Evaluation of deep learning algorithms for landslide susceptibility mapping in an alpine-gorge area: a case study in Jiuzhaigou County

• Published in: Journal of mountain science 2023-02, Vol.20 (2), p.484-500
• Main Authors: Wang, Di, Yang, Rong-hao, Wang, Xiao, Li, Shao-da, Tan, Jun-xiang, Zhang, Shi-qi, Wei, Shuo-you, Wu, Zhang-ye, Chen, Chao, Yang, Xiao-xia
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Deep learning; Disaster management; Earth and Environmental Science; Earth Sciences; Earthquakes; Ecology; Emergency preparedness; Environment; Evaluation; Feature extraction; Geography; Landslides; Landslides & mudslides; Machine learning; Mountain regions; Mountains; Original Article; Regression models; Seismic activity; Spatial distribution; Support vector machines; Susceptibility; Transformers; Zonation
• ISSN: 1672-6316; 1993-0321; 1008-2786
• DOI: 10.1007/s11629-022-7326-5

With its high mountains, deep valleys, and complex geological formations, the Jiuzhaigou County has the typical characteristics of a disaster-prone mountainous region in southwestern China. On August 8, 2017, a strong Ms 7.0 earthquake occurred in this region, causing some of the mountains in the area to become loose and cracked. Therefore, a survey and evaluation of landslides in this area can help to reveal hazards and take effective measures for subsequent disaster management. However, different evaluation models can yield different spatial distributions of landslide susceptibility, and thus, selecting the appropriate model and performing the optimal combination of parameters is the most effective way to improve susceptibility evaluation. In order to construct an evaluation indicator system suitable for Jiuzhaigou County, we extracted 12 factors affecting the occurrence of landslides, including slope, elevation and slope surface, and made samples. At the core of the transformer model is a self-attentive mechanism that enables any two of the features to be interlinked, after which feature extraction is performed via a forward propagation network (FFN). We exploited its coding structure to transform it into a deep learning model that is more suitable for landslide susceptibility evaluation. The results show that the transformer model has the highest accuracy (86.89%), followed by the random forest and support vector machine models (84.47% and 82.52%, respectively), and the logistic regression model achieves the lowest accuracy (79.61%). Accordingly, this deep learning model provides a new tool to achieve more accurate zonation of landslide susceptibility in Jiuzhaigou County.