Use este identificador para citar ou linkar para este item: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1183257
Registro completo de metadados
Campo DCValorIdioma
dc.contributor.authorMAGALHÃES, I. A. L.
dc.contributor.authorSANO, E. E.
dc.contributor.authorBOLFE, E. L.
dc.contributor.authorSILVA, G. B. S. da
dc.date.accessioned2025-12-30T11:48:48Z-
dc.date.available2025-12-30T11:48:48Z-
dc.date.created2025-12-30
dc.date.issued2026
dc.identifier.citationLand, v. 15, n. 1, 53, Jan. 2026.
dc.identifier.issn2073-445X
dc.identifier.urihttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1183257-
dc.descriptionFarmland abandonment is becoming a growing land use challenge in the Brazilian Cerrado, yet its extent, spatial distribution, and underlying drivers remain poorly understood. This study addresses the following question: Can deep learning methods reliably identify abandoned farmlands in tropical savanna environments using multispectral satellite images? To answer this question, we used a Fully Connected Neural Network (FCNN) classifier to map abandoned farmlands in the municipality of Buritizeiro, Minas Gerais State, Brazil, using Sentinel-2 images acquired in 2018 and 2022. Seven land use and land cover (LULC) classes were mapped using visible and near-infrared bands, spectral indices, spectral mixture components, and principal components as input parameters for the CNN. The LULC map for 2022 achieved high classification performance (overall accuracy = 94.7%; Kappa coefficient = 0.93). Agricultural areas classified in 2018 as annual croplands, cultivated pastures, eucalyptus plantations, or harvested eucalyptus that transitioned to grasslands or shrublands in 2022 were considered abandoned. Based on this definition, we identified 13,147 hectares of abandoned land in 2022, representing 4.7% of the municipality’s agricultural area in 2018. Most abandoned areas corresponded to eucalyptus plantations established for charcoal production. This study provides the first deep learning-based assessment of farmland abandonment in the Cerrado. Our findings demonstrated the potential of FCNN classifiers for detecting abandoned farmlands in this biome and provide important contribution for public policies focused on ecological restoration, carbon sequestration, and sustainable agricultural planning.
dc.language.isoeng
dc.rightsopenAccess
dc.subjectCobertura da terra
dc.subjectSavana tropical
dc.subjectAprendizado profundo
dc.subjectRedes neurais
dc.subjectTropical savanna
dc.subjectDeep learning
dc.titlePutting abandoned farmlands in the legend of land use and land cover maps of the Brazilian tropical savanna.
dc.typeArtigo de periódico
dc.subject.thesagroSensoriamento Remoto
dc.subject.thesagroUso da Terra
dc.subject.nalthesaurusRemote sensing
dc.subject.nalthesaurusLand use
dc.subject.nalthesaurusLand cover
dc.description.notesNa publicação: Gustavo Bayma.
riaa.ainfo.id1183257
riaa.ainfo.lastupdate2025-12-30
dc.identifier.doihttps://doi.org/10.3390/land15010053
dc.contributor.institutionIVO AUGUSTO LOPES MAGALHÃES, UNIVERSIDADE DE BRASÍLIA; EDSON EYJI SANO, CPAC; EDSON LUIS BOLFE, CNPTIA; GUSTAVO BAYMA SIQUEIRA DA SILVA, CNPMA.
Aparece nas coleções:Artigo em periódico indexado (CPAC)

Arquivos associados a este item:
Arquivo TamanhoFormato 
Putting-abandoned.pdf37,32 MBAdobe PDFVisualizar/Abrir
Mostrar registro simples do item Visualizar estatísticas

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace