Integrating InSAR Observables and Multiple Geological Factors for Landslide Susceptibility Assessment

Due to extreme weather, researchers are constantly putting their focus on prevention and mitigation for the impact of disasters in order reduce loss life property. The disaster associated with slope failures is among most challenging ones due multiple driving factors complicated mechanisms between them. In this study, a modern space remote sensing technology, InSAR, was introduced as direct observable dynamics. InSAR-derived displacement fields other situ geological topographical were integrated, correlations landslide susceptibility analyzed. Moreover, machine learning approaches applied goal construct an optimal model these susceptibility. Two case studies performed mountainous areas Taiwan Island performance evaluated by confusion matrix. numerical results revealed that different approaches, Random Forest outperformed others, average accuracy higher than 80%. More importantly, inclusion InSAR data resulted improved all training which first be reported scientific literature. words, proposed approach provides novel integrated technique enables highly reliable analysis so subsequent management or reinforcement can better planned.