Tambov, Tambov, Russian Federation
employee from 01.01.1972 to 01.01.2025
Tambov, Tambov, Russian Federation
Road traffic accidents (RTAs) pose a significant threat to public safety and transportation networks, requiring advanced modeling techniques to study their causes, trends, and consequences. The complexity of RTAs modeling stems from the need to integrate diverse data sources, including spatiotemporal changes, environmental variables, vehicle and driver characteristics, and infrastructure elements. Recent advances in machine learning, including graph neural networks, attention-based deep learning models, and hybrid tree classifiers, have improved prediction accuracy and interpretability. These methods leverage heterogeneous data to provide real-time crash prediction, severity assessment, and identification of problem areas. However, obstacles remain, such as data sparsity, class imbalance, and model interpretability. This article reviews modern approaches to RTAs modeling and identifies the impact of diverse information on crash frequency and severity estimates, thereby improving road safety, optimizing traffic management, and refining crash prevention approaches and technologies. Promising research directions in this area of modeling and machine learning are identified: integration of heterogeneous data, use of causal machine learning methods and real-time decision support systems.
modeling, heterogeneous information, traffic accidents, machine learning
1. Uthaib M.A., Tyutyunnik V.M. Pattern recognition of the state registration plate of a vehicle // Mir nauki bez granic: materialy XI Vseros. nauch.-prakt. konf. molodyh uchyonyh. Tambov: izdat. Centr FGBOU VO «TGTU», 2024. S. 285–287.
2. Udaib M.A. Sovremennye metody i informacionnye sistemy fiksirovaniya, prognozirovaniya i predotvrashcheniya dorozhno-transportnyh proisshestvij // Informacionnye processy, sistemy i tekhnologii. 2024. T.5. №2. S. 14–22. DOI:https://doi.org/10.52529/27821617_2024_5_2_14
3. Tyutyunnik V.M., Udaib M.A. Nejrosetevye metody i modeli prognozirovaniya dorozhno-transportnyh proisshestvij i snizheniya ih riskov // Promyshlennye ASU i kontrollery. 2024. №12. S. 47–56. DOI:https://doi.org/10.25791/asu.12.2024.15483
4. Uthaib M.A., Tyutyunnik V.M. Integrating situational factors and heterogeneous data for enhanced traffic accident analysis // Obshchestvo. 2025. №1 (36), Ch. 2. S. 15–19.
5. Uthaib M.A., Tyutyunnik V.M. The effects of heterogeneous information in analyzing traffic accidents // Mir nauki bez granic: sb. materialov 12-j Mezhdunar. nauch.-prakt. konf. molodyh uchyonyh. Tambov: Izdat. centr FGBOU VO «TGTU», 2025. S. 41–44.
6. SMA-HYPER: Spatiotemporal Multi-View Fusion Hypergraph Learning for Traffic Accident Prediction / X. Gao [et al.] // Preprint Submitted to Elsevier, 2024.
7. Ghahremannezhad H., Shi H., Liu C. Real-Time Accident Detection in Traffic Surveillance Using Deep Learning. 2022. URL: https://doi.org/10.48550/arXiv.2208.06461 (data obrashcheniya: 20.02.2026).
8. Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis / A. Nippani [et al.] // 2023. URL: arXiv.org.2311.00164 (data obrashcheniya: 20.02.2026).
9. Interpretable Traffic Accident Prediction: Attention Spatial–Temporal Multi-Graph Traffic Stream Learning Approach / C. Li [et al.] // IEEE Transactions on Intelligent Transportation Systemsyu 2024. P. 1–13.
10. Predictive analysis for road accidents using a tree-based and deep learning fusion system / M. Ameksa [et al.]. // Journal of Intelligent and Fuzzy Systems. 2023. Vol. 46. P. 2381–2397.
11. AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Model / L. Wang [et al.] // 2023. Vol. abs/2312.13156.
12. Exploring the spatiotemporal heterogeneity of freeway secondary crashes using GTWR model / H. Liu [et al.]. // Journal of Transportation Safety & Security. 2023. P. 1–24.
13. Jiang J., Miao Y., Wu D. Machine Learning-based Prediction Analysis of Potential Factors in Traffic Accidents // Applied and Computational Engineering. EWA Publishing. 2024. Vol. 99. № 1. P. 112–120.
14. Sukonna R.T., Swapnil S.I. A Bi-level Framework for Traffic Accident Duration Prediction: Leveraging Weather and Road Condition Data within a Practical Optimum Pipeline // URL: arXiv.org.2311.00634 (data obrashcheniya: 20.02.2026).
15. It Is About Weather: Explainable Machine Learning for Traffic Accident Understanding. / S. Soedirman [et al.]. // 2023. P. 2689–2694.
16. Exploring spatial heterogeneity in factors associated with injury severity in speeding-related crashes: An integrated machine learning and spatial modeling approach / Z. Zhang [et al.] // Accident Analysis & Prevention. Elsevier BV, 2024. Vol. 206. P. 107697.
17. Prediction of Accident Risk Levels in Traffic Accidents Using Deep Learning and Radial Basis Function Neural Networks Applied to a Dataset with Information on Driving Events / C. Arciniegas-Ayala [et al.] // Applied Sciences. Multidisciplinary Digital Publishing Institute, 2024. Vol. 14. № 14. P. 6248.
18. Sorum N.G., Pal D. Identification of the best machine learning model for the prediction of driver injury severity // International Journal of Injury Control and Safety Promotion. 2024. P. 1–16.
19. Mehdi M. Machine learning and multisource data analysis approach towards traffic accident risk prediction // Scientific Publishing Center InterConf. 2024. No. 50 (221). P. 401–406.
20. Development and Application of Highway Traffic Congestion and Accident Risk Early / B. Xie [et al.] // Warning Model. 2024. P. 1519–1523.
21. Nayak A., Goyal K. Traffic modeling and accidental data analysis using GIS // A Review. 2024.
22. Machine Learning Applications in Traffic Safety / S. Priyanka [et al.]. // Assessing Accident Severity Automatically. 2023. P. 1197–1203.
23. Exploring the spatiotemporal heterogeneity of freeway secondary crashes using GTWR model / H. Liu [et al.]. // Journal of Transportation Safety & Security. 2023. P. 1–24.
24. Benfaress I., Bouhoute A., Zinedine A. Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability // AI. Multidisciplinary Digital Publishing Institute, 2024. Vol. 5. No.4. P. 2568–2585.
25. Kashifi M.T. Robust spatiotemporal crash risk prediction with gated recurrent convolution network and interpretable insights from SHapley additive explanations // Engineering Applications of Artificial Intelligence. 2024.
