Assessing Machine Learning Models on Temporal and Multi-Sensor Data for Mapping Flooded Areas

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorNegri, Rogério Galante-
Autor(es): dc.creatorda Costa, Fernanda Dácio-
Autor(es): dc.creatorda Silva Andrade Ferreira, Bruna-
Autor(es): dc.creatorRodrigues, Matheus Wesley-
Autor(es): dc.creatorBankole, Abayomi-
Autor(es): dc.creatorCasaca, Wallace-
Data de aceite: dc.date.accessioned2025-08-21T21:09:01Z-
Data de disponibilização: dc.date.available2025-08-21T21:09:01Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2025-04-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1111/tgis.70028-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/298433-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/298433-
Descrição: dc.descriptionNatural disasters, particularly floods, are escalating in frequency and intensity, disproportionately impacting economically disadvantaged populations and leading to substantial economic losses. This study leverages temporal and multi-sensor data from Synthetic Aperture Radar (SAR) and multispectral sensors on Sentinel satellites to evaluate a range of supervised and semi-supervised machine learning (ML) models. These models, combined with feature extraction and selection techniques, effectively process large datasets to map flood-affected areas. Case studies in Brazil and Mozambique demonstrate the efficacy of the methods. The Support Vector Machine (SVM) with an RBF kernel, despite achieving high kappa values, tended to overestimate flood extents. In contrast, the Classification and Regression Trees (CART) and Cluster Labeling (CL) methods exhibited superior performance both qualitatively and quantitatively. The Gaussian Mixture Model (GMM), however, showed high sensitivity to input data and was the least effective among the methods tested. This analysis highlights the critical need for careful selection of ML models and preprocessing techniques in flood mapping, facilitating rapid, data-driven decision-making processes.-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionInstitute of Science and Technology São Paulo State University, São Paulo-
Descrição: dc.descriptionGraduate Program in Natural Disasters São Paulo State University Brazilian Center for Early Warning and Monitoring for Natural Disasters, São Paulo-
Descrição: dc.descriptionGraduate Program in Civil and Environmental Engineering São Paulo State University, São Paulo-
Descrição: dc.descriptionInstitute of Biosciences Letters and Exact Sciences São Paulo State University, São Paulo-
Descrição: dc.descriptionInstitute of Science and Technology São Paulo State University, São Paulo-
Descrição: dc.descriptionGraduate Program in Natural Disasters São Paulo State University Brazilian Center for Early Warning and Monitoring for Natural Disasters, São Paulo-
Descrição: dc.descriptionGraduate Program in Civil and Environmental Engineering São Paulo State University, São Paulo-
Descrição: dc.descriptionInstitute of Biosciences Letters and Exact Sciences São Paulo State University, São Paulo-
Descrição: dc.descriptionFAPESP: 2021/01305-6-
Descrição: dc.descriptionFAPESP: 2021/03328-3-
Descrição: dc.descriptionCNPq: 305220/2022-5-
Descrição: dc.descriptionCNPq: 316228/2021-4-
Idioma: dc.languageen-
Relação: dc.relationTransactions in GIS-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectclassification-
Palavras-chave: dc.subjectdigital image analysis-
Palavras-chave: dc.subjectflooding-
Palavras-chave: dc.subjectmachine learning-
Palavras-chave: dc.subjectremote sensing-
Título: dc.titleAssessing Machine Learning Models on Temporal and Multi-Sensor Data for Mapping Flooded Areas-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.