Automated Mapping of Ms 7.0 Jiuzhaigou Earthquake (China) Post-Disaster Landslides Based on High-Resolution UAV Imagery

A novel method combining high-resolution UAV imagery and machine learning achieved near-perfect accuracy (99.89%) in mapping landslides triggered by the 2017 Ms 7.0 Jiuzhaigou earthquake in China, surpassing traditional manual interpretation. The approach used a support vector machine (SVM) classification model integrated with pre-seismic road and village data to automatically identify landslide distribution with high precision (Kappa coefficient > 0.9). This advancement significantly improves post-disaster response capabilities by enabling rapid and accurate landslide mapping, critical for emergency rescue operations. The study also revealed spatial patterns of earthquake-triggered landslides, influenced by factors such as altitude, slope gradient, aspect, and proximity to faults, providing valuable insights for future risk assessment and susceptibility prediction in UNESCO World Heritage Sites.

Liang, R., Dai, K., Shi, X., Guo, B., Dong, X., Liang, F., Tomás, R., Wen, N., & Fan, X. (2021). Automated Mapping of Ms 7.0 Jiuzhaigou Earthquake (China) Post-Disaster Landslides Based on High-Resolution UAV Imagery. Remote Sensing, 13(7), 1330. https://doi.org/10.3390/rs13071330