Optimal location of rescue bases on the Chalous road: a deep learning-based approach

Document Type : Applied Article

Authors

1 PhD In Remote Sensing and Geographic Information Systems, Faculty of Geography, Kish International Campus, University of Tehran, Iran

2 Associate Professor, Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran

3 Department of Health in Emergencies and Disasters, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran

4 M.Sc. in Geographic Information Systems and Remote Sensing, Faculty of Geography, University of Tehran, Iran

10.22059/jhsci.2026.411833.922

Abstract

Objective: Road accidents, especially on mountainous roads, pose significant traffic safety challenges that require accurate prediction and optimal management. In Iran, as a disaster-prone country, road accidents rank as the second-highest risk in terms of occurrence frequency, after earthquakes, highlighting the critical importance of road accidents as a significant risk factor. In this study, using data from the Red Crescent mission reports along with road, environmental, and traffic features, a deep learning transformer model was developed to identify accident-prone locations on the Chalous road corridor. This model extracted complex nonlinear patterns with considerable accuracy and predicted high-risk points categorized into three accident severity classes (fatal, injured, treated on site). Subsequently, using the Grey Wolf Optimizer algorithm, the optimal placement of rescue bases was performed to increase road coverage and reduce response time. Results showed that rescue coverage on the Chalous corridor increased from 22.77% to 86.91%, and average response time decreased from approximately 14 minutes 45 seconds to 8 minutes 22 seconds, representing a 64% improvement in coverage and a 43% reduction in reaction time, respectively. This study demonstrated that integrating real-world data, advanced deep learning models, and optimization algorithms provides an effective tool for improving rescue management, enhancing safety on high-traffic and high-risk corridors, and reducing injuries and fatalities. The findings can serve as a basis for designing intelligent crisis management systems and developing preventive programs in other regions of the country.

Keywords

References

Zheng, M., Li, T., Zhu, R., Chen, J., Ma, Z., Tang, M., Cui, Z., & Wang, Z. (2019). Traffic accident's severity prediction: A deep-learning approach-based CNN network. IEEE Access, 7, 45613-45620. https://doi.org/10.1109/ACCESS.2019.2903319.
Soltani, A., Alaedini, F., Shamspour, N., & Ahmadi Marzaleh, M. (2021). Hazard assessment of Iran provinces based on the Health Ministry tool in 2019. Iran Red Crescent Medical Journal, 23(1), e204. https://doi.org/10.32592/ircmj.2021.23.1.204
Zhang, J.H. (2019). Integration Theory and Optimal Application of the Traffic Accident Management System. In Proceedings of the International Conference on Cyber Security Intelligence and Analytics (CSIA), Shenyang, China, February 2019; Springer International Publishing Ag: Shenyang, China, 2019; pp. 99–104. DOI:10.1007/978-3-030-15235-2_16
Astarita, V., Shaffiee Haghshenas, S., Guido, G., & Vitale, A. (2023). Developing new hybrid grey wolf optimization-based artificial neural network for predicting road crash severity. Transportation Engineering, 12, 100164. https://doi.org/10.1016/j.treng.2023.100164
Goli, A., & Malmir, B. (2019, May 4). A covering tour approach for disaster relief locating and routing with fuzzy demand. International Journal of Intelligent Transportation Systems Research. https://doi.org/10.1007/s13177-019-00185-2
Li, P., Abdel-Aty, M., & Yuan, J. (2020). Real-time crash risk prediction on arterials based on LSTM-CNN. Accident Analysis and Prevention, 135,105371. https://doi.org/10.1016/j.aap.2019.105371
Shang, Q., Feng, L., & Gao, S. (2020). A hybrid method for traffic incident detection using Random Forest-Recursive Feature Elimination and Long Short-Term Memory network with Bayesian Optimization Algorithm. IEEE Access, 8,223513-223522. https://doi.org/10.1109/ACCESS.2020.3047340.
Guo, Y., Jena, R., Hughes, D., Lewis, M., & Sycara, K. (2021). Transfer learning for human navigation and triage strategies prediction in a simulated urban search and rescue task. Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), 1-8. https://doi.org/10.1109/ICRA48506.2021.9562203
Yang, J., Wang, P., Yuan, W., Ju, Y., Han, W., & Zhao, J. (2021). Automatic generation of optimal road trajectory for the rescue vehicle in case of emergency on mountain freeway using reinforcement learning approach. IET Intelligent Transport Systems, 15(10), 1281–1289. https://doi.org/10.1049/itr2.12037
Zhao, W., Yang, Y., & Lu, Z. (2022). Interval short-term traffic flow prediction method based on CEEMDAN-SE noise reduction and LSTM optimized by GWO. Wireless Communications and Mobile Computing, 2022, Article ID 5257353, 16 pages. https://doi.org/10.1155/2022/5257353
Wang, D., Peng, J., Zhao, J., Teng, Y., Xue, W., & Tao, X. (2023, October 10–13). Dual-Transformer: A general model for traffic accident prediction. In 2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall). IEEE. https://doi.org/10.1109/VTC2023-Fall60731.2023.10333613
Mousavi, B.S., Jahangir, E., Neysani Samani, N., & Argany, M. (2023). Spatial Analysis of Rescue and Relief Bases in Alborz Province in order to Reduce Hazards. Sci J Rescue Relief, 2023; 15(3): 194- 206. acceptance: 27 Jun. 2023. Doi: 10.32592/jorar.2023.15.3.5.
Al-Thani, M. G., Sheng, Z., Cao, Y., & Yang, Y., "Traffic Transformer: Transformer-based framework for temporal traffic accident prediction," AIMS Mathematics, vol. 9, no. 5, pp. 12610–12629, Apr. 2024. doi: 10.3934/math.2024617.
Huang, G., Qi, Y., Cai, Y., Luo, Y., & Huang, H. (2024). A Grey Wolf Optimizer Algorithm for Multi-Objective Cumulative Capacitated Vehicle Routing Problem Considering Operation Time. Biomimetics, 9(6), 331. https://doi.org/10.3390/biomimetics9060331
Forouzandeh, M., Mousavi, B. S., Neysani, N., & Argany, M. (2025). Spatial prediction of the impact of road accidents on traffic using machine learning algorithms. Earth Observation and Geomatics Engineering, 8(1), 29–47. https://doi.org/10.22059/eoge.2025.378825.1155
Jiang, Y., Qu, X., Zhang, W., Guo, W., Xu, J., Yu, W., & Chen, Y. (2025). Analyzing crash severity: Human injury severity prediction method based on transformer model. Vehicles, 7(1), 5. https://doi.org/10.3390/vehicles7010005
Peng, D., & Yan, W. (2025). Test-Time Training with Adaptive Memory for Traffic Accident Severity Prediction. Computers, 14(5), 186. https://doi.org/10.3390/computers14050186
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention Is All You Need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
https://doi.org/10.48550/arXiv.1706.03762
Wu, H., Xu, J., Wang, J., & Long, G. (2021). Auto former: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting. Advances in Neural Information Processing Systems, 34. https://doi.org/10.48550/arXiv.2106.13008
Environmental Management Hazards
Volume 12, Issue 4
January 2026
Pages 297-302

Files

Share

How to cite

Statistics