GIS-based landslide susceptibility assessment using optimized hybrid machine learning methods

• Published in: Catena (Giessen) Vol. 196; p. 104833
• Main Authors: Chen, Xi, Chen, Wei
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2021
• Subjects: catenas; China; data collection; decision making; Geographic information system; Hybrid models; inventories; Kernel functions; Kernel logistic regression; Landslide; landslides; prediction; regression analysis; rivers; China; Landslide; Kernel logistic regression; Kernel functions; Hybrid models; Geographic information system
• DOI: 10.1016/j.catena.2020.104833
• ISSN: 0341-8162

•Landslide modeling use optimized KLR with different kernel functions.•Optimization of factors using FR analysis and multicollinearity analysis.•Comparison of landslide susceptibility maps to reveal difference affected by factors. Globally, but especially in China, landslides are considered to be one of the most severe and significant natural hazards. In this study, bivariate statistical-based kernel logistic regression (KLR) models with different kernel functions (Polynomial, PUK, and Radial Basis Function), named the PLKLR, PUKLR, and RBFKLR models, were proposed for landslide susceptibility evaluation in Zichang City, China. Meanwhile, the present study aims to build landslide susceptibility maps based on bivariate statistical correlation analysis, optimization of different kernel functions, comparison of three landslide susceptibility maps and systematic analysis of spatial patterns. The steps of this article are organized as follows: Firstly, a landslide inventory containing 263 historical landslide locations was constructed. For the purpose of training and validation of models, 263 landslide locations were randomly divided into two parts with a ratio of 70/30. Secondly, 14 landslide conditioning factors were extracted from the spatial database. Subsequently, correlation analysis between the conditioning factors and the occurrence of landslides was conducted using frequency ratios. Then, the conditioning factors with normalized frequency ratios values were used as inputs to build the landslide susceptibility maps using the three models. A multicollinearity analysis was performed using collinearity statistics. Finally, the area under the receiver operating characteristic curve (AUC) was used for comparison and validation of models for recognizing the prediction capability. By further quantitative comparing mapped susceptibility values on a pixel-by-pixel basis, which can acquire underestimations and overestimations of factors (distance to river and slope) and susceptibility area. The results indicated that the PUKLR model had superior performance in landslide susceptibility assessment, with the highest AUC values of 0.884 and 0.766 for training and validation datasets, respectively. This model was followed by the RBFKLR model and the PLKLR model for the training datasets (AUC values of 0.879 and 0.797, respectively), and the PLKLR model and the RBFKLR model for the validation datasets (AUC values of 0.758 and 0.752, respectively). The landslide susceptibility map could help government agencies and decision-makers make wise decisions for future natural hazards prevention in Zichang region.