Application of XGBoost for Hazardous Material Road Transport Accident Severity Analysis

Abstract

Hazardous material road transport accidents pose a serious threat to public life, property and the environment. Therefore, studying the factors influencing road transport accidents involving hazardous materials can help identify the main causes behind them and contribute to the adoption of specific and targeted measures to reduce casualty rates and improve traffic safety. However, most existing research either adopted methods based on statistical analysis or neglected to further evaluate the spatial relationships. This study aims to use the eXtreme Gradient Boosting (XGBoost) algorithm to analyze hazardous material road transport accident data from seven regions of China. Considering the rarity of these events, the classification performance of different methods is compared based on precision, recall, F-score and Area Under Curve (AUC). The results indicate that the proposed XGBoost method has the best modeling performance. There is some variation between regions in the features that have a significant impact on accident severity. The influence of the same feature on the severity of an accident even varies from region to region. The aforementioned results provide a theoretical basis for exploring the issues, sustainability, challenges, and tasks of safe transportation activities for hazardous materials in the future. These results can help regions develop targeted prevention and response policies to efficiently reduce the incidence and severity of accidents.

Keywords

• Feature analysis
• hazardous materials
• road transport accident
• transport safety
• XGBoost