Spatiotemporal prediction of rainfall erosivity by machine learning in southeastern Brazil

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.creatorSouza, Cristiano Marcelo Pereira de-
Autor(es): dc.creatorVeloso, Gustavo Vieira-
Autor(es): dc.creatorMello, Carlos Rogério de-
Autor(es): dc.creatorRibeiro, Ricardo Pires-
Autor(es): dc.creatorSilva, Lucas Augusto Pereira da-
Autor(es): dc.creatorLeite, Marcos Esdras-
Autor(es): dc.creatorFernandes Filho, Elpídio Inácio-
Data de aceite: dc.date.accessioned2026-02-09T12:35:50Z-
Data de disponibilização: dc.date.available2026-02-09T12:35:50Z-
Data de envio: dc.date.issued2022-07-14-
Data de envio: dc.date.issued2022-07-14-
Data de envio: dc.date.issued2022-04-
Fonte completa do material: dc.identifierhttps://repositorio.ufla.br/handle/1/50608-
Fonte completa do material: dc.identifierhttps://doi.org/10.1080/10106049.2022.2060318-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/capes/1164479-
Descrição: dc.descriptionThe spatiotemporal dynamic of rainfall erosivity is essential for environmental studies and guidance to control erosion. The purpose of this study is to assess rainfall erosivity (monthly and annual), testing machine learning algorithms aided by a covariate bank for spatial prediction of rainfall erosivity in Southeastern Brazil. The modeling tested Random Forest-RF, Cubist, Support Vector Machine, Earth, and Linear Model, associated with 154 covariates (topographic, climatic, and vegetation data). However, we apply the cut-off correlation function (findcorrelation) and feature selection algorithm (Recursive Feature Elimination—RFE) to select strong covariates. Our results show that the RF algorithm was more efficient in modeling (R2 values between 0.29 and 0.82), whit the best metrics in the low rainfall period (winter). The modeling showed fluidity by selecting only 43 significant covariates due to the findcorrelation and RFE functions. The most important and frequent covariates in spatial modeling were coordinates, water deficit, topographical, and climatic data. In general, the spatial results show that the dynamics of rainfall erosivity is strongly affected by factors of air mass circulation, relief, and geographic position. Our approach is promising as it is a method capable of estimating rainfall erosivity in unsampled areas, capturing information from significant spatial covariates.-
Idioma: dc.languageen-
Publicador: dc.publisherTaylor & Francis Group-
Direitos: dc.rightsrestrictAccess-
???dc.source???: dc.sourceGeocarto International-
Palavras-chave: dc.subjectRainfall intensity-
Palavras-chave: dc.subjectRandom Forest-
Palavras-chave: dc.subjectClimatic heterogeneity-
Palavras-chave: dc.subjectPrecipitation intensity-
Palavras-chave: dc.subjectIntensidade da chuva-
Palavras-chave: dc.subjectFloresta aleatória-
Palavras-chave: dc.subjectHeterogeneidade climática-
Palavras-chave: dc.subjectErosividade da chuva-
Palavras-chave: dc.subjectPredição espaço-temporal-
Título: dc.titleSpatiotemporal prediction of rainfall erosivity by machine learning in southeastern Brazil-
Tipo de arquivo: dc.typeArtigo-
Aparece nas coleções:Repositório Institucional da Universidade Federal de Lavras (RIUFLA)

Não existem arquivos associados a este item.