Statistical Analysis of Debris Flow Susceptibility Factors in Hunan Province
Year: 2025
Type: conference-paper
Abstract: Hunan Province has abundant precipitation and complex terrain, making it a high-risk area for debris flow disasters. However, the current research on the susceptibility of debris flows and their influencing factors in this region is still relatively weak. Based on multi-source data from 2003 to 2022, this paper uses the random forest regression model to identify the main influencing factors of debris flows, and combines the support vector machine (SVM) and XGBoost models to conduct susceptibility assessment and time series prediction. The results show that precipitation, slope, water resource volume, and forest coverage rate are the key factors, among which precipitation has the highest weight; the AUC value of the SVM model reaches 0.97, demonstrating good classification performance; the prediction results of the XGBoost model are highly consistent with the measured values (R²=0.7901, MSE=0.4104). The research results can provide technical support for the risk assessment and early warning of debris flow disasters in Hunan Province.
Authors: Jiayin Yang, Yitong Lu, Jiawen Yang, Jing Bai
Institution: Zhuhai College of Science and Technology
Language: English
Subfield: Management, Monitoring, Policy and Law
Field: Environmental Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7154378657