Crash risk prediction and analysis from the perspective of alignment and environment features: A study on an expressway in a hilly area
This study proposes an approach to predict crash risks on road sections without historical crash data. Combining the XGBoost model with the SHAP approach, enables accurate identification of risks on expressways in hilly areas using alignment and environment features and enhances the understanding of how these factors contribute to high risks.
Authors
- Yuntao Ye (ORCID: https://orcid.org/0000-0003-3176-3134)
- Zhiming Fang (ORCID: https://orcid.org/0000-0001-7368-1183)
- Xintong Yan (ORCID: https://orcid.org/0000-0001-7160-2541)
- Zhang Changjian
- Pengcheng Qin (ORCID: https://orcid.org/0000-0002-5008-5933)
- Chenwei Wang (ORCID: https://orcid.org/0000-0002-2375-5743)
- Jie He
Institutions
- University of Hawaiʻi at Mānoa (US)
- Southeast University (BD)
- Southeast University (CN)
Publication Details
- Journal
- Traffic Injury Prevention
- Published
- 2025-02-21
- DOI
- https://doi.org/10.1080/15389588.2025.2459297
- Citations
- 3
- Primary Topic
- Traffic and Road Safety
- Type
- article
- Field-Weighted Citation Impact
- 3.91
Funders
- National Natural Science Foundation of China