Integrating Topographic Features and Satellite Images with Deep Learning for Landslide Mapping and Monitoring

Landslide is one of the most commonly happened and threatening natural hazards in Taiwan. Because of the complicated terrain, geological, geotechnical and weather conditions landslides are frequently triggered by earthquakes, typhoons or heavy rainfalls in Taiwan, and sometimes result in serious damages. Satellite imagery is one of the commonly used sources to determine the extent of landslides for mapping, inventorying, assessment and hazard mitigation decision support. However, conventional image-based landslide detection approaches rely only on spectral and two-dimensional spatial characteristics, which may not be able to achieve high accuracy and difficult to differentiate different landslide-related terrain interpretations. This research integrates topographic features with high resolution satellite images to improve landslide detection and monitoring effectiveness and efficiency. In addition to just including height information from three-dimensional (3D) point clouds or digital elevation/terrain models (DEM/DTM), multi-scale landslide-related topographic features are derived from 3D DTM generated from airborne LiDAR surveys or stereo satellite images. These features include: slope, curvature, surface roughness, topographic position index, geomorphons and geo-hydrological features etc. These features are essential for identifying important landslide terrains, such as hummocky, crown scarps, toe bulges, gullies and the like. Based on the calculated topographic features, landslide candidate areas can be identified according to a developed scoring/classification equation. The derived topographic features and resultant landslide candidate (scores) are integrated with high resolution satellite images for landslide detection. A deep learning model based on ResUet is utilized to identify landslide areas. The developed framework was applied to analyze multi-temporal satellite images and digital terrain data of a mountainous watershed region in southern Taiwan. Preliminary results indicate that integrating topographic features with satellite images can improve the performance of landslide detection and is an effective approach for long-term monitoring of large- areas vulnerable to landslide hazards.