Optimal sample size and composition for crop classification with Sen2-Agri’s random forest classifier

dc.creatorSchulthess, U.
dc.creatorRodrigues, F.
dc.creatorTaymans, M.
dc.creatorBellemans, N.
dc.creatorBontemps, S.
dc.creatorOrtiz-Monasterio, I.
dc.creatorGerard, B.
dc.creatorDefourny, P.
dc.date2023-02-01T01:30:13Z
dc.date2023-02-01T01:30:13Z
dc.date2023
dc.date.accessioned2023-07-17T20:10:18Z
dc.date.available2023-07-17T20:10:18Z
dc.identifierhttps://hdl.handle.net/10883/22489
dc.identifier10.3390/rs15030608
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/7514233
dc.descriptionSen2-Agri is a software system that was developed to facilitate the use of multi-temporal satellite data for crop classification with a random forest (RF) classifier in an operational setting. It automatically ingests and processes Sentinel-2 and LandSat 8 images. Our goal was to provide practitioners with recommendations for the best sample size and composition. The study area was located in the Yaqui Valley in Mexico. Using polygons of more than 6000 labeled crop fields, we prepared data sets for training, in which the nine crops had an equal or proportional representation, called Equal or Ratio, respectively. Increasing the size of the training set improved the overall accuracy (OA). Gains became marginal once the total number of fields approximated 500 or 40 to 45 fields per crop type. Equal achieved slightly higher OAs than Ratio for a given number of fields. However, recall and F-scores of the individual crops tended to be higher for Ratio than for Equal. The high number of wheat fields in the Ratio scenarios, ranging from 275 to 2128, produced a more accurate classification of wheat than the maximal 80 fields of Equal. This resulted in a higher recall for wheat in the Ratio than in the Equal scenarios, which in turn limited the errors of commission of the non-wheat crops. Thus, a proportional representation of the crops in the training data is preferable and yields better accuracies, even for the minority crops.
dc.languageEnglish
dc.publisherMDPI
dc.relationhttps://hdl.handle.net/11529/10548637
dc.relationNutrition, health & food security
dc.relationPoverty reduction, livelihoods & jobs
dc.relationDigital Innovation
dc.relationSystems Transformation
dc.relationResilient Agrifood Systems
dc.relationCGIAR Research Program on Maize
dc.relationCGIAR Research Program on Wheat
dc.relationHenan Agricultural University
dc.relationCGIAR Trust Fund
dc.relationhttps://hdl.handle.net/10568/128426
dc.rightsCIMMYT manages Intellectual Assets as International Public Goods. The user is free to download, print, store and share this work. In case you want to translate or create any other derivative work and share or distribute such translation/derivative work, please contact CIMMYT-Knowledge-Center@cgiar.org indicating the work you want to use and the kind of use you intend; CIMMYT will contact you with the suitable license for that purpose
dc.rightsOpen Access
dc.source3
dc.source15
dc.source2072-4292
dc.sourceRemote Sensing
dc.source608
dc.subjectAGRICULTURAL SCIENCES AND BIOTECHNOLOGY
dc.subjectCrop Classification
dc.subjectRandom Forest
dc.subjectSample Size
dc.subjectCROPS
dc.subjectFORESTS
dc.subjectMACHINE LEARNING
dc.subjectAGRICULTURE
dc.subjectREMOTE SENSING
dc.subjectSustainable Agrifood Systems
dc.titleOptimal sample size and composition for crop classification with Sen2-Agri’s random forest classifier
dc.typeArticle
dc.typePublished Version
dc.coverageMexico
dc.coverageBasel (Switzerland)


Este ítem pertenece a la siguiente institución