Evaluation of landslide susceptibility of the Ya’an–Linzhi section of the Sichuan–Tibet Railway based on deep learning

• Published in: Environmental earth sciences Vol. 81; no. 9; p. 250
• Main Authors: Wang, Shibao, Zhuang, Jianqi, Mu, Jiaqi, Zheng, Jia, Zhan, Jiewei, Wang, Jie, Fu, Yuting
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2022; Springer Nature B.V
• Subjects: Algorithms; altitude; Artificial neural networks; Biogeosciences; China; Climatic conditions; Correlation analysis; Correlation coefficient; Correlation coefficients; Deep learning; Earth and Environmental Science; Earth Sciences; Environmental risk; Environmental Science and Engineering; Geochemistry; Geological hazards; Geological surveys; Geology; Human settlements; humans; Hydrology/Water Resources; Immunoglobulins; Interferometric synthetic aperture radar; interferometry; Landslides; Landslides & mudslides; Machine learning; Model testing; model validation; Modelling; Neural networks; Original Article; Railroads; Rain; Rainfall; Risk management; Risk reduction; River basins; rivers; SAR (radar); spatial data; Surveys; Susceptibility; Synthetic aperture radar; Synthetic aperture radar interferometry; Terrestrial Pollution; Testing; Training; Tibet; China; CNN; Landslide susceptibility; Sichuan–Tibet Railway; DNN; ROC
• ISSN: 1866-6280; 1866-6299
• DOI: 10.1007/s12665-022-10375-z

The Qinghai–Tibet Plateau is an area with frequent landslide hazards due to its unique geology, topography, and climate conditions, posing severe threats to engineering construction and human settlements. The primary purpose of this paper is to map the landslide susceptibility of the Ya’an–Lin branch of the Sichuan–Tibet Railway using two deep learning (DL) algorithms, convolutional neural network (CNN) and deep neural network (DNN). Initially, a geospatial database was generated based on 587 landslide hazards determined by Interferometric Synthetic Aperture Radar (InSAR) Stacking technology and field geological hazard surveys; thus, 18 landslide-influencing factors were selected. Subsequently, the landslides were randomly divided into training (70%) and validation data (30%) for model training and testing. Next, a Pearson correlation coefficient and information gain (IG) method were used to perform the correlation analysis and feature selection of the 18 influencing factors. Afterward, landslide susceptibility maps were generated for the two models. Finally, the performance of the model is validated using the receiver-operating characteristic (ROC) curve and confusion matrix. The results show that the CNN model (AUC = 0.88) provided better performance in both the training and testing phases compared to the DNN model (AUC = 0.84). In addition, the high landslide susceptibility is primarily distributed in the Jinsha, Lancang and Nu River basins along the railway. The slope, altitude and rainfall are the main factors for the formation of the landslides. Furthermore, the two deep learning models can accurately map the landslide susceptibility, providing important information for landslide risk reduction and prevention.