Landslide susceptibility mapping using an integration of different statistical models for the 2015 Nepal earthquake in Tibet

Landslide susceptibility maps (LSMs) can play a bigger role in promoting the understanding of future landslides. This paper explores and compares the capability of three state-of-the-art bivariate models, namely the frequency ratio (FR), statistical index (SI), and weights of evidence (WoE), with ensembles of multivariate logistic regression (LR), for LSM in part of Tibet. Firstly, a landslide inventory map with 829 landslide records is obtained from field surveys and interpretation. Secondly, 15 landslide conditioning factors (LCFs) are considered and prepared from multi-data sources. Subsequently, a multicollinearity analysis is conducted to calculate the independence between different factors. Then, the Information Gain Ratio method (IGR) is performed to confirm the predictive ability of the LCFs. Finally, LSMs are constructed by, SI, WoE, LR and their combination through 12 preferred LCFs. The performance of different methods are validated and compared in term of areas under the receiver operating characteristic curve (AUC) and statistical measures. The results from this study indicate the hybrid models FR-LR, WoE-LR and SI-LR achieved higher AUC value than all corresponding single methods. The ensemble frameworks are well in line with the distribution pattern of historical landslides in the research area. Therefore, the proposed high-performance ensemble frameworks are expected to provide a useful reference for landslide hazard prevention in similar areas.