Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches

Autor(es)

Dias, Helen Cristina ; Hoelbling, Daniel ; Grohmann, Carlos Henrique

• Tipo de documento: Artigo Científico
• Fonte: GEOSCIENCES; v. 15, n. 3, p. 17-pg., 2025-02-20.

Resumo

Shallow landslides are one of the most common natural hazards in Brazil and worldwide. Susceptibility maps are powerful tools to analyze the spatial probability of shallow landslide occurrences. The outputs of susceptibility maps strongly depend on the type of landslide inventory used. The aim of this study is to examine the influence of different inventories on shallow landslide susceptibility modeling using the different methods LR, SVM, and XGBoost. Three different shallow landslide inventories were compiled following a single extreme rainfall event in the Ribeira Valley, S & atilde;o Paulo, Brazil. The results indicate that inventories generated through different landslide detection methods and imagery produce diverse susceptibility maps, as evidenced by the calculated Cohen's Kappa coefficient values (0.33-0.79). The agreement among the models varied depending on the specific model: LR exhibited the highest agreement (0.79), whereas SVM (0.36) and XGBoost (0.33) showed lower numbers. Conversely, the accuracy numbers suggest that XGBoost achieved the highest success rate in terms of AUC (85-78%), followed by SVM (82-76%), and LR (80-71%). Inventories obtained through different detection methods, using distinct datasets, can directly influence the susceptibility assessment, leading to varying classifications of the same area. These findings demonstrate the importance of well-established landslide mapping criteria. (AU)

• Processo FAPESP: 22/01534-8 - Criação e avaliação de inventários de escorregamentos rasos construídos a partir do método de Análise Orientada a Objetos (OBIA)
• Beneficiário: Helen Cristina Dias
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado
• Processo FAPESP: 23/11197-1 - Geomorfometria multi-escala na análise de movimentos de massa em São Sebastião (SP)
• Beneficiário: Carlos Henrique Grohmann de Carvalho
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 19/26568-0 - Sensoriamento remoto de alta resolução, deep learning e geomorfometria em análise de deslizamentos naturais e risco geológico
• Beneficiário: Carlos Henrique Grohmann de Carvalho
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 19/17261-8 - Análise de Inventário manuais e semi-automáticos de escorregamentos rasos e sua adequabilidade para utilização em modelos preditivos
• Beneficiário: Helen Cristina Dias
• Modalidade de apoio: Bolsas no Brasil - Doutorado