Spatial prediction of rainfall-induced shallow landslides using hybrid integration approach of Least-Squares Support Vector Machines and differential evolution optimization: a case study in Central Vietnam

摘要: ABSTRACTThis study represents a hybrid intelligence approach based on the differential evolution optimization and Least-Squares Support Vector Machines for shallow landslide prediction, named as DE–LSSVMSLP. The LSSVM is used to establish prediction model whereas DE adopted search optimal tuning parameters of model. In this research, GIS database with 129 historical records in Quy Hop area (Central Vietnam) has been collected receiver operating characteristic (ROC) curve under (AUC) were assess performance newly constructed Experimental results show that proposed high performances approximately 82% AUCs both training validating datasets. model’s compared those obtained from other methods, Machines, Multilayer Perceptron Neural Networks, J48 Decision Trees. result comparison demonstrates DE–LSSV...