Machine learning-based approach for landslide susceptibility mapping using multimodal data

In this work, a practical Machine Learning (ML) approach is proposed to produce Landslide Susceptibility Mapping (LSM) by exploiting multiple data sources. In contrast to conventional ML-based methods that consider a large number of factors, the proposed method fuses only three carefully selected factors, namely inventory Landslide and Debris Flow (LDF) data, rainfall data and forest change information to model and predict landslides and debris flow. More specifically, a Global Deforestation Detection Algorithm (GDDA) based on Synthetic Aperture Radar (SAR) and Convolutional Neural Network (CNN) are first developed to generate a hazard map by identifying areas of substantial forest changes. Capitalizing on rainfall forecast data derived from the Doppler Weather Radar (DWR) over the areas of severe deforestation detected by GDDA, an SVM-based classifier is established to predict the likelihood of the occurrence of landslide and debris flow. Using two real-world landslide and debris flows in 2021, we demonstrate that the proposed LSM system was able to provide early warning in advance.