JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Medical Biometry, Informatics and Epidemiology, Medical Faculty, University of Bonn, Venusberg-Campus 1, 53127, Bonn, Germany", 
          "id": "http://www.grid.ac/institutes/grid.10388.32", 
          "name": [
            "Department of Medical Biometry, Informatics and Epidemiology, Medical Faculty, University of Bonn, Venusberg-Campus 1, 53127, Bonn, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Welchowski", 
        "givenName": "Thomas", 
        "id": "sg:person.01072763633.64", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01072763633.64"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "U.S. Geological Survey (USGS) Eastern Ecological Science Center at the Leetown Research Laboratory, 11649, Leetown Rd, 25430, Kearneysville, WV, USA", 
          "id": "http://www.grid.ac/institutes/grid.2865.9", 
          "name": [
            "U.S. Geological Survey (USGS) Eastern Ecological Science Center at the Leetown Research Laboratory, 11649, Leetown Rd, 25430, Kearneysville, WV, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Maloney", 
        "givenName": "Kelly O.", 
        "id": "sg:person.014030242625.51", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014030242625.51"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "U.S. Environmental Protection Agency Office of Water Washington, 20460, Washington, DC, USA", 
          "id": "http://www.grid.ac/institutes/grid.418698.a", 
          "name": [
            "U.S. Environmental Protection Agency Office of Water Washington, 20460, Washington, DC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mitchell", 
        "givenName": "Richard", 
        "id": "sg:person.015320662343.00", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015320662343.00"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Medical Biometry, Informatics and Epidemiology, Medical Faculty, University of Bonn, Venusberg-Campus 1, 53127, Bonn, Germany", 
          "id": "http://www.grid.ac/institutes/grid.10388.32", 
          "name": [
            "Department of Medical Biometry, Informatics and Epidemiology, Medical Faculty, University of Bonn, Venusberg-Campus 1, 53127, Bonn, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Schmid", 
        "givenName": "Matthias", 
        "id": "sg:person.0745220772.74", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0745220772.74"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s10750-008-9655-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009225584", 
          "https://doi.org/10.1007/s10750-008-9655-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1003442013650", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038558926", 
          "https://doi.org/10.1023/a:1003442013650"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10651-010-0158-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046581893", 
          "https://doi.org/10.1007/s10651-010-0158-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-0-387-84858-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032573094", 
          "https://doi.org/10.1007/978-0-387-84858-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1010933404324", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024739340", 
          "https://doi.org/10.1023/a:1010933404324"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-87479-9_34", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005796247", 
          "https://doi.org/10.1007/978-3-540-87479-9_34"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2105-8-25", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019863657", 
          "https://doi.org/10.1186/1471-2105-8-25"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11634-016-0276-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046420813", 
          "https://doi.org/10.1007/s11634-016-0276-4"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2021-10-28", 
    "datePublishedReg": "2021-10-28", 
    "description": "Statistical modeling of ecological data is often faced with a large number of variables as well as possible nonlinear relationships and higher-order interaction effects. Gradient boosted trees (GBT) have been successful in addressing these issues and have shown a good predictive performance in modeling nonlinear relationships, in particular in classification settings with a categorical response variable.  They also tend to be robust against outliers. However, their black-box nature makes it difficult to interpret these models. We introduce several recently developed statistical tools to the environmental research community in order to advance interpretation of these black-box models. To analyze the properties of the tools, we applied gradient boosted trees to investigate biological health of streams within the contiguous USA, as measured by a benthic macroinvertebrate biotic index. Based on these data and a simulation study, we demonstrate the advantages and limitations of partial dependence plots (PDP), individual conditional expectation (ICE) curves and accumulated local effects (ALE) in their ability to identify covariate\u2013response relationships. Additionally, interaction effects were quantified according to interaction strength (IAS) and Friedman\u2019s H2\\documentclass[12pt]{minimal}\n\t\t\t\t\\usepackage{amsmath}\n\t\t\t\t\\usepackage{wasysym}\n\t\t\t\t\\usepackage{amsfonts}\n\t\t\t\t\\usepackage{amssymb}\n\t\t\t\t\\usepackage{amsbsy}\n\t\t\t\t\\usepackage{mathrsfs}\n\t\t\t\t\\usepackage{upgreek}\n\t\t\t\t\\setlength{\\oddsidemargin}{-69pt}\n\t\t\t\t\\begin{document}$$H^2$$\\end{document} statistic. Interpretable machine learning techniques are useful tools to open the black-box of gradient boosted trees in the environmental sciences. This finding is supported by our case study on the effect of impervious surface on the benthic condition, which agrees with previous results in the literature. Overall, the most important variables were ecoregion, bed stability, watershed area, riparian vegetation and catchment slope. These variables were also present in most identified interaction effects. In conclusion, graphical tools (PDP, ICE, ALE) enable visualization and easier interpretation of GBT but should be supported by analytical statistical measures. Future methodological research is needed to investigate the properties of interaction tests.\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0Supplementary materials accompanying this paper appear on-line.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s13253-021-00479-7", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1134206", 
        "issn": [
          "1085-7117", 
          "1537-2693"
        ], 
        "name": "Journal of Agricultural, Biological and Environmental Statistics", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "27"
      }
    ], 
    "keywords": [
      "categorical response variables", 
      "partial dependence plots", 
      "covariate-response relationships", 
      "interaction strength", 
      "Black-box Machine Learning Models", 
      "black-box models", 
      "ecological interpretability", 
      "statistical modeling", 
      "higher order interaction effects", 
      "expectation curve", 
      "statistical tools", 
      "nonlinear relationship", 
      "statistical measures", 
      "simulation study", 
      "response variables", 
      "black-box nature", 
      "environmental research community", 
      "machine learning models", 
      "supplementary material", 
      "good predictive performance", 
      "previous results", 
      "easy interpretation", 
      "future methodological research", 
      "graphical tool", 
      "classification setting", 
      "predictive performance", 
      "interpretable machine", 
      "possible nonlinear relationship", 
      "methodological research", 
      "model", 
      "variables", 
      "large number", 
      "statistics", 
      "gradient", 
      "outliers", 
      "properties", 
      "environmental science", 
      "learning model", 
      "modeling", 
      "ecological data", 
      "interaction effects", 
      "interpretability", 
      "tool", 
      "technique", 
      "GBT", 
      "macroinvertebrate biotic index", 
      "useful tool", 
      "interpretation", 
      "stability", 
      "case study", 
      "order", 
      "curves", 
      "number", 
      "research community", 
      "important variables", 
      "machine", 
      "trees", 
      "performance", 
      "advantages", 
      "data", 
      "conditions", 
      "science", 
      "Friedman", 
      "results", 
      "effect", 
      "local effects", 
      "nature", 
      "surface", 
      "lines", 
      "limitations", 
      "slope", 
      "strength", 
      "literature", 
      "bed stability", 
      "streams", 
      "materials", 
      "plots", 
      "measures", 
      "contiguous USA", 
      "issues", 
      "relationship", 
      "visualization", 
      "setting", 
      "study", 
      "index", 
      "area", 
      "research", 
      "test", 
      "ability", 
      "watershed area", 
      "conclusion", 
      "interaction test", 
      "impervious surfaces", 
      "catchment slope", 
      "benthic conditions", 
      "community", 
      "USA", 
      "findings", 
      "riparian vegetation", 
      "vegetation", 
      "biotic indices", 
      "biological health", 
      "ecoregions", 
      "health", 
      "paper"
    ], 
    "name": "Techniques to Improve Ecological Interpretability of Black-Box Machine Learning Models", 
    "pagination": "175-197", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1142240872"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s13253-021-00479-7"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s13253-021-00479-7", 
      "https://app.dimensions.ai/details/publication/pub.1142240872"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-05-20T07:39", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220519/entities/gbq_results/article/article_903.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s13253-021-00479-7"
  }
]

Download the RDF metadata as:  json-ld nt turtle xml License info

This table displays all metadata directly associated to this object as RDF triples.

222 TRIPLES      22 PREDICATES      138 URIs      122 LITERALS      6 BLANK NODES