Estimation of Landslide Hazard Zones Using Deep Learning Based on Diverse Geospatial Data

Traditional landslide hazard mapping in Japan relies on labor-intensive field surveys, which are slow, costly, and fail to update dynamically amid rising climate-driven disasters like the 2018 Heavy Rain Event, leaving gaps in timely evacuations. This study addresses these challenges by proposing a semantic segmentation framework using ResUNet to fuse Sentinel-2 optical, Sentinel-1 SAR amplitude, DEM-derived Terrain Ruggedness Index (TRI), and JAXA land cover data, tackling class imbalance with BCE + Dice loss and providing probability/uncertainty maps via 4-TTA for robust hazard delineation under adverse weather. The principal aim is to enable operational, weather-robust hazard zone extraction with AUC upto 0.89 (best multimodal configuration), outperforming single-modality baselines (e.g., optical-only AUC 0.74; SAR-only 0.69) through synergistic feature fusion, while highlighting multimodal SAR's edge for cloud-obscured scenarios. Validated on Hiroshima Prefecture data—Japan's highest-risk region with ~32,000 hazard spots—this approach demonstrates pre/post-disaster change detection, but reveals limitations in spatial generalization due to region-specific training.

@article{Arai2026,
  title     = {Estimation of Landslide Hazard Zones Using Deep Learning Based on Diverse Geospatial Data},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {2},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Kohei Arai and Kengo Oiwane and Hiroshi Okumura},
  doi       = {10.14569/IJACSA.2026.0170214},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170214}
}