The impact of reference data errors on land-cover classifiers.

Errors in thematically detailed land-cover maps have large consequences for downstream applications. Moreover, simulation-based studies suggest that land-cover classifiers are sensitive to errors in reference data. We (1) quantified the expected error from field interpretation of land-cover types; (...

Descripción completa

Detalles Bibliográficos
Publicado en:Norwegian Journal of Geography Vol. 79; no. 4; pp. 174 - 189
Autores principales: Naas, Adam Eindride, Horvath, Peter, Halvorsen, Rune, Sivertsen, Bendik, Bryn, Anders
Formato: Artículo
Publicado: Taylor & Francis Ltd Sep2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=195343892&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 195343892
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00291951
        9DP
      jtl: Norwegian Journal of Geography
      issn: 00291951
      maglogo: N
    pubinfo:
      dt: Sep2025
      vid: 79
      iid: 4
      pid: 377
      pub: Taylor & Francis Ltd
    artinfo:
      ui:
        195343892
        10.1080/00291951.2026.2661590
      ppf: 174
      ppct: 15
      formats:
      tig:
        atl: The impact of reference data errors on land-cover classifiers.
      aug:
        au:
          Naas, Adam Eindride
          Horvath, Peter
          Halvorsen, Rune
          Sivertsen, Bendik
          Bryn, Anders
        affil:
          Natural History Museum, University of Oslo, Oslo, Norway
          Department of Nature Consultancy, Sállir Natur AS, Harstad, Norway
          Division of Survey and Statistics, Norwegian Institute of Bioeconomy Research, Ås, Norway
      su:
        Data quality
        Classification algorithms
        Thematic maps
        Error analysis in mathematics
      sug:
        subj:
          Data quality
          Classification algorithms
          Thematic maps
          Error analysis in mathematics
      keyword:
        error sensitivity
        field data
        ground truth
        remote sensing
        vegetation mapping
      ab: Errors in thematically detailed land-cover maps have large consequences for downstream applications. Moreover, simulation-based studies suggest that land-cover classifiers are sensitive to errors in reference data. We (1) quantified the expected error from field interpretation of land-cover types; (2) the sensitivity of classifiers to reference data errors; and (3) the error transferred from reference data to classifiers. Lastly, we (4) recommended strategies to reduce errors. The study area was mapped by 12 field interpreters divided into three equal-sized experience-level groups. The field-based land-cover maps were aggregated to three thematic resolutions and used to train 6804 land-cover classifiers by varying inputs, algorithm, and hyperparameter values. Separately from the first field campaign, four field interpreters classified validation data points, which were used to quantify error for each field interpreter and land-cover classifier, as the proportion of incorrectly classified validation points. We observed (1) generally high and varying levels of interpreter error; (2) a strong relationship between interpreter and classifier error; and (3) a net positive transfer of errors from reference data to classifiers. Because classifier error seems largely driven by interpreter error at the levels commonly observed in thematically detailed land-cover mapping, we (4) recommend strategies to reduce interpreter error before modelling.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N