Innovative prediction and causal analysis of accident vehicle towing probability using advanced gradient boosting techniques on extensive road traffic scene data

Ronghui Zhang; Yang Liu; Zihan Wang; Junzhou Chen; Qiang Zeng; Lai Zheng; Hui Zhang; Yulong Pei

doi:10.1016/j.aap.2024.107909

Innovative prediction and causal analysis of accident vehicle towing probability using advanced gradient boosting techniques on extensive road traffic scene data

Accid Anal Prev. 2025 Jan 13:211:107909. doi: 10.1016/j.aap.2024.107909. Online ahead of print.

Authors

Ronghui Zhang¹, Yang Liu¹, Zihan Wang¹, Junzhou Chen², Qiang Zeng³, Lai Zheng⁴, Hui Zhang⁵, Yulong Pei⁶

Affiliations

¹ Guangdong Key Laboratory of Intelligent Transportation System, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, 510275, Guangdong, China.
² Guangdong Key Laboratory of Intelligent Transportation System, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, 510275, Guangdong, China. Electronic address: [email protected].
³ School of Civil Engineering and Transportation, South China University of technology, Guangzhou, 510640, Guangdong, China.
⁴ School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin, 150040, Heilongjiang, China.
⁵ Intelligent Transportation Systems Research Center, Wuhan University of Technology, Wuhan, 430063, Hubei, China; Engineering Research Center of Transportation Information and Safety, Ministry of Education, Wuhan, 430063, Hubei, China.
⁶ School of Civil Engineering and Transportation, Northeast Forestry University, Harbin, 150040, Heilongjiang, China.

PMID: 39809047
DOI: 10.1016/j.aap.2024.107909

Abstract

Accurate prediction and causal analysis of road crashes are crucial for improving road safety. One critical indicator of road crash severity is whether the involved vehicles require towing. Despite its importance, limited research has utilized this factor for predicting vehicle towing probability and analyzing its causal factors. This study addresses this gap by predicting the probability of vehicle towing in road crashes based on road scene features and identifying key causal factors. Utilizing the Transportation Injury Mapping System (TIMS) dataset from California, USA, encompassing 12 years, 14 relevant features, and over 2 million road crash records, research team developed a prediction model using advanced gradient boosting techniques. Our model outperforms Random Forest, GBDT, and XGBoost in predictive accuracy. Employing the Shapley Additive Explanation (SHAP) method, researchers elucidate seven key factors influencing towing necessity. These findings introduce a novel predictive approach and offer valuable insights for road crash risk assessment and road safety planning.

Keywords: Causal factor; Prior scene feature; Road crash vehicle towing; Traffic safety.