Cotton yield map prediction using Sentinel-2 satellite imagery in the Brazilian Cerrado production system.

Vista sencilla de ítem
dc.contributorCARLOS MANOEL PEDRO VAZ, CNPDIA; EDNALDO JOSE FERREIRA, CNPDIA; EDUARDO ANTONIO SPERANZA, CNPTIA; JULIO CEZAR FRANCHINI DOS SANTOS, CNPSO; JOAO DE MENDONCA NAIME, CNPDIA; RICARDO YASSUSHI INAMASU, CNPDIA; IVANI DE OLIVEIRA NEGRAO LOPES, CNPSO; SÉRGIO DAS CHAGAS, AMAGGI GROUP; MATHIAS XAVIER SCHELP, BOSCH BRAZIL; LEONARDO VECCHI, BOSCH BRAZIL; RAFAEL GALBIERI, INSTITUTO MATO-GROSSENSE DO ALGODÃO.
dc.creatorVAZ, C. M. P.
dc.creatorFERREIRA, E. J.
dc.creatorSPERANZA, E. A.
dc.creatorFRANCHINI, J. C.
dc.creatorNAIME, J. de M.
dc.creatorINAMASU, R. Y.
dc.creatorLOPES, I. de O. N.
dc.creatorCHAGAS, S. das
dc.creatorSCHELP, M. X.
dc.creatorVECCHI, L.
dc.creatorGALBIERI, R.
dc.date2026-05-18T13:49:23Z
dc.date2026-05-18T13:49:23Z
dc.date2026-05-15
dc.date2025
dc.date.accessioned2026-07-07T04:29:56Z
dc.descriptionYield maps from combine harvesters are essential in precision agriculture for capturing within-field variability and guiding variable-rate input management. However, in largescale systems such as those in the Brazilian Cerrado, these maps are often inconsistent due to calibration errors, use of multiple harvesters, and complex post-processing. Orbital remote sensing offers an alternative by providing consistent vegetation index (VI) data for crop monitoring and yield estimation. This study developed regression models relating Sentinel-2 VIs (EVI, TVI, NDVI, and NDRE) to cotton yield data obtained from combine harvesters across 30 commercial plots in Mato Grosso, Brazil, over six cropping seasons (2019–2024), totaling 76 plot-season datasets. Vegetation indices were grouped into 15-day intervals based on days after sowing, and a logistic growth function was applied in the regression modeling. Model performance evaluated using 15 independent plot-seasons showed good pixel-level accuracy, with RMSE of 0.695 t ha−1 and R2 of 0.78, with EVI performing slightly better. At the plot scale, mean yield predictions across all datasets achieved an RMSE of 0.41 t ha−1, reflecting the higher reliability of module-based yield measurements. These results demonstrate the potential of Sentinel-2 VIs combined with logistic regression to predict cotton yields in the Cerrado, complementing or replacing harvester-based monitoring.
dc.identifierAgriEngineering, v. 7, n. 11, 390, Nov. 2025.
dc.identifier2624-7402
dc.identifierhttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1186887
dc.identifierhttps://doi.org/10.3390/ agriengineering7110390
dc.identifier.urihttp://hdl.handle.net/123456789/463223
dc.languageeng
dc.rightsopenAccess
dc.subjectModelo de regressão
dc.subjectMapas
dc.subjectRegression model
dc.subjectAgricultura de Precisão
dc.subjectSensoriamento Remoto
dc.subjectAlgodão
dc.subjectPrecision agriculture
dc.subjectRemote sensing
dc.subjectYield mapping
dc.subjectCotton
dc.titleCotton yield map prediction using Sentinel-2 satellite imagery in the Brazilian Cerrado production system.
dc.typeArtigo de periódico

Archivos

Colecciones

Embrapa Instrumentación (CNPDIA)