作者: Majid Shadman Roodposhti , Jagannath Aryal , Himan Shahabi , Taher Safarrad
DOI: 10.3390/E18100343
关键词: Statistical model 、 Receiver operating characteristic 、 Information theory 、 Decision tree 、 Fuzzy logic 、 Artificial neural network 、 Support vector machine 、 Data mining 、 Landslide
摘要: Assessing Landslide Susceptibility Mapping (LSM) contributes to reducing the risk of living with landslides. Handling vagueness associated LSM is a challenging task. Here we show application hybrid GIS-based LSM. The approach embraces fuzzy membership functions (FMFs) in combination Shannon entropy, well-known information theory-based method. Nine landslide-related criteria, along an inventory landslides containing 108 recent and historic landslide points, are used prepare susceptibility map. A random split into training (≈70%) testing (≈30%) samples for validation model. study area—Izeh—is located Khuzestan province Iran, highly susceptible zone. performance method evaluated using receiver operating characteristics (ROC) curves area under curve (AUC). proposed AUC 0.934 superior multi-criteria evaluation approaches subjective scheme this research comparison previous same dataset through extended value 0.894, was built on basis decision makers’ area.