Use este identificador para citar ou linkar para este item: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1185940
Registro completo de metadados
Campo DCValorIdioma
dc.contributor.authorPARREIRAS, T. C.
dc.contributor.authorBOLFE, E. L.
dc.date.accessioned2026-03-31T13:52:34Z-
dc.date.available2026-03-31T13:52:34Z-
dc.date.created2026-03-31
dc.date.issued2025
dc.identifier.citationIn: WORKSHOP CIENTÍFICO DO CENTRO DE CIÊNCIA PARA O DESENVOLVIMENTO EM AGRICULTURA DIGITAL – SEMEAR DIGITAL, 2., 2025, Campinas. Anais [...]. Piracicaba: ESALQ/USP, 2025. p. 397-404.
dc.identifier.isbn978-85-86481-94-9
dc.identifier.urihttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1185940-
dc.descriptionThis study explores the potential of Harmonized Landsat Sentinel-2 (HLS) data for detailed agricultural mapping in diversified farming regions of São Paulo, Brazil. Focusing on Casa Branca and Caconde, the research integrates multitemporal HLS imagery (2021–2024) to perform crop classifications at multiple levels. In Caconde, high-resolution temporal data (2–4 day revisit) enabled strong performance in distinguishing perennial crops, particularly coffee, which achieved an average sensitivity of 0.97 and specificity of 0.91. Phenological stages of coffee, such as Producing and Newly Planted, were reliably mapped, while Stumping and Skeletoning showed lower consistency. In Casa Branca, six field campaigns supported the construction of a robust training dataset across up to nine growing seasons. Integrating Landsat 9 into the HLS collection more than doubled temporal resolution over the study period, enhancing model accuracy and phenological tracking. Future work will focus on model transferability across time and space and on evaluating the relative performance of HLS versus individual Landsat and Sentinel data.
dc.language.isoeng
dc.rightsopenAccess
dc.subjectAprendizado de máquina
dc.subjectDiversidade de culturas
dc.subjectProdção de café
dc.subjectHarmonized Landsat Sentinel-2
dc.subjectMachine learning
dc.subjectCrop diversity
dc.subjectCoffee production
dc.titleThe role of Landsat and Sentinel-2 data harmonization in monitoring agricultural dynamics on smallholder farming regions.
dc.typeArtigo em anais e proceedings
dc.subject.thesagroAgricultura
dc.subject.thesagroIrrigação
dc.subject.nalthesaurusAgriculture
dc.subject.nalthesaurusIrrigation
dc.description.notesOrganização: Silvia Maria Fonseca Silveira Massruhá, Durval Dourado Neto, Luciana Alvim Santos Romani, Jayme Garcia Arnal Barbedo, Édson Luis Bolfe, Ivan Bergier, Maria Angelica de Andrade Leite, Vitor Del Alamo Guarda, Catarina Barbosa Careta.
riaa.ainfo.id1185940
riaa.ainfo.lastupdate2026-03-31
dc.contributor.institutionTAYA CRISTO PARREIRAS, UNIVERSIDADE ESTADUAL DE CAMPINAS; EDSON LUIS BOLFE, CNPTIA.
Aparece nas coleções:Artigo em anais de congresso (CNPTIA)

Arquivos associados a este item:
Arquivo TamanhoFormato 
AA-Role-Landsat-Workshop-2025.pdf438,4 kBAdobe PDFVisualizar/Abrir
Mostrar registro simples do item Visualizar estatísticas

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace