaborating with a team it is important to identify f there are any limitations to accessing any software or tool.\nResource\n\nHere is an example from the LTER Scientific Computing Support Team on working on NCEAS Server.\n\n\n\n\n3.4.1.4 Explain how the data will be documented\n\nWe know documenting data is very important. To successfully achieve this we need a plan in place. Three main steps to plan accordingly are:\n\nIdentifying the type of information you want/need to collect to document your data thoroughly\nDetermine if the is a metadata standard or schema (organized set of elements) you will follow (eg. EML, Dublin Core, ISO 19115, ect). In many cases this relates with what data repository you intend to archive your data.\nEstablish tools that can help you create and manage metadata content.\n\nResource\n\nExcel-to EML by Li Kui is a workflow that provides a spreadsheet template to collect metadata based on the Ecological Metadata Language Schema (EML)\nThe Environmental Data Repository (EDI) providees a tool called ezEML. A form-based web application that helps streamline the process of creating EML metadata.\n\n\n\n\n3.4.1.5 Describe how data quality will be assured\n\nQuality assurance and quality control (QA/QC) are the procedures taken to ensure data looks how we expect it to be. The ultimate goal is to improve the quality of the data products. Some fields of study, data types or funding organizations have specific set of guidelines for QA/QCing data. However, when writing your DMP it is important to describe what measures you plan to take to QA/QC the data (e.g: instrument calibration, verification tests, visualization approaches for error detection, etc.)\nResources\n\nEnvironmental Data Initiative (EDI) description and examples of Quality Assurance and Quality Control\n\n\n\n\n3.4.1.6 Have a data storage strategy (short and long term)\n\nPapers get lost, hardware disk crash, URLs break, different media format degrade. It’s inevitable! Plan ahead and think on where your data will live in the short and long-term to ensure the access and use of this data during and long after the project. It is important to have a backup mechanism in place during the project to avoid losing any information.\nResource\n\nRemote locations to store your data during your project are: institutional repositories or servers or commercial services such as Amazon, Dropbox, Google, Microsoft, Box, etc.\nLong-term storage: identify an appropriate and stable data repository for your research domain (See section 3.6 Data Preservation and Sharing)\n\n\n\n\n3.4.1.7 Define the project’s data policies\n\nMany organizations and institutions require to include an explicit policy statement about how data will be managed and shared. Including licensing or sharing arrangements and legal and ethical restrictions on access and use of human subject and other sensitive data. It is valuable to establish a shared agreement around handling of data when embarking on collaborative projects. Collaborative research brings together data from across research projects with different data management plans and can include publicly accessible data from repositories where no management plan is available. For these reasons, a discussion and agreement around the handling of data brought into and resulting from the collaboration is warranted, and management of this new data may benefit from going through a data management planning process.\nResource\n\nTemplate provided by the Arctic Data Center, including sections for individual data not in the public domain, individual data with public access, derived data resulting from the project.\n\n\n\n\n3.4.1.8 What data products will be made available and how?\n\nThis portion of the DMP tries to ensure that the data products of your project will be disseminated. This can be achieved by stating how, when and where these products will be available. We encourage open data practices, this means making data extensively available and with the least restrictions possible.\nExamples\n\nPublishing the data in an open repository or archive\nSubmitting the data (or subsets thereof) as appendices or supplements to journal articles\nPublishing the data, metadata, and relevant code as a “data paper”\n\n\n\n\n3.4.1.9 Assign roles and responsibilities\n\nIt is important to clearly determine the roles and responsibilities of each group member of the project. Roles may include data collection, data entry, QA/QC, metadata creation and management, backup, data preparation and submission to an archive, and systems administration.\n\n\n\n3.4.1.10 Prepare a realistic budget\n\nGenerally overlooked, but preparing a realistic budget it’s an important part when planning for your data management. Data management takes time and it may have cost associates to it for example access to software, hardware, and personnel. Make sure you plan considers budget to support people involved as well as software or data fees or other services as needed.", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#metadata-best-practices", "href": "session_03.html#metadata-best-practices", "title": "3  Data Management Essentials", "section": "3.5 Metadata Best Practices", - "text": "3.5 Metadata Best Practices\nWithin the data life cycle you can be collecting data (creating new data) or integrating data that has all ready been collected. Either way, metadata plays plays a major role to successfully spin around the cycle because it enables data reuse long after the original collection.\nImagine that you’re writing your metadata for a typical researcher (who might even be you!) 30+ years from now - what will they need to understand what’s inside your data files?\nThe goal is to have enough information for the researcher to understand the data, interpret the data, and then reuse the data in another study.\n\n3.5.1 Overall Guidelines\nAnother way to think about metadata is to answer the following questions with the documentation:\n\nWhat was measured?\nWho measured it?\nWhen was it measured?\nWhere was it measured?\nHow was it measured?\nHow is the data structured?\nWhy was the data collected?\nWho should get credit for this data (researcher AND funding agency)?\nHow can this data be reused (licensing)?\n\n\n\n3.5.2 Bibliographic Guidelines\nThe details that will help your data be cited correctly are:\n\nGlobal identifier like a digital object identifier (DOI)\nDescriptive title that includes information about the topic, the geographic location, the dates, and if applicable, the scale of the data\nDescriptive abstract that serves as a brief overview off the specific contents and purpose of the data package\nFunding information like the award number and the sponsor\nPeople and organizations like the creator of the dataset (i.e. who should be cited), the person to contact about the dataset (if different than the creator), and the contributors to the dataset\n\n\n\n3.5.3 Discovery Guidelines\nThe details that will help your data be discovered correctly are:\n\nGeospatial coverage of the data, including the field and laboratory sampling locations, place names and precise coordinates\nTemporal coverage of the data, including when the measurements were made and what time period (ie the calendar time or the geologic time) the measurements apply to\nTaxonomic coverage of the data, including what species were measured and what taxonomy standards and procedures were followed\nAny other contextual information as needed\n\n\n\n3.5.4 Interpretation Guidelines\nThe details that will help your data be interpreted correctly are:\n\nCollection methods for both field and laboratory data the full experimental and project design as well as how the data in the dataset fits into the overall project\nProcessing methods for both field and laboratory samples\nAll sample quality control procedures\nProvenance information to support your analysis and modelling methods\nInformation about the hardware and software used to process your data, including the make, model, and version\nComputing quality control procedures like testing or code review\n\n\n\n3.5.5 Data Structure and Contents\n\nEverything needs a description: the data model, the data objects (like tables, images, matrices, spatial layers, etc), and the variables all need to be described so that there is no room for misinterpretation.\nVariable information includes the definition of a variable, a standardized unit of measurement, definitions of any coded values (i.e. 0 = not collected), and any missing values (i.e. 999 = NA).\n\nNot only is this information helpful to you and any other researcher in the future using your data, but it is also helpful to search engines. The semantics of your dataset are crucial to ensure your data is both discoverable by others and interoperable (that is, reusable).\nFor example, if you were to search for the character string “carbon dioxide flux” in a data repository, not all relevant results will be shown due to varying vocabulary conventions (i.e., “CO2 flux” instead of “carbon dioxide flux”) across disciplines — only datasets containing the exact words “carbon dioxide flux” are returned. With correct semantic annotation of the variables, your dataset that includes information about carbon dioxide flux but that calls it CO2 flux WOULD be included in that search.\n\n\n3.5.6 Rights and Attribution\nCorrectly assigning a way for your datasets to be cited and reused is the last piece of a complete metadata document. This section sets the scientific rights and expectations for the future on your data, like:\n\nCitation format to be used when giving credit for the data\nAttribution expectations for the dataset\nReuse rights, which describe who may use the data and for what purpose\nRedistribution rights, which describe who may copy and redistribute the metadata and the data\nLegal terms and conditions like how the data are licensed for reuse.\n\n\n\n3.5.7 Metadata Standards\nSo, how does a computer organize all this information? There are a number of metadata standards that make your metadata machine readable and therefore easier for data curators to publish your data.\n\nEcological Metadata Language (EML)\nGeospatial Metadata Standards (ISO 19115 and ISO 19139)\n\nSee NOAA’s ISO Workbook\n\nBiological Data Profile (BDP)\nDublin Core\nDarwin Core\nPREservation Metadata: Implementation Strategies (PREMIS)\nMetadata Encoding Transmission Standard (METS)\n\nNote this is not an exhaustive list.\n\n\n3.5.8 Data Identifiers\nMany journals require a DOI (a digital object identifier) be assigned to the published data before the paper can be accepted for publication. The reason for that is so that the data can easily be found and easily linked to.\nSome data repositories assign a DOI for each dataset you publish on their repository. But, if you need to update the datasets, check the policy of the data repository. Some repositories assign a new DOI after you update the dataset. If this is the case, researchers should cite the exact version of the dataset that they used in their analysis, even if there is a newer version of the dataset available.\n\n\n3.5.9 Data Citation\nResearchers should get in the habit of citing the data that they use (even if it’s their own data!) in each publication that uses that data." + "text": "3.5 Metadata Best Practices\nWithin the data life cycle you can be collecting data (creating new data) or integrating data that has all ready been collected. Either way, metadata plays plays a major role to successfully spin around the cycle because it enables data reuse long after the original collection.\nImagine that you’re writing your metadata for a typical researcher (who might even be you!) 30+ years from now - what will they need to understand what’s inside your data files?\nThe goal is to have enough information for the researcher to understand the data, interpret the data, and then reuse the data in another study.\n\n3.5.1 Overall Guidelines\nAnother way to think about metadata is to answer the following questions with the documentation:\n\nWhat was measured?\nWho measured it?\nWhen was it measured?\nWhere was it measured?\nHow was it measured?\nHow is the data structured?\nWhy was the data collected?\nWho should get credit for this data (researcher AND funding agency)?\nHow can this data be reused (licensing)?\n\n\n\n3.5.2 Bibliographic Guidelines\nThe details that will help your data be cited correctly are:\n\nGlobal identifier like a digital object identifier (DOI)\nDescriptive title that includes information about the topic, the geographic location, the dates, and if applicable, the scale of the data\nDescriptive abstract that serves as a brief overview off the specific contents and purpose of the data package\nFunding information like the award number and the sponsor\nPeople and organizations like the creator of the dataset (i.e. who should be cited), the person to contact about the dataset (if different than the creator), and the contributors to the dataset\n\n\n\n3.5.3 Discovery Guidelines\nThe details that will help your data be discovered correctly are:\n\nGeospatial coverage of the data, including the field and laboratory sampling locations, place names and precise coordinates\nTemporal coverage of the data, including when the measurements were made and what time period (ie the calendar time or the geologic time) the measurements apply to\nTaxonomic coverage of the data, including what species were measured and what taxonomy standards and procedures were followed\nAny other contextual information as needed\n\n\n\n3.5.4 Interpretation Guidelines\nThe details that will help your data be interpreted correctly are:\n\nCollection methods for both field and laboratory data the full experimental and project design as well as how the data in the dataset fits into the overall project\nProcessing methods for both field and laboratory samples\nAll sample quality control procedures\nProvenance information to support your analysis and modelling methods\nInformation about the hardware and software used to process your data, including the make, model, and version\nComputing quality control procedures like testing or code review\n\n\n\n3.5.5 Data Structure and Contents\n\nEverything needs a description: the data model, the data objects (like tables, images, matrices, spatial layers, etc), and the variables all need to be described so that there is no room for misinterpretation.\nVariable information includes the definition of a variable, a standardized unit of measurement, definitions of any coded values (i.e. 0 = not collected), and any missing values (i.e. 999 = NA).\n\nNot only is this information helpful to you and any other researcher in the future using your data, but it is also helpful to search engines. The semantics of your dataset are crucial to ensure your data is both discoverable by others and interoperable (that is, reusable).\nFor example, if you were to search for the character string “carbon dioxide flux” in a data repository, not all relevant results will be shown due to varying vocabulary conventions (i.e., “CO2 flux” instead of “carbon dioxide flux”) across disciplines — only datasets containing the exact words “carbon dioxide flux” are returned. With correct semantic annotation of the variables, your dataset that includes information about carbon dioxide flux but that calls it CO2 flux WOULD be included in that search.\n\n\n3.5.6 Rights and Attribution\nCorrectly assigning a way for your datasets to be cited and reused is the last piece of a complete metadata document. This section sets the scientific rights and expectations for the future on your data, like:\n\nCitation format to be used when giving credit for the data\nAttribution expectations for the dataset\nReuse rights, which describe who may use the data and for what purpose\nRedistribution rights, which describe who may copy and redistribute the metadata and the data\nLegal terms and conditions like how the data are licensed for reuse.\n\n\n\n3.5.7 Metadata Standards\nSo, how does a computer organize all this information? There are a number of metadata standards that make your metadata machine readable and therefore easier for data curators to publish your data.\n\nEcological Metadata Language (EML)\nGeospatial Metadata Standards (ISO 19115 and ISO 19139)\n\nSee NOAA’s ISO Workbook\n\nBiological Data Profile (BDP)\nDublin Core\nDarwin Core\nPREservation Metadata: Implementation Strategies (PREMIS)\nMetadata Encoding Transmission Standard (METS)\n\nNote this is not an exhaustive list.\n\n\n3.5.8 Data Identifiers\nMany journals require a DOI (a digital object identifier) be assigned to the published data before the paper can be accepted for publication. The reason for that is so that the data can easily be found and easily linked to.\nSome data repositories assign a DOI for each dataset you publish on their repository. But, if you need to update the datasets, check the policy of the data repository. Some repositories assign a new DOI after you update the dataset. If this is the case, researchers should cite the exact version of the dataset that they used in their analysis, even if there is a newer version of the dataset available.\n\n\n3.5.9 Data Citation\nResearchers should get in the habit of citing the data that they use (even if it’s their own data!) in each publication that uses that data.", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#data-preservation-sharing", "href": "session_03.html#data-preservation-sharing", "title": "3  Data Management Essentials", "section": "3.6 Data Preservation & Sharing", - "text": "3.6 Data Preservation & Sharing\n\n\n3.6.1 Data Packages\n\nWe define a data package as a scientifically useful collection of data and metadata that a researcher wants to preserve.\n\nSometimes a data package represents all of the data from a particular experiment, while at other times it might be all of the data from a grant, or on a topic, or associated with a paper. Whatever the extent, we define a data package as having one or more data files, software files, and other scientific products such as graphs and images, all tied together with a descriptive metadata document.\nMany data repositories assign a unique identifier to every version of every data file, similarly to how it works with source code commits in GitHub. Those identifiers usually take one of two forms. A DOI identifier, often assigned to the metadata and becomes a publicly citable identifier for the package. Each of the other files gets a global identifier, often a UUID that is globally unique. This allows to identify a digital entity within a data package.\nIn the graphic to the side, the package can be cited with the DOI doi:10.5063/F1Z1899CZ,and each of the individual files have their own identifiers as well.\n\n\n\n3.6.2 Data Repositories: Built for Data (and code)\n\nGitHub is not an archival location\nExamples of dedicated data repositories:\n\nKNB\nArctic Data Center\ntDAR\nEDI\nZenodo\n\nDedicated data repositories are:\n\nRich in metadata\nArchival in their mission\nCertified\n\nData papers, e.g., Scientific Data\nre3data is a global registry of research data repositories\nRepository Finder is a pilot project and tool to help researchers find an appropriate repository for their work\n\n\n3.6.2.1 DataOne Federation\nDataONE is a federation of dozens of data repositories that work together to make their systems interoperable and to provide a single unified search system that spans the repositories. DataONE aims to make it simpler for researchers to publish data to one of its member repositories, and then to discover and download that data for reuse in synthetic analyses.\nDataONE can be searched on the web, which effectively allows a single search to find data from the dozens of members of DataONE, rather than visiting each of the (currently 44!) repositories one at a time." + "text": "3.6 Data Preservation & Sharing\n\n\n3.6.1 Data Packages\n\nWe define a data package as a scientifically useful collection of data and metadata that a researcher wants to preserve.\n\nSometimes a data package represents all of the data from a particular experiment, while at other times it might be all of the data from a grant, or on a topic, or associated with a paper. Whatever the extent, we define a data package as having one or more data files, software files, and other scientific products such as graphs and images, all tied together with a descriptive metadata document.\nMany data repositories assign a unique identifier to every version of every data file, similarly to how it works with source code commits in GitHub. Those identifiers usually take one of two forms. A DOI identifier, often assigned to the metadata and becomes a publicly citable identifier for the package. Each of the other files gets a global identifier, often a UUID that is globally unique. This allows to identify a digital entity within a data package.\nIn the graphic to the side, the package can be cited with the DOI doi:10.5063/F1Z1899CZ,and each of the individual files have their own identifiers as well.\n\n\n\n3.6.2 Data Repositories: Built for Data (and code)\n\nGitHub is not an archival location\nExamples of dedicated data repositories:\n\nKNB\nArctic Data Center\ntDAR\nEDI\nZenodo\n\nDedicated data repositories are:\n\nRich in metadata\nArchival in their mission\nCertified\n\nData papers, e.g., Scientific Data\nre3data is a global registry of research data repositories\nRepository Finder is a pilot project and tool to help researchers find an appropriate repository for their work\n\n\n3.6.2.1 DataOne Federation\nDataONE is a federation of dozens of data repositories that work together to make their systems interoperable and to provide a single unified search system that spans the repositories. DataONE aims to make it simpler for researchers to publish data to one of its member repositories, and then to discover and download that data for reuse in synthetic analyses.\nDataONE can be searched on the web, which effectively allows a single search to find data from the dozens of members of DataONE, rather than visiting each of the (currently 44!) repositories one at a time.", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#summary", "href": "session_03.html#summary", "title": "3  Data Management Essentials", "section": "3.7 Summary", - "text": "3.7 Summary\n\nThe Data Life Cycle help us see the big picture of our data project.\nIt is extremely helpful to develop a data management plan describing each step of the data life cycle to stay organized.\nDocument everything. Having rich metadata is a key factor to enable data reuse. Describe your data and files and use an appropriate metadata standard.\nIdentify software and tools that will help you and your team organize and document the project’s data life cycle.\nPublish your data in a stable long live repository and assign a unique identifier." + "text": "3.7 Summary\n\nThe Data Life Cycle help us see the big picture of our data project.\nIt is extremely helpful to develop a data management plan describing each step of the data life cycle to stay organized.\nDocument everything. Having rich metadata is a key factor to enable data reuse. Describe your data and files and use an appropriate metadata standard.\nIdentify software and tools that will help you and your team organize and document the project’s data life cycle.\nPublish your data in a stable long live repository and assign a unique identifier.", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#activity", "href": "session_03.html#activity", "title": "3  Data Management Essentials", "section": "3.8 Activity", - "text": "3.8 Activity\n\n\n\n\n\n\nQuestions to guide your Data Management Plan\n\n\n\nUsing the Logic Models you started on Monday, read the questions in this document. Answer as many as possible to the best of your knowledge. Identify which aspects of managing your data are easier to think about and which ones are more difficult, or you need more guidance." + "text": "3.8 Activity\n\n\n\n\n\n\nQuestions to guide your Data Management Plan\n\n\n\nUsing the Logic Models you started on Monday, read the questions in this document. Answer as many as possible to the best of your knowledge. Identify which aspects of managing your data are easier to think about and which ones are more difficult, or you need more guidance.", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] }, { "objectID": "session_03.html#resources", "href": "session_03.html#resources", "title": "3  Data Management Essentials", "section": "Resources", - "text": "Resources\n\nDMP Example: Using NASA Remote Sensing Data to Reduce Uncertainty of Land-Use Transitions in Global Carbon-Climate Models\nDPM Example: USGS Coastal and Marine Science Center Data Management Plan\nUSGS Data Management Plan Checklist\nSOP for data management for Ocean Health Index assessments (2023 version)\n\n\n\n\n\nMichener, William K. 2015. “Ten Simple Rules for Creating a Good Data Management Plan.” PLOS Computational Biology 11 (10): 1–9. https://doi.org/10.1371/journal.pcbi.1004525." + "text": "Resources\n\nDMP Example: Using NASA Remote Sensing Data to Reduce Uncertainty of Land-Use Transitions in Global Carbon-Climate Models\nDPM Example: USGS Coastal and Marine Science Center Data Management Plan\nUSGS Data Management Plan Checklist\nSOP for data management for Ocean Health Index assessments (2023 version)\n\n\n\n\n\nMichener, William K. 2015. “Ten Simple Rules for Creating a Good Data Management Plan.” PLOS Computational Biology 11 (10): 1–9. https://doi.org/10.1371/journal.pcbi.1004525.", + "crumbs": [ + "Week 1", + "3  Data Management Essentials" + ] + }, + { + "objectID": "session_04.html", + "href": "session_04.html", + "title": "4  Install R, RStudio and Git", + "section": "", + "text": "4.1 Installation steps for MacOS", + "crumbs": [ + "Week 2", + "4  Install R, RStudio and Git" + ] + }, + { + "objectID": "session_04.html#installation-steps-for-macos", + "href": "session_04.html#installation-steps-for-macos", + "title": "4  Install R, RStudio and Git", + "section": "", + "text": "4.1.1 Install or update R\nTo install R, visit cloud.r-project.org to download the most recent version for your operating system. The latest release is version 4.3.2 ( released 2023-10-31).\n\n\n4.1.2 Install or update RStudio\nWhile R is a programming language, RStudio is a software (often referred to as an IDE, Integrated Development Environment) that provides R programmers with a neat, easy-to-use interface for coding in R. There are a number of IDEs out there, but RStudio is arguably the best and definitely most popular among R programmers.\nNote: RStudio will not work without R installed, and you won’t particularly enjoy using R without having RStudio installed. Be sure to install both!\n\n\n\n\n\nImage Credit: Manny Gimond | Accessible at https://mgimond.github.io/ES218/R_vs_RStudio.html\n\n\n\n\n\nNew install: To install RStudio, visit https://posit.co/download/rstudio-desktop/. Download the free (“Open Source Edition”) Desktop version for your operating system. You should install the most up-to-date version available that is supported by your operating system.\nUpdate: If you already have RStudio and need to update: Open RStudio, and under ‘Help’ in the top menu, choose ‘Check for updates.’ If you have the most recent release, it will return ‘No update available. You are running the most recent version of RStudio.’ Otherwise, you should follow the instructions to install an updated version.\nOpen RStudio (logo you’ll click on shown below): If upon opening RStudio you are prompted to install Command Line Tools, do it.\n\n\n\n\n\n\n\n\n\n\n\nNote: you may need to install command line tools and XQuartz.\n\nTo install command line tools (if you’re not automatically prompted), run in the Terminal tab in RStudio: xcode-select --install\nVisit xquartz.org to download & install XQuartz\n\n\n\n\n4.1.3 Install Quarto\nQuarto is a scientific publishing tool built on Pandoc that allows R, Python, Julia, and ObservableJS users to create dynamic documents, websites, books and more.\nQuarto is now included with RStudio v2022.07.1+ so no need for a separate download/install if you have the latest version of RStudio! You can find all releases (current, pre, and older releases) on the Quarto website download page, should you want/need to reference them.\n\n\n4.1.4 Check for git\nYou should already have git on your device, but let’s check for it anyway.\n\nOpen RStudio\nIn the Terminal, run the following command:\n\n\nwhich git\n\n\nIf after running that you get something that looks like a file path to git on your computer, then you have git installed. For example, that might return something like this (or it could differ a bit): /usr/local/bin/git. If you instead get no response at all, you should download & install git from here: git-scm.com/downloads\n\nAn aside: Is it ncesary to have Git installed in your machine for this workshop. GitHub’s Git Guides are a really wonderful resource to start learning about this topic.\n\n\n4.1.5 Install R packages\n\nInstall the usethis and gitcreds packages in R by running the following in the RStudio Console:\n\n\ninstall.packages(“usethis”)\n\ninstall.packages(\"gitcreds\")\n\nA lot of scary looking red text will show up while this is installing - don’t panic. If you get to the end and see something like below (with no error) it’s installed successfully.\n\n\n\n\n\n\n\n\n\n\n\n4.1.6 Create a GitHub account\n\nIf you don’t already have a GitHub account, go to github.com and create one. Here are helpful considerations for choosing a username: happygitwithr.com/github-acct.html.\n\nOnce you’ve completed these steps you are ready for our workshop on Git and Github", + "crumbs": [ + "Week 2", + "4  Install R, RStudio and Git" + ] + }, + { + "objectID": "session_04.html#installation-steps-for-windows", + "href": "session_04.html#installation-steps-for-windows", + "title": "4  Install R, RStudio and Git", + "section": "4.2 Installation steps for Windows", + "text": "4.2 Installation steps for Windows\n\n4.2.1 Install or update R\nTo install R, visit cloud.r-project.org to download the most recent version for your operating system. The latest release is version 4.3.2 ( released 2023-10-31).\n\n\n4.2.2 Install or update RStudio\nWhile R is a programming language, RStudio is a software (often referred to as an IDE, Integrated Development Environment) that provides R programmers with a neat, easy-to-use interface for coding in R. There are a number of IDEs out there, but RStudio is arguably the best and definitely most popular among R programmers.\nNote: RStudio will not work without R installed, and you won’t particularly enjoy using R without having RStudio installed. Be sure to install both!\n\n\n\n\n\nImage Credit: Manny Gimond | Accessible at https://mgimond.github.io/ES218/R_vs_RStudio.html\n\n\n\n\n\nNew install: To install RStudio, visit https://posit.co/download/rstudio-desktop/. Download the free (“Open Source Edition”) Desktop version for your operating system. You should install the most up-to-date version available that is supported by your operating system.\nUpdate: If you already have RStudio and need to update: Open RStudio, and under ‘Help’ in the top menu, choose ‘Check for updates.’ If you have the most recent release, it will return ‘No update available. You are running the most recent version of RStudio.’ Otherwise, you should follow the instructions to install an updated version.\nOpen RStudio (logo you’ll click on shown below): If upon opening RStudio you are prompted to install Command Line Tools, do it.\n\n\n\n\n\n\n\n\n\n\n\n\n4.2.3 Install Quarto\nQuarto is a scientific publishing tool built on Pandoc that allows R, Python, Julia, and ObservableJS users to create dynamic documents, websites, books and more.\nQuarto is now included with RStudio v2022.07.1+ so no need for a separate download/install if you have the latest version of RStudio! You can find all releases (current, pre, and older releases) on the Quarto website download page, should you want/need to reference them.\n\n\n4.2.4 Check for git\nYou should already have git on your device, but let’s check for it anyway.\n\nOpen RStudio\nIn the Terminal, run the following command:\n\n\nwhere git\n\n\nIf after running that you get something that looks like a file path to git on your computer, then you have git installed. For example, that might return something like this (or it could differ a bit): /usr/local/bin/git. If you instead get no response at all or something along the lines “git is not installed”, you should download & install git from here: https://gitforwindows.org/.\n\nOnce you have download and installed Git, restart your computer. Then open RStudio and again run:\n\nwhere git\n\nIf you still get a message saying something like “git is not installed”, check out the Troubleshooting section below.\nAn aside: Is it necessary to have Git installed in your machine for this workshop. GitHub’s Git Guides are a really wonderful resource to start learning about this topic.\n\n\n4.2.5 Install R packages\n\nInstall the usethis and gitcreds packages in R by running the following in the RStudio Console:\n\n\ninstall.packages(\"usethis\")\n\ninstall.packages(\"gitcreds\")\n\nA lot of scary looking red text will show up while this is installing - don’t panic. If you get to the end and see something like below (with no error) it’s installed successfully.\n\n\n\n\n\n\n\n\n\n\n\n4.2.6 Create a GitHub account\n\nIf you don’t already have a GitHub account, go to github.com and create one. Here are helpful considerations for choosing a username: happygitwithr.com/github-acct.html.\n\nOnce you’ve completed these steps you are ready for our workshop on Git and Github", + "crumbs": [ + "Week 2", + "4  Install R, RStudio and Git" + ] + }, + { + "objectID": "session_04.html#troubleshooting", + "href": "session_04.html#troubleshooting", + "title": "4  Install R, RStudio and Git", + "section": "4.3 Troubleshooting", + "text": "4.3 Troubleshooting\n\n\n\n\n\n\nIssues installing Git on a Windows\n\n\n\nIf you download Git and the Git commands still not recognized by your computer, check your computer’s PATHS.\nTo do this, follow the instructions in this link on how to set the right PATHS.\nRestart your computer and try running git --version on the terminal. You should get something like git version XX.XX (but with numbers instead of Xs).\nIf you see the git version printed out in your terminal, you are all set", + "crumbs": [ + "Week 2", + "4  Install R, RStudio and Git" + ] + }, + { + "objectID": "session_05.html", + "href": "session_05.html", + "title": "5  R and GitHub Setup", + "section": "", + "text": "Learning Objectives", + "crumbs": [ + "Week 2", + "5  R and GitHub Setup" + ] + }, + { + "objectID": "session_05.html#learning-objectives", + "href": "session_05.html#learning-objectives", + "title": "5  R and GitHub Setup", + "section": "", + "text": "Set global options in your .gitconfig file\nPractice how to set up GitHub Authentication using a Personal Access Token (PAT)", + "crumbs": [ + "Week 2", + "5  R and GitHub Setup" + ] + }, + { + "objectID": "session_05.html#set-up-global-options-in-git", + "href": "session_05.html#set-up-global-options-in-git", + "title": "5  R and GitHub Setup", + "section": "5.1 Set up global options in Git", + "text": "5.1 Set up global options in Git\nBefore using Git, you need to tell it who you are, also known as setting the global options. To do this, we will be setting the global options in the Terminal.\n\n\n\n\n\n\nWhat’s the Terminal?\n\n\n\nTechnically, the Terminal is an interface for the shell, a computer program. To put that simply, we use the Terminal to tell a computer what to do. This is different from the Console in RStudio, which interprets R code and returns a value.\n\n\nTo get started, let’s open a new Terminal window in RStudio. Do this by clicking Tools > Terminal > New Terminal.\nA Terminal tab should now be open where your Console usually is.\n\n\n\n\n\n\nDon’t be afraid to dip your toes in the Terminal\n\n\n\nMost of our git operations will be done in RStudio, but there are some situations where you must work in the Terminal and use command line. It may be daunting to code in the Terminal, but as your comfort increases over time, you might find you prefer it. Either way, it’s beneficial to learn enough command line and to feel comfortable in the Terminal.\n\n\nLet’s start by adding your user name to the global options. Type the following into the command prompt, with your exact GitHub username, and press enter:\ngit config --global user.name \"my_user_name\"\n\n\nNote that if it ran successfully, it will look like nothing happened. We will check at the end to make sure it worked.\nNext, enter the following line, with the email address you used when you created your account on github.com:\ngit config --global user.email \"my_email@nceas.ucsb.edu\"\n\n\n\n\n\n\nCase and spelling matters!\n\n\n\nWhen you add your username and email to the global options you must use the exact same spelling and case that you used on GitHub otherwise, Git won’t be able to sync to your account.\n\n\nNext, we will set our credentials to not time out for a very long time. This is related to how our server operating system handles credentials - not doing this will make your Personal Access Token (PAT, which we will set up in the next section) expire immediately on the system, even though it is actually valid for at least a month.\ngit config --global credential.helper 'cache --timeout=10000000'\nNext, we will set the default branch name to main for any new repositories that are created moving forward. Why are we doing this? Previously, the default branch name was master and this racist terminology for git branches motivates us to update our default branch to main instead.\ngit config --global init.defaultBranch main\nFinally, check to make sure everything looks correct by entering this command, which will return the global options you have set.\ngit config --global --list", + "crumbs": [ + "Week 2", + "5  R and GitHub Setup" + ] + }, + { + "objectID": "session_05.html#github-authentication", + "href": "session_05.html#github-authentication", + "title": "5  R and GitHub Setup", + "section": "5.2 GitHub Authentication", + "text": "5.2 GitHub Authentication\nGitHub recently deprecated password authentication for accessing repositories, so we need to set up a secure way to authenticate.\nThe book Happy Git and GitHub for the useR has a wealth of information related to working with Git in R, and these instructions are based off of Chapter 9 Personal access token for HTTPS.\nWe will be using a Personal Access Token (PAT) in this course. For better security and long term use, we recommend taking the extra steps to set up SSH keys (check out Chapter 10 Set up Keys for SSH).\n\n\n\n\n\n\nSetting up your PAT\n\n\n\n\nRun usethis::create_github_token() in the Console.\nA new browser window should open up to GitHub, showing all the scopes options. You can review the scopes, but you don’t need to worry about which ones to select this time. Using create_github_token() automatically pre-selects some recommended scopes. Go ahead and scroll to the bottom and click “Generate Token”.\nCopy the generated token.\nBack in RStudio, run gitcreds::gitcreds_set() in the Console.\nPaste your PAT when the prompt asks for it.\nLast thing, run usethis::git_sitrep() in the Console to check your Git configuration and that you’ve successful stored your PAT.\n\n\n\nCongrats! Now you’ve setup your authentication you should be able to work with GitHub in RStudio now.", + "crumbs": [ + "Week 2", + "5  R and GitHub Setup" + ] + }, + { + "objectID": "session_06.html", + "href": "session_06.html", + "title": "6  Into to Git and GitHub", + "section": "", + "text": "Learning Objectives", + "crumbs": [ + "Week 2", + "6  Into to Git and GitHub" + ] + }, + { + "objectID": "session_06.html#learning-objectives", + "href": "session_06.html#learning-objectives", + "title": "6  Into to Git and GitHub", + "section": "", + "text": "Apply the principles of Git to track and manage changes of a project\nUtilize the Git workflow including pulling changes, staging modified files, committing changes, pulling again to incorporate remote changes, and pushing changes to a remote repository\nCreate and configure Git repositories using different workflows", + "crumbs": [ + "Week 2", + "6  Into to Git and GitHub" + ] } ] \ No newline at end of file diff --git a/public/2023-08-usgs/session_01.html b/public/2023-08-usgs/session_01.html index 3d0d0374..d7bd3609 100644 --- a/public/2023-08-usgs/session_01.html +++ b/public/2023-08-usgs/session_01.html @@ -2,7 +2,7 @@ - + @@ -24,6 +24,7 @@ div.csl-bib-body { } div.csl-entry { clear: both; + margin-bottom: 0em; } .hanging-indent div.csl-entry { margin-left:2em; @@ -67,7 +68,13 @@ "collapse-after": 3, "panel-placement": "start", "type": "textbox", - "limit": 20, + "limit": 50, + "keyboard-shortcut": [ + "f", + "/", + "s" + ], + "show-item-context": false, "language": { "search-no-results-text": "No results", "search-matching-documents-text": "matching documents", @@ -76,6 +83,7 @@ "search-more-match-text": "more match in this document", "search-more-matches-text": "more matches in this document", "search-clear-button-title": "Clear", + "search-text-placeholder": "", "search-detached-cancel-button-title": "Cancel", "search-submit-button-title": "Submit", "search-label": "Search" @@ -89,15 +97,15 @@
-
+
-
+

1  Successful Synthesis Science

@@ -123,14 +131,14 @@

1  -

-
  • +
  • +
    + + Week 1 + + + +
    + +
    • +
  • +
    + + Week 2 + + + +
    + +
    • -
    +
    @@ -236,7 +285,7 @@

    -
    Graphic adapted from Engingeering Ideas newsletter on Substack
    +
    Graphic adapted from Engingeering Ideas newsletter on Substack

    Data is everywhere and information is more accessible than ever, but how can we leverage both data and knowledge to further our understanding of a topic and turn those insights into meaningful action? This is where synthesis research shines.

    @@ -290,7 +339,7 @@

    1.3 NCEAS and Synthesis Science

    -

    +

    In 1995, the National Science Foundation (NSF) responded to the increasing calls by environmental researchers and professionals for interdisciplinary and transdisciplinary explanations, methods to connect science to applications, and ways to advance research technologies by creating NCEAS, the first synthesis center.

    @@ -303,7 +352,7 @@

    1.4.1 Ocean Health Index (OHI)

    -

    +

    The Ocean Health Index brought together a diverse group of experts including marine scientists, economists, policy experts, and more. This collaborative effort aimed to comprehensively assess the health of oceans worldwide by integrating data from various sources, including physical, biological, and socioeconomic factors.

    @@ -320,7 +369,7 @@

    1.4.2 State of Alaska’s Salmon and People (SASAP)

    -

    +

    The SASAP project was a partnership between NCEAS and Anchorage-based Nautilus Impact Investing to create an equitable decision-making platform for salmon management through information synthesis, collaboration, and stakeholder engagement.

    @@ -397,7 +446,7 @@

    +
    Carpenter, Stephen R., E. Virginia Armbrust, Peter W. Arzberger, F. Stuart Chapin, James J. Elser, Edward J. Hackett, Anthony R. Ives, et al. 2009. “Accelerate Synthesis in Ecology and Environmental Sciences.” BioScience 59 (8): 699–701. https://doi.org/10.1525/bio.2009.59.8.11.
    @@ -499,10 +548,9 @@

    2) { + container.appendChild(note.children[0].cloneNode(true)); + for (let i = 1; i < note.children.length; i++) { + const child = note.children[i]; + if (child.tagName === "P" && child.innerText === "") { + continue; + } else { + container.appendChild(child.cloneNode(true)); + break; + } + } + if (window.Quarto?.typesetMath) { + window.Quarto.typesetMath(container); + } + return container.innerHTML + } else { + if (window.Quarto?.typesetMath) { + window.Quarto.typesetMath(note); + } + return note.innerHTML; + } + } else { + // Remove any anchor links if they are present + const anchorLink = note.querySelector('a.anchorjs-link'); + if (anchorLink) { + anchorLink.remove(); + } + if (window.Quarto?.typesetMath) { + window.Quarto.typesetMath(note); + } + // TODO in 1.5, we should make sure this works without a callout special case + if (note.classList.contains("callout")) { + return note.outerHTML; + } else { + return note.innerHTML; + } + } + } + for (var i=0; i res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.getElementById(id); + if (note !== null) { + const html = processXRef(id, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + } else { + // See if we can fetch a full url (with no hash to target) + // This is a special case and we should probably do some content thinning / targeting + fetch(url) + .then(res => res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.querySelector('main.content'); + if (note !== null) { + // This should only happen for chapter cross references + // (since there is no id in the URL) + // remove the first header + if (note.children.length > 0 && note.children[0].tagName === "HEADER") { + note.children[0].remove(); + } + const html = processXRef(null, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + }, function(instance) { + }); } let selectedAnnoteEl; const selectorForAnnotation = ( cell, annotation) => { @@ -569,6 +745,7 @@

    { + elRect = undefined; + if (selectedAnnoteEl) { + selectCodeLines(selectedAnnoteEl); + } + }, 10) + ); + function throttle(fn, ms) { + let throttle = false; + let timer; + return (...args) => { + if(!throttle) { // first call gets through + fn.apply(this, args); + throttle = true; + } else { // all the others get throttled + if(timer) clearTimeout(timer); // cancel #2 + timer = setTimeout(() => { + fn.apply(this, args); + timer = throttle = false; + }, ms); + } + }; + } // Attach click handler to the DT const annoteDls = window.document.querySelectorAll('dt[data-target-cell]'); for (const annoteDlNode of annoteDls) { @@ -655,12 +858,12 @@

    - + Overview
    - + 2  Logic Model
    @@ -669,4 +872,5 @@

    - + @@ -48,7 +48,13 @@ "collapse-after": 3, "panel-placement": "start", "type": "textbox", - "limit": 20, + "limit": 50, + "keyboard-shortcut": [ + "f", + "/", + "s" + ], + "show-item-context": false, "language": { "search-no-results-text": "No results", "search-matching-documents-text": "matching documents", @@ -57,6 +63,7 @@ "search-more-match-text": "more match in this document", "search-more-matches-text": "more matches in this document", "search-clear-button-title": "Clear", + "search-text-placeholder": "", "search-detached-cancel-button-title": "Cancel", "search-submit-button-title": "Submit", "search-label": "Search" @@ -73,15 +80,15 @@
    -
    +
    -
    +

    2  Logic Model

    @@ -107,14 +114,14 @@

    2  -

    -
  • +
  • +
    + + Week 1 + + + +
    + +
    • +
  • +
    + + Week 2 + + + +
    + +
    • -
    +