Quantitative Analysis of Factors Influencing Vulnerable Road User Crash Frequency on Rural Roads via Random Forest Modeling (Case Study: Isfahan Province)

Document Type : Original Article

Authors
Ali Tavakoli Kashani 1
Mohammad Najafpour Derav 2
Mahdi Heydari 3
Moied Zehbion 4
1 Associate Professor, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran and Road Safety Research Center, Iran University of Science and Technology, Tehran, Iran.
2 Ph.D., Stud., School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran and Road Safety Research Center, Iran University of Science and Technology, Tehran, Iran.
3 M.Sc., Student, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran.
4 M.Sc., Grad., School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran.
10.22034/road.2025.556982.2448
Abstract
Vulnerable road users (VRUs), including pedestrians and motorcyclists, are among the most at-risk groups in the transportation system and account for a significant share of road traffic fatalities. This study aims to identify the key determinants of crash frequency among these users on rural roads in Isfahan Province by employing a data-driven approach and the Random Forest machine learning model. The dataset comprises 14,875 crashes, 19% of which resulted in injury or fatality for VRUs, along with information collected from 400 road segments through field surveys covering more than 15,000 kilometers of the provincial road network. Modeling results indicate that traffic volume has the most substantial positive impact on the likelihood of VRU crashes, while the share of heavy vehicles in the traffic stream shows a nonlinear relationship with crash frequency. The findings further reveal that two-lane roads exhibit higher VRU crash rates due to limited capacity and traffic interactions, whereas on highways, higher speeds and crossing difficulties increase collision risks. Moreover, factors such as population density, road segment length, and the number of students in each area were found to positively influence crash frequency. Based on the study findings, implementing speed control measures on high-traffic routes, segregating heavy vehicle lanes, providing safe pedestrian crossings on multilane roads, and strengthening traffic enforcement in densely populated areas are identified as key strategies for mitigating VRU crash risks.
Keywords
Vulnerable Road Users
Motorcyclists
Pedestrians
Road Safety
Random Forest Model
-(1402). آمار متوفیات و مصدومین حوادث رانندگی در سال 1402.
 
-Al-Nuaimi, A. and A.K. Jameel.  (2023). An Impact of Traffic Characteristics on Crash Frequency. in E3S Web of Conferences.
 -Analysis, N.C.f.S.a.,  (2017). Bicyclists and other cyclists: 2015 data., in Traffic Safety Facts.
-Breiman, L., Random forests. (2001). Machine learning, 45: 5-32.
-Budzynski, M., et al. (2019). Effects of Road Infrastructure on Pedestrian Safety. in IOP Conference Series, Materials Science and Engineering.
-Lee, C. and M. Abdel-Aty, (2005). Comprehensive analysis of vehicle-pedestrian crashes at intersections in Florida. Accident Analysis and Prevention, 37(4), 775-786.
-Manullang, O.R., et al. (2019). Changes of landuse in the campus area and their implications toward traffic condition. in IOP Conference Series, Earth and Environmental Science.
 -Mohan, D., (2016). Speed and its effects on road traffic crashes, in Transport Planning and Traffic Safety: Making Cities, Roads, and Vehicles Safer. 127-135.
-Neri, T.B. and C.A.P. da Silva, (2023).The Barrier Effect of Urban Highway and the Impacts on Mobility and Transport Expenses. Urbe.
  -Parikh, P., et al. (2024). Impact of Road Infrastructure on VRU Safety: A Case–Control Study. in Lecture Notes in Civil Engineering.
-Popa, Ș., et al., (2023). Current Epidemiological Trends of Pediatric Traffic Accidents at a Romanian Clinical Hospital. Children, 10(9).
-Retallack, A.E. and B. Ostendorf, (2020). Relationship between traffic volume and accident frequency at intersections. International Journal of Environmental Research and Public Health, 17(4).
-Shawky, M.A., A.M. Garib, and H. Al-Harthei, (2014). The impact of road and site characteristics on the crash-injury severity of pedestrian crashes. Advances in Transportation Studies, (special issue):27-36.
-V S, V. and V. Perumal, (2024). Analysis of crash severity in rear-end and angle collisions on an urban roundabout in heterogeneous non-lane-based traffic conditions. Transportation Letters.
-World Health, O., (2023). Global status report on road safety 2023. Geneva: World Health Organization.
-Yan, M. and Y. Shen, (2022). Traffic accident severity prediction based on random forest. Sustainability, 14(3):1729-1730.
-Yu, C.Y. and X. Zhu, (2016). Planning for Safe Schools: Impacts of School Siting and Surrounding Environments on Traffic Safety. Journal of Planning Education and Research, 36(4): 476-486.
-Zhu, M., et al., (2022). Exploring the impacts of street layout on the frequency of pedestrian crashes: A micro-level study. Journal of Safety Research, 81: 91-100.