Comparison of LiDAR- and UAV-derived data for landslide susceptibility mapping using Random Forest algorithm

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorMCTI-
Autor(es): dc.contributorUFRGS - Federal University of Rio Grande do Sul-
Autor(es): dc.contributorUniversity of Algarve-
Autor(es): dc.creatorFrança Pereira, Felicia-
Autor(es): dc.creatorSussel Gonçalves Mendes, Tatiana-
Autor(es): dc.creatorJorge Coelho Simões, Silvio-
Autor(es): dc.creatorRoberto Magalhães de Andrade, Márcio-
Autor(es): dc.creatorLuiz Lopes Reiss, Mário-
Autor(es): dc.creatorFortes Cavalcante Renk, Jennifer-
Autor(es): dc.creatorCorreia da Silva Santos, Tatiany-
Data de aceite: dc.date.accessioned2025-08-21T15:24:19Z-
Data de disponibilização: dc.date.available2025-08-21T15:24:19Z-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-03-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1007/s10346-022-02001-7-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/246684-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/246684-
Descrição: dc.descriptionEarthquakes, extreme rainfall, or human activity can all cause landslides. Several landslides occur each year around the world, often resulting in casualties and economic consequences. Landslide susceptibility mapping is considered to be the main technique for predicting the likelihood of an event based on the characteristics of the physical environment. Digital Terrain Model (DTM) is one of the fundamental data of modeling and is used to derive important conditional factors for detailed scale landslide susceptibility analyses. With this in mind, this study aimed to compare landslide susceptibility maps generated by Random Forest (RF) machine learning algorithm with data from Light Detection and Range (LiDAR) and Unmanned Aerial Vehicle (UAV). To this end, the performance achieved in prediction was evaluated using statistical evaluation measures based on training and validation datasets. The obtained results showed that the accuracy of both models is greater than 0.70, the area under the curve (AUC) is greater than 0.80, and the model generated from the LiDAR data is more accurate. The results also showed that the data from UAV have potential to use in landslide susceptibility mapping on an intra-urban scale, contributing to studies in risk areas without available data.-
Descrição: dc.descriptionFinanciadora de Estudos e Projetos-
Descrição: dc.descriptionGraduate Program in Natural Disasters UNESP/CEMADEN, Estrada Doutor Altino Bondesan, São Paulo-
Descrição: dc.descriptionDepartment of Environmental Engineering Institute of Science and Technology São Paulo State University - Unesp, Estrada Doutor Altino Bondesan, São Paulo-
Descrição: dc.descriptionNational Center for Monitoring and Early Warning of Natural Disasters - CEMADEN MCTI, Estrada Doutor Altino Bondesan, São Paulo-
Descrição: dc.descriptionLAFOTO - Laboratory of Photogrammetry Research Department of Geodesy UFRGS - Federal University of Rio Grande do Sul, Av. Bento Gonçalves, Rio Grande do Sul-
Descrição: dc.descriptionCenter for Marine and Environmental Research - CIMA University of Algarve, Estr. da Penha-
Descrição: dc.descriptionGraduate Program in Natural Disasters UNESP/CEMADEN, Estrada Doutor Altino Bondesan, São Paulo-
Descrição: dc.descriptionDepartment of Environmental Engineering Institute of Science and Technology São Paulo State University - Unesp, Estrada Doutor Altino Bondesan, São Paulo-
Descrição: dc.descriptionFinanciadora de Estudos e Projetos: 0304/16-
Formato: dc.format579-600-
Idioma: dc.languageen-
Relação: dc.relationLandslides-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectDTM-
Palavras-chave: dc.subjectLandslide susceptibility model-
Palavras-chave: dc.subjectLiDAR-
Palavras-chave: dc.subjectRandom Forest-
Palavras-chave: dc.subjectUAV-
Título: dc.titleComparison of LiDAR- and UAV-derived data for landslide susceptibility mapping using Random Forest algorithm-
Tipo de arquivo: dc.typevídeo-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.