Susceptibility assessment of geological hazard based on XGBoost and cloud model

Abstract

In the conventional process of geological hazard assessment, issues such as subjectivity in selecting susceptibility factor weights, randomness, and fuzziness in factor grading are prevalent. The application of a single assessment model can only provide qualitative evaluation of geological hazard susceptibility, lacking quantitative analysis. To overcome these challenges, this study employs an enhanced integrated algorithm (XGBoost) and cloud model. Among 189 disaster potential points in Chaoyang City, twelve susceptibility factors including slope, meteorological conditions, vegetation coverage and elevation were selected. The XGBoost classification algorithm was used to determine susceptibility factor weights. The results showed that the algorithm classification achieved high performance with fitting accuracy of 96.5%. On this basis, the cloud model was employed to transform the fuzzy factor grading into a quantitative problem, establishing a susceptibility evaluation index system for geological hazards in Chaoyang City, thereby assessing their susceptibility. To validate the evaluation index system, the Dadongshan landslide in Chaoyang City was selected as the assessment unit. Results indicate a high susceptibility level for this evaluation unit, consistent with actual conditions. The methodology proposed in this study is promising and can offers reference for evaluating geological hazard susceptibility.

Keywords

• xgboost
• susceptibility factor weights
• cloud model
• susceptibility assessment
• geological disaster