Machine Learning Models for Proactive Road Safety: Evaluating Regression and Ensemble Techniques Based on Road Geometry
Received: 18 April 2025 | Revised: 21 May 2025, 4 June 2025, and 16 June 2025 | Accepted: 18 June 2025 | Online: 14 July 2025
Corresponding author: P. Manoj
Abstract
The complex interplay of factors contributing to road accidents necessitates the use of advanced predictive techniques capable of identifying the high-risk zones before incidents occur. The present research addresses this need by using a dataset with 16 road characteristics, such as curve radius, entry/exit speeds, and sight distance, and developing several models for this task, namely traditional linear models, including Simple Linear Regression (SLR), Ridge, Lasso, ElasticNet, ensemble techniques, including Random Forest Regressor (RFR), gradient boosting, Support Vector Regressor (SVR), and Extreme Gradient Boosting (XGBoost), and advanced gradient boosting frameworks, like LightGBM, and CatBoost. Among these, SLR achieved the best performance, with a Root Mean Square Error (RMSE): 6.92, and R2: 0.94 on the test set, while XGBoost ranked highest among the ensemble methods (RMSE: 14.55, R2: 0.75). The feature importance analysis revealed that the superelevation e (%), entry speed V(entry) (km/h), and mid-section speed V(mid) (km/h) were the most significant predictors across the models. This analysis offers valuable insights for the transportation authorities to predict accident-prone areas and implement targeted safety measures to reduce the road accidents.
Keywords:
accident forecasting, machine learning, road safety, regression models, ensemble methods, feature importanceDownloads
References
World Health Organization, Global status report on road safety 2018. Geneva: World Health Organization, 2018.
M. L. Siregar, T. Tjahjono, and N. Yusuf, "Predicting the Segment-Based Effects of Heterogeneous Traffic and Road Geometric Features on Fatal Accidents," International Journal of Technology, vol. 13, no. 1, Jan. 2022, Art. no. 92. DOI: https://doi.org/10.14716/ijtech.v13i1.4450
S. Alshiya, E. Anoop, K. D. Arpith, K. Sanal, and A. Happy, "Raps-Road Accident Prediction System Using Random Forest," International Research Journal of Modernization in Engineering Technology and Science, vol. 3, no. 4, Apr. 2023.
U. Iliyasu, M. M. Yakudu, and A. A. Abdulwasiu, "Predictive Analysis of Road Traffic Accidents in Katsina State, Nigeria Using Machine Learning Algorithms: A Study on Factors and Mitigation Strategies," International Journal of Science for Global Sustainability, vol. 9, no. 2, pp. 188–198, Jul. 2023. DOI: https://doi.org/10.57233/ijsgs.v9i2.475
J. Siswanto, A. S. N. Syaban, and H. Hariani, "Artificial Intelligence in Road Traffic Accident Prediction," Jambura Journal of Informatics, vol. 5, no. 2, pp. 77–90, Nov. 2023. DOI: https://doi.org/10.37905/jji.v5i2.22037
S. Olugbade, S. Ojo, A. L. Imoize, J. Isabona, and M. O. Alaba, "A Review of Artificial Intelligence and Machine Learning for Incident Detectors in Road Transport Systems," Mathematical and Computational Applications, vol. 27, no. 5, Sep. 2022, Art. no. 77. DOI: https://doi.org/10.3390/mca27050077
Y. Zhang and Y. Sung, "Traffic Accident Detection Method Using Trajectory Tracking and Influence Maps," Mathematics, vol. 11, no. 7, Apr. 2023, Art. no. 1743. DOI: https://doi.org/10.3390/math11071743
H. Khanum, A. Garg, and M. I. Faheem, "Accident severity prediction modeling for road safety using random forest algorithm: an analysis of Indian highways," F1000Research, vol. 12, Oct. 2023, Art. no. 494. DOI: https://doi.org/10.12688/f1000research.133594.1
P. Gorzelańczyk, M. Jurkovič, T. Kalina, and M. Mohanty, "Forecasting the road accident rate and the impact of the covid 19 on its frequency in the polish provinces," Communications - Scientific letters of the University of Zilina, vol. 24, no. 4, pp. A216–A231, Oct. 2022. DOI: https://doi.org/10.26552/com.C.2022.4.A216-A231
C. D. Wirz, J. L. Demuth, M. G. Cains, M. White, J. Radford, and A. Bostrom, "National Weather Service (NWS) Forecasters’ Perceptions of AI/ML and Its Use in Operational Forecasting," Bulletin of the American Meteorological Society, vol. 105, no. 11, pp. E2194–E2215, Nov. 2024. DOI: https://doi.org/10.1175/BAMS-D-24-0044.1
H. Xu, Y. Zhao, D. Zhao, Y. Duan, and X. Xu, "Improvement of disastrous extreme precipitation forecasting in North China by Pangu-weather AI-driven regional WRF model," Environmental Research Letters, vol. 19, no. 5, May 2024, Art. no. 054051. DOI: https://doi.org/10.1088/1748-9326/ad41f0
M. Girija and V. Divya, "Deep Learning-Based Traffic Accident Prediction: An Investigative Study for Enhanced Road Safety," EAI Endorsed Transactions on Internet of Things, vol. 10, Feb. 2024. DOI: https://doi.org/10.4108/eetiot.5166
Q. Guo, B. Guo, Y. Wang, S. Tian, and Y. Chen, "A Combined Prediction Model Composed of the GM (1,1) Model and the BP Neural Network for Major Road Traffic Accidents in China," Mathematical Problems in Engineering, vol. 2022, pp. 1–11, Apr. 2022. DOI: https://doi.org/10.1155/2022/8392759
A. P. Kumar and D. Teja Santosh, "Road Accident Severity Prediction Using Machine Learning Algorithms," International Journal of Computer Engineering in Research Trends, vol. 9, no. 9, pp. 175–183, Oct. 2022. DOI: https://doi.org/10.22362/ijcert/2022/v9/i9/v9i902
V. Prajwal, R. Abhay, R. D. Gowda, and G. Savitha, "AI-Driven Urban Traffic Optimization to Assess Complex Traffic Patterns for Public Traffic Control and Mobility," International Journal for Research in Applied Science and Engineering Technology, vol. 11, no. 11, pp. 794–798, Nov. 2023. DOI: https://doi.org/10.22214/ijraset.2023.56630
K. Yao, "AI-driven innovations in automation and urban management," Applied and Computational Engineering, vol. 57, no. 1, pp. 160–165, Apr. 2024, https://doi.org/10.54254/2755-2721/57/20241327. DOI: https://doi.org/10.54254/2755-2721/57/20241327
I. De Zarzà, J. De Curtò, G. Roig, and C. T. Calafate, "LLM Multimodal Traffic Accident Forecasting," Sensors, vol. 23, no. 22, Nov. 2023, Art. no. 9225. DOI: https://doi.org/10.3390/s23229225
P. Gorzelanczyk, "Impact of information on the number of traffic accidents on the outcome of the forecast," Technical Sciences, vol. 26, Nov. 2023. DOI: https://doi.org/10.31648/ts.8945
S. A. Arhin and A. Gatiba, "Predicting Injury Severity of Angle Crashes Involving Two Vehicles at Unsignalized Intersections Using Artificial Neural Networks," Engineering, Technology & Applied Science Research, vol. 9, no. 2, pp. 3871–3880, Apr. 2019. DOI: https://doi.org/10.48084/etasr.2551
M. Touahmia, "Identification of Risk Factors Influencing Road Traffic Accidents," Engineering, Technology & Applied Science Research, vol. 8, no. 1, pp. 2417–2421, Feb. 2018, https://doi.org/10.48084/etasr.1615. DOI: https://doi.org/10.48084/etasr.1615
A. N. Al-Nuaimi, A. K. Jameel, and S. M. Alsadik, "Impact of Variable Speed Limits on Crash Frequency and Crash Rate: Stimulation by Flow Rate and Percentage of Heavy Vehicles," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 20335–20341, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9660
H. Khanum, R. Kulkarni, A. Garg, and M. Iqbal Faheem, "Enhancing Road Safety in India: A Predictive Analysis Using Machine Learning Algorithm for Accident Severity Modeling," in Recent Topics in Highway Engineering - Up-to-Date Overview of Practical Knowledge, vol. 10, S. Antonio Biancardo, Ed. IntechOpen, 2024. DOI: https://doi.org/10.5772/intechopen.1006547
P. Manoj, "Enhancing road safety through blackspots mitigative measures - a review," Sigma Journal of Engineering and Natural Sciences – Sigma Mühendislik ve Fen Bilimleri Dergisi, pp. 1670–1682, 2024. DOI: https://doi.org/10.14744/sigma.2023.00077
P. Manoj, K. C. Manjunath, and P. B. Punith, "ANFIS-Based Traffic Accident Prediction Model for Karnataka State," International Journal of Computational and Experimental Science and Engineering, vol. 11, no. 2, May 2025. DOI: https://doi.org/10.22399/ijcesen.2137
Accident-Data-Set-1. (2025), P. Manoj. [Online]. Available: https://github.com/manojp2690/Accident-Data-Set-1.git.
Downloads
How to Cite
License
Copyright (c) 2025 P. Manoj, K. C. Manjunath, Punith B. Kotagi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
