Journal of Transportation Research

Journal of Transportation Research

Identification of Factors Affecting Motorcycle Crash Severity on Intercity Roads Using the Random Forest (RF) Algorithm and SHAP Analysis

Document Type : Original Article

Authors
Hamed Saify 1
Shahin Shabani 1
Mohammad Koohi 2
1 Department of Civil Engineering‌, Payame Noor University (PNU), Tehran, Iran.
2 M.Sc., Grad., Department of Civil Engineering, Payame Noor University (PNU), Tehran, Iran.
10.22034/tri.2026.567167.3419
Abstract
Motorcycle crashes account for a substantial share of road traffic fatalities due to the high vulnerability of this group of road users, and the severity of their consequences—particularly on intercity roads—has consistently remained one of the major challenges in road safety. The primary objective of this study is to identify and interpret the factors influencing motorcycle crash severity on intercity roads using interpretable machine learning approaches. To this end, three-year motorcycle crash data (2017–2019) from intercity roads in Razavi Khorasan Province were utilized. The explanatory variables were classified into thirteen categories, including road characteristics, geometric conditions, shoulder type, contributing road defects, human factors, at-fault vehicle type, land use, and other environmental and traffic-related factors. In this study, three machine learning algorithms—Random Forest, XGBoost, and LightGBM—were employed to predict crash severity levels (property damage only, injury, and fatal). After data preprocessing and class balancing using the SMOTE method, model performance was evaluated using precision, recall, and F1-score metrics. The results indicated that the Random Forest model achieved superior performance compared to the other models, with an overall accuracy of 76%, and was therefore selected as the optimal model. To interpret the output of the selected model, the SHAP method was applied. The SHAP analysis revealed that shoulder type, at-fault vehicle type, contributing road defects, human factors, land use, posted speed limit, road type, pavement marking condition, and roadway geometry were, respectively, the most influential factors affecting motorcycle crash severity on intercity roads. The findings of this study demonstrate that motorcycle crash severity results from a complex interaction of infrastructural, behavioral, and vehicle-related factors, and that adopting severity-oriented approaches in road safety planning can play an effective role in reducing severe crash outcomes.
Keywords
Motorcycle Crashes
Random Forest (RF)
SHAP Analysis
Subjects
-Akter, R., Susilawati, S., Zubair, H., Chor, W, T., (2025). Analyzing feature importance for older pedestrian crash severity: A comparative study of DNN models, emphasizing road and vehicle types with SHAP interpretation, Multimodal Transportation, 4, 100203.
-Amiri, A.M., Sadri, A., Nadimi, N., Shams, M., (2020). A comparison between Artificial Neural Network and Hybrid Intelligent Genetic Algorithm in predicting the severity of fixed object crashes among elderly drivers. Accid. Anal. Prev. 138, 105468.
-Assi, K., Rahman, S.M., Mansoor, U., Ratrout, N., (2020), Predicting crash injury severity with machine learning algorithm synergized with clustering technique: a promising protocol. Int. J. Environ. Res. Publ. Health 17, 5497.
-Breiman, L., (2001). Random forests. Machine Learning, 45 (1), 5–32.
-Brockhusa, L. A., Liasidisb, P., Lewisb, M., Jakoba, D. A., Demetriadesb, D., (2024). Injury patterns and outcomes in motorcycle driver crashes in the United States: The effect of helmet use, Injury, 55, 111196.
-Chai, A. B. Zh., Lau, B. T., Tee, M. K. T., McCarthyb, C., (2024). Enhancing road safety with machine learning: Current advances and future directions in accident prediction using non-visualdata, Engineering Applications of Articial Intelligence, 137, 109086.
-Champahom, T., Se, CH., Watcharamaisakul, F., Jomnonkwao, S., Karoonsoontawong, A., Ratanavaraha, V., (2024). Tree-based approaches to understanding factors influencing crash severity across roadway classes: A Thailand case study, IATSS Research 48, 464–476.
-Chang, F., Li, M., Xu, P., Zhou, H., Haque, M., Huang, H., (2016). Injury severity of motorcycle riders involved in traffic crashes in Hunan, China: a mixed ordered logit approach, Int. J. Environ. Res. Public Health, 13, 714.
-Chen, M.M. Chen, M.C., (2020), Modeling road accident severity with comparisons of logistic regression, decision tree and random forest, Inf. 11.
-Chen, T., Guestrin, C., (2016). XGboost:A scalable tree boosting system, in proceeding of the 22nd ACM SIGKDD Conference,785-794.
-Cunto, F.J.C., Ferreira, S., (2017). An analysis of the injury severity of motorcycle crashes in Brazil using mixed ordered response models, J. Transp. Saf. Secur, 9, 33–46.
-Donchenko, D., Sadovnikova, N., Parygin, D., (2020). Prediction of road accidents’ severity on Russian roads using machine learning techniques. In: Proceedings of the 5th International Conference on Industrial Engineering (ICIE 2019). Springer,1493–1501.
-Fiorentini, N., Losa, M., (2020). Handling imbalanced data in road crash severity prediction by machine learning algorithms. Infrastructure 5, 61.
-Fondzenyuya, S. K., Usamia, D. SH., Gonz´alez-Hern´andezb, B., Brownc, L., Morrisc, A., Persia, L., (2024). Developing improved crash prevention approaches through in-depth investigation of motorcycle crash causation patterns, Heliyon10, e32866.
-Ghasedi, M., Sarfjoo, M., Bargegol, I., (2021). Prediction and analysis of the severity and number of suburban accidents using Logit model, factor analysis and machine learning: a case study in a developing country. SN Appl. Sci. 3, 13.
-Hadjidimitriou, N.S., Lippi, M., Dell’Amico, M., Skiera, A., (2019). Machine learning for severity classification of accidents involving powered two wheelers, IEEE Trans. Intell. Transp. Syst. 21, 4308–4317.
-Haruna, L., Sallehuddin, R., Radzi, H.M., (2020). Discrete particle swarm optimization based filter feature selection technique for the severity of road traffic accident prediction.
In: Advances in Intelligent Systems and Computing, Springer.
-Hasan, A. S., Jalayer­, M., Das­, S., Bin Kabir, A., (2024). Application of machine learning models and SHAP to examine crashes involving young drivers in New Jersey, International Journal of Transportation Science and Technology, 14, 156–170.
-Hsu, C. K., (2024). Heat-induced risks of road crashes among older motorcyclists: Evidence from three motorcycle-dominant cities in Taiwan, Journal of Transport & Health, 35, 101754.
-Ijaz, M., lan, L., Zahid, M., Jamal, A., (2021). A comparative study of machine learning classifiers for injury severity prediction of crashes involving three-wheeled motorized rickshaw. Accid. Anal. Prev. 154, 106094.
-Infante, P., Jacinto, G., Afonso, A., Rego, L., Nogueira, V., Quaresma, P., Saias, J., Santos, D., Nogueira, P., Silva, M., Costa, R.P., Gois, P., Manuel, P.R., (2022). Comparison of statistical and machine-learning models on road traffic accident severity classification. Computers 11, 80.
-Kashifi, M. T., (2023), Investigating two-wheelers risk factors for severe crashes using an interpretable machine learning approach and SHAP analysis, IATSS Research 47, 357–371.
-Kashifi, M. T., Ahmad, I.., (2022). Efficient histogram-based gradient boosting approach for accident severity prediction with multisource data, Transp. Res. Rec, 036119812210743.
-Ke, G., Meng, Q., Finely, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.-Y., (2017). LightGBM: A highly efficient gradient boosting decision tree, Advances in Neural Information Processing Systems, 30.
-Khan, M.N., Das, A., Ahmed, M.M., (2024). Prediction of truck-involved crash severity on a rural mountainous freeway using transfer learning with ResNet-50 deep neural network. J Transp Eng a Syst 150, 04023131.
-Lanzaro, G., Andrade, M., (2023). Afuzzy expert system for setting Brazilian highway speed limits, International Journal of Transportation Science and Technology, 12, 505-524.
-Lapparent, M. de, (2006). Empirical Bayesian analysis of accident severity for motorcyclists in large French urban areas, Accid. Anal. Prev. 38, 260–268.
-Ma, Z., Mei, G., Cuomo, S., (2021), An analytic framework using deep learning for prediction of traffic accident injury severity based on contributing factors, Accid. Anal. Prev. 160.
 -Montellaa, A., Calvib, A., D’Amicob, F., Ferranteb, C., Galantea, F., Maurielloa, F., Riccardia, M, R., Scaranoa, A., (2024). A methodology for setting credible speed limits based on numerical analyses and driving simulator experiments, Transportation Research Part F: PsychologyandBehaviour, 100, 289–307.
-Naqvi, H. M., Tiwari, G., (2017), Factors Contributing to Motorcycle Fatal Crashes on National Highways in Inda, Transportation Research Procedia, 25, 2084–2097.
-Pai, C.W., Saleh, W., (2007). An analysis of motorcyclist injury severity under various traffic control measures at three-legged junctions in the UK, Saf. Sci., 45, 832–847.
-Pai, C.-W., Saleh, W., (2008). Modelling motorcyclist injury severity by various crash types at T-junctions in the UK, Saf. Sci., 46, 1234–1247.
-Panda, C., Mishra, A.K., Dash, A.K., Nawab, H., (2022). Predicting and explaining severity of road accident using artificial intelligence techniques, SHAP and feature analysis. Int. J. Crashworthiness 28, 186–201.
-Panicker, A.K., Ramadurai, G., (2022). Injury severity prediction model for two-wheeler crashes at mid-block road sections, Int. J. Crashworthiness 27, 328–336.
-Parsa, A.B., Movahedi, A., Taghipour, H., Derrible, S., Kouros Mohammadian, A., (2020). Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis, Accid. Anal. Prev. 136.
-Qu, Y., Lin, Z., Li, H., Zhang, X., (2019). Feature recognition of urban road traffic accidents based on GA-XGBoost in the context of big data, IEEE Access 7,  170106–170115.
-Rasria, N., Satiennama, T., Satiennama, W., Sukkhoa, P., Jaensirisakb, S., Kronprasertc, N., Champahomd, T., (2024). Factors influencing wrong way driving behavior of motorcycle riders in Thailand, Transportation Research Interdisciplinary Perspectives, 25, 101122.
-Rezapour, M., Mehrara Molan, A., Ksaibati, K., (2020). Analyzing injury severity of motorcycle at-fault crashes using machine learning techniques, decision tree and logistic regression models. International Journal of Transportation Science and Technology 9, 89–99.
-Rifaat, S.M., Tay, R., De Barros, A., (2012). Severity of motorcycle crashes in Calgary, Accid. Anal. Prev. 49, 44–49.
-Sajid Hasan, A, B., Jalayer, M., Das, S., Kabir, A, B., (2024). Application of machine learning models and SHAP to examine crashes involving young drivers in New Jersey, International Journal of Transportation Science and Technology 14, 156–170.
-Savolainen, P., Mannering, F., (2007). Probabilistic models of motorcyclists’ injury severities in single-and multi-vehicle crashes, Accid. Anal. Prev., 39, 955–963.
-Scarano, A., Sadeghi, M., Mauriello, F, Riccardi, M, R., Aghabayk, K, Montella, A., (2025). Cyclist crash severity modeling: A hybrid approach of XGBoost-SHAP and random parameters logit with heterogeneity in means and variances, Journal of Safety Research, 93, 373–398.
-Shaheed, M.S.B., Gkritza, K., Zhang, W., Hans, Z., (2013). A mixed logit analysis of two- vehicle crash severities involving a motorcycle, Accid. Anal. Prev., 61, 119–128.
-Shapley, L. S. (1953). A value for n-person games. Contrib. Theory Games, 2(28), 307–317.
-Siddik, MdA.B., Arman, MdS., Hasan, A., Jahan, M.R., Islam, M., Biplob, K.B.B., (2021). Predicting the death of road accidents in Bangladesh using machine learning algorithms. In: Communications in Computer and Information Science. Springer Science and Business Media Deutschland GmbH, 160–171.
-Sunkpho, J., Se, C., Wipulanusat, W., Ratanavaraha, V., (2025). SHAP-based convolutional neural network modeling for intersection crash severity on Thailand’s highways, IATSS Research 49, 27–41.
-Tariq, A.-M., Xiao, H., Jean, P.N., Eshrak, N.A., Ibrahim, A., (2020). Exploiting machine learning algorithms for predicting crash injury severity in Yemen: hospital case study. Appl. Comput. Math. 9, 164.
-Wahab, L., Jiang, H., (2019). A comparative study on machine learning based algorithms for prediction of motorcycle crash severity, PLoS One 14, e0214966.
-Wahab, L., Jiang, H., (2020). Severity prediction of motorcycle crashes with machine learning methods. Int. J. Crashworthiness 25, 485–492.
-Wang, X., Zhou, Q., Quddaus, M., Fang, S., (2018). Speed, speed variation and crash relationship for urban arterials, Accid. Anal. Prev., 113, 236-243.
-Wang, Z., Lee, C., Lin, P.-S., (2014). Modeling injury severity of single-motorcycle crashes on curved roadway segments, in: 93rd Annual Meeting of the Transportation Research Board, Washington, DC.
-Xin, C., Wang, Z., Lee, C., Lin, P.-S., (2017). Modeling safety effects of horizontal curve design on injury severity of single-motorcycle crashes with mixed-effects logistic model, Transp. Res. Rec. 2637 38–46.
-Yan, M., Shen, Y., (2022). Traffic accident severity prediction based on random forest, Sustain 14.
-Yoon, J., (2025). Prediction of high-risk areas using the interpretable machine learning: Based on each determinant for the severity of pedestrian crashes, Journal of Transport Geography, 126, 104216.
-Zhang, C., He, J., Wang, Y., Yan, X., Zhang, Changjian, Chen, Y., Liu, Z., Zhou, B., (2020). A crash severity prediction method based on improved neural network and factor analysis. Discrete Dynam Nat. Soc. 1–13.