SkySlide: A Hybrid Method for Landslide Susceptibility Assessment based on Landslide-Occurring Data Only

Abstract

Abstract Landslide susceptibility assessment is the problem of determining the likelihood of a landslide occurrence in a particular area with respect to the geographical and morphological properties of the area. This paper presents a hybrid method, namely SkySlide, that incorporates clustering, skyline operator, classification and majority voting principle for region-scale landslide susceptibility assessment. Clustering and skyline operator are utilized to model landslides while classification and majority voting principle are utilized to assess landslide susceptibility. The contribution of the study is 2-fold. First, the proposed method requires properties of landslide-occurring data only to model landslides. Second, the proposed method is evaluated on imbalanced data and experimental results include performance metrics of imbalanced data. Experiments conducted on two real-life datasets show that clustering greatly improves performance of SkySlide. Experiments further demonstrate that SkySlide achieves higher class balance accuracy, Matthews correlation coefficient, geometric mean and bookmaker informedness scores compared with the most commonly used methods for landslide susceptibility assessment such as support vector machines, logistic regression and decision trees.