A spatial case-based reasoning method for regional landslide risk assessment
Zheng Zhao, Jianhua Chen, Kaihang Xu, Huawei Xie, Xianxia Gan, He Xu
Abstract
Various machine learning methods have been applied to study regional landslide risk assessment problems, but most of them mainly consider the influencing factors associated with landslide occurrences and ignore the spatial features. Therefore, by combining the advantages of traditional case-based reasoning (CBR) and by fully mining the spatial features, this paper proposes a novel spatial case-based reasoning method for landslide risk assessment. In this method, the spatial proximity and spatial topological relationships were extracted as spatial features, and the influencing factors associated with landslide occurrences were selected as attribute features. Then, the integrated expression of the spatial and attribute features of a landslide case was further constructed. Finally, attribute similarity and spatial similarity were used for joint reasoning. This study then carried out experiments in Lushan, China. Upon comparison of the three CBR models, the proposed integrated CBR outperformed the other models. Furthermore, an optimized support vector machine and a deep convolutional neural network were selected as experimental methods in the control group. The results show that the proposed integrated CBR has better performance. In conclusion, the proposed integrated CBR can be effectively applied to regional landslide risk evaluation and other similar geospatial problems.