EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multidimensional Framework for Traffic Accident Consequence Prediction: Integrating Multi-Objective Optimization, Explainable AI, and Causal Inference

Yanni Ju, Wanqiu Li, Di Tang, Gen Li

Applied Sciences · 05.08.2026 · 16 (15) · 7785

DOI: 10.3390/app16157785 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 05.08.2026. Verfasst von Yanni Ju und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program, Open Project of the Intelligent Policing Key Laboratory of Sichuan Province, Key Laboratory of Intelligent Policing and National Security Risk Governance 2025 Independent Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road traffic accident consequences are multidimensional, involving fatalities, injuries, and property loss. Existing studies have mainly focused on single outcomes, limiting the understanding of heterogeneous mechanisms across different consequence dimensions. Based on road accident data from Yancheng City in 2022, this study develops an integrated framework combining multi-output prediction, NSGA-II multi-objective optimization, SHAP-based interpretation, LOWESS nonlinear analysis, and DirectLiNGAM causal inference. The results show that the optimized Voting ensemble achieved competitive and comparatively balanced performance across the three accident-consequence dimensions. Road category, traffic control type, junction/road-segment type, and crash-cause category are identified as key influencing factors, with differentiated effects across accident consequences. POI variables exhibit nonlinear and threshold effects, while causal analysis further indicates that road infrastructure and traffic control conditions are positioned upstream in the formation mechanism of accident consequences. This study provides evidence for multidimensional accident-consequence category prediction and differentiated traffic safety management, rather than traditional continuous regression-based modeling.

Förderung

  • Sichuan Science and Technology Program
  • Open Project of the Intelligent Policing Key Laboratory of Sichuan Province
  • Key Laboratory of Intelligent Policing and National Security Risk Governance 2025 Independent Research Project
  • Open Project of Intelligent Policing and National Security Risk Management Laboratory
  • Open Project of the Key Laboratory of Automotive Measurement, Control and Safety

Zitieren

APA

Ju, Y., Li, W., Tang, D., & Li, G. (2026). A Multidimensional Framework for Traffic Accident Consequence Prediction: Integrating Multi-Objective Optimization, Explainable AI, and Causal Inference. Applied Sciences, 16(15), 7785. https://doi.org/10.3390/app16157785

Vancouver

Ju Y, Li W, Tang D, Li G. A Multidimensional Framework for Traffic Accident Consequence Prediction: Integrating Multi-Objective Optimization, Explainable AI, and Causal Inference. Applied Sciences. 2026;16(15):7785. doi:10.3390/app16157785

BibTeX
@article{Ju2026,
  author = {Ju, Yanni and Li, Wanqiu and Tang, Di and Li, Gen},
  title = {A Multidimensional Framework for Traffic Accident Consequence Prediction: Integrating Multi-Objective Optimization, Explainable AI, and Causal Inference},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7785},
  doi = {10.3390/app16157785}
}
Kostenlos starten →