Global Dynamic Rainfall-Induced Landslide Susceptibility Mapping Using Machine Learning

Abstract

Precipitation is the main factor that triggers landslides. Rainfall-induced landslide susceptibility mapping (LSM) is crucial for disaster prevention and disaster losses mitigation, though most studies are temporally ambiguous and on a regional scale. To better reveal landslide mechanisms and provide more accurate landslide susceptibility maps for landslide risk assessment and hazard prediction, developing a global dynamic LSM model is essential. In this study, we used Google Earth Engine (GEE) as the main data platform and applied three tree-based ensemble machine learning algorithms to construct global, dynamic rainfall-induced LSM models based on dynamic and static landslide influencing factors. The dynamic perspective is used in LSM: dynamic changes in landslide susceptibility can be identified on a daily scale. We note that Random Forest algorithm offers robust performance for accurate LSM (AUC = 0.975) and although the classification accuracy of LightGBM is the highest (AUC = 0.977), the results do not meet the sufficient conditions of a landslide susceptibility map. Combined with quantitative precipitation products, the proposed model can be used for the release of historical and predictive global dynamic landslide susceptibility information.