Prediction of landslide induced debris’ severity using machine learning algorithms: a case of South Korea

Abstract

Abstract. Rainfall-induced landslides frequently occur in the mountainous region of the Korean peninsula. The resulting landslide-induced debris causes extreme property damage, huge financial losses, and human deaths. To mitigate their effect different landslide susceptibility mapping is frequently used. However, these methods do identify regions with potential landslides but they do not quantify their severity. In this paper, multi-category ordered machine models, namely, proportional odd logistic regression (POLR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (EGB) methods, are proposed to fill the specified gap. Moreover, the exploratory data analysis on the landslide-induced debris dataset has been conducted to examine patterns and relationships between landslide-induced debris severity(size), causal factors(rainfall), and influencing factors. Findings revealed that cumulative three days’ rainfall and slope length were most responsible for the severity of landslide-originated debris severity and slopes between 20° to 40° were identified as the most vulnerable region. Furthermore, the predictive accuracy statistics were compared to assess the suitable model for debris severity for the Korean case. The RF and EGB ranked higher with an overall accuracy of 90.07 % and 86.09 % and kappa of 0.72 and 0.61 on the validation set, respectively. The findings of this research may be useful in the identification of high-risk zones for extreme rainfall-induced debris to elaborate mitigation and resilience policies, post-disaster rehabilitation planning, and land use management.