Journal of Transportation Research

Journal of Transportation Research

Crash Injury Severity Analysis of Familiar and Unfamiliar Drivers on Horizontal Curves of Rural Two-Lane Roads Using GIS and Random Forest Algorithm

Document Type : Original Article

Authors
morteza safari 1
Meysam Effati 2
mahyar arabani 3
1 Department of Civil Engineering (Road and Transportation), Faculty of Engineering, University of Guilan, Rasht, Iran
2 Department of Civil Engineering (Road & Transportation), Faculty of Engineering, University of Guilan, Rasht, Iran
3 Department of Civil Engineering(Road and Transportation), Faculty of Engineering, University of Guilan, Rasht, Iran
10.22034/tri.2024.413567.3181
Abstract
By providing a transition between two straight road segments, horizontal curves play a significant role in the interurban road network. According to statistics, these locations are characterized by high incident and accident rates. The aim of this study is to introduce a geospatial based method for extracting the geometric parameters of horizontal curves on rural two-lane roads using Geospatial Information Systems (GIS) and satellite imagery, as well as identifying accident-prone curves through the utilization of spatial clustering functions and and investigating factors influencing the injury severity of accidents on the horizontal curves of rural two-lane roads based on familiar and unfamiliar drivers, using the Random Forest algorithm. The implementation results of the proposed method on the studied corridor (Rasht - Anzali) indicated that the most significant contributing factors to severity of crashes on accident-prone horizontal curves, which were identified using the kernel density estimation method were collision type and road light condition with coefficients of 0.51 and 0.41 for accidents involving familiar drivers and the factors of daily traffic volume and collision type with coefficients of 0.53 and 0.51 for accidents involving unfamiliar drivers. Factors such as daily traffic volume and driver age for familiar drivers, road surface conditions and road light condition for unfamiliar drivers were recognized as additional influential factors on the severity of crashes of studied corridor's horizontal curves.
Keywords
Spatial Analysis
Random Forest
Rural Two-Lane Roads
Crash Severity
Horizontal Curves

Subjects

-AlThuwaynee, O. F., Kim, S.-W., Najemaden, M. A., Aydda, A., Balogun, A.-L., Fayyadh, M. M., & Park, H.-J. (2021). Demystifying uncertainty in PM10 susceptibility mapping using variable drop-off in extreme-gradient boosting (XGB) and random forest (RF) algorithms. Environmental Science and Pollution Research, 28, 43544–43566.
-Amiri, A. M., Nadimi, N., Khalifeh, V., & Shams, M. (2021). GIS-based crash hotspot identification: a comparison among mapping clusters and spatial analysis techniques. International Journal of Injury Control and Safety Promotion, 28(3), 325–338.
-Azari, M., Paydar, A., Feizizadeh, B., & Hasanlou, V. G. (2023). A GIS-based approach for accident hotspots mapping in mountain roads using seasonal and geometric indicators. Applied Geomatics, 15(1), 127–139.
-Beijer, D., Smiley, A., & Eizenman, M. (2004). Observed driver glance behavior at roadside advertising signs. Transportation Research Record, 1899(1), 96–103.
-Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114,
24–31. doi.org/https://doi.org/10.1016/j.isprsjprs.2016.01.011
-Bertola, M. A., Balk, S. A., & Shurbutt, J. (2012). Evaluating driver performance on rural two-lane horizontal curved roadways using a driving simulator. United States. Federal Highway Administration.
-Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.
-Didin, F. S., & Iridiastadi, H. (2020). Risk factors for rear-end collision: a systematic literature review. IOP Conference Series: Materials Science and Engineering, 909(1), 012076.
-Eboli, L., Forciniti, C., & Mazzulla, G. (2020). Factors influencing accident severity: an analysis by road accident type. Transportation Research Procedia, 47, 449–456. doi.org/https://doi.org/10.1016/j.trpro.2020.03.120
-Effati, M., & Atrchian, C. (2024). Considering the Reliability of Police-Reported Weather Information on Freeways Traffic Crash Severity Analysis: Proposing a Mixed Statistical and Geospatial Solution. Transportation in Developing Economies, 10(2), 30.
-Effati, M., Thill, J. C., & Shabani, S. (2015a). Geospatial and machine learning techniques for wicked social science problems: analysis of crash severity on a regional highway corridor. Journal of Geographical Systems, 17, 107-135.
-Effati, M., Rajabi, M. A., Hakimpour, F., & Shabani, S. (2015b). Prediction of crash severity on two-lane, two-way roads based on fuzzy classification and regression tree using geospatial analysis. Journal of Computing in Civil Engineering, 29(6), 04014099.
-Elyassami, S., Hamid, Y., & Habuza, T. (2021). Road crashes analysis and prediction using gradient boosted and random forest trees. 2020 6th IEEE Congress on Information Science and Technology (CiSt), 520–525.
-Federal Highway Administration (FHWA). (2010). Roads and curves, 2005–2008. FHWA Office of Safety, Washington, DC. (n.d.).
-Findley, D., Zegeer, C., Sundstrom, C., Hummer, J., & Rasdorf, W. (2012). Applying the Highway Safety Manual to two-lane road curves. Journal of the Transportation Research Forum, 51(1424-2016–117840), 25–38.
-Flach, P. (2012). Machine learning: the art and science of algorithms that make sense of data. Cambridge university press.
-Gooch, J. P., Gayah, V. v, & Donnell, E. T. (2018). Safety performance functions for horizontal curves and tangents on two lane, two way rural roads. Accident Analysis & Prevention, 120, 28–37.
-Harootunian, K., Aultman-Hall, L., & Lee, B. H. Y. (2014). Assessing the relative crash fault of out-of-state drivers in Vermont, USA. Journal of Transportation Safety & Security, 6(3), 207–219.
-Harootunian, K., Lee, B. H. Y., & Aultman-Hall, L. (2014). Odds of fault and factors for out-of-state drivers in crashes in four states of the USA. Accident Analysis & Prevention, 72, 32–43. doi.org/10.1016/j.aap.2014.06.01
-Harootunian, K., Lee, B. H. Y., & Aultman-Hall, L. (2015). Fault determination for crashes in Vermont: implications of distance from home. Transportation Research Record, 2514(1), 97–104.
-Hummer, J. E., Rasdorf, W., Findley, D. J., Zegeer, C. v, & Sundstrom, C. A. (2010). Curve collisions: road and collision characteristics and countermeasures. Journal of Transportation Safety & Security, 2(3), 203–220.
-Intini, P., Berloco, N., Colonna, P., Ranieri, V., & Ryeng, E. (2018). Exploring the relationships between drivers’ familiarity and two-lane rural road accidents. A multi-level study. Accident Analysis & Prevention, 111, 280–296.
-Katicha, S. W., & Flintsch, G. W. (2023). A kernel density empirical Bayes (KDEB) approach to estimate accident risk. Accident Analysis & Prevention, 186, 107039.
doi.org/https://doi.org/10.1016/j.aap.2023.107039
-Khan, I. U., Vachal, K., Ebrahimi, S., & Wadhwa, S. S. (2023). Hotspot analysis of single-vehicle lane departure crashes in North Dakota. IATSS Research, 47(1), 25–34. doi.org/10.1016/j.iatssr.2022.12.003
-Khattak, A. J., & Shamayleh, H. (2005). Highway safety assessment through geographic information system-based data visualization. Journal of Computing in Civil Engineering, 19(4), 407–411.
-Liang, O. S., & Yang, C. C. (2022). How are different sources of distraction associated with at-fault crashes among drivers of different age gender groups? Accident Analysis & Prevention, 165, 106505.doi.org/10.1016/j.aap.2021.106505
-Liu, C., & Ye, T. J. (2011). Run-off-road crashes: An on-scene perspective.
-Ma, Z., Lu, X., Chien, S. I.-J., & Hu, D. (2018). Investigating factors influencing pedestrian injury severity at intersections. Traffic Injury Prevention, 19(2), 159–164.
-Mekonnen, A. A., Sipos, T., & Krizsik, N. (2023). Identifying Hazardous Crash Locations Using Empirical Bayes and Spatial Autocorrelation. ISPRS International Journal of Geo-Information, 12(3), 85.
-Peng, Z., Wang, Y., & Wang, L. (2021). A comparative analysis of factors influencing the injury severity of daytime and nighttime crashes on a mountainous expressway in China. International Journal of Injury Control and Safety Promotion, 28(4), 503–512.
-Quddus, M. (2015). Effects of geodemographic profiles of drivers on their injury severity from traffic crashes using multilevel mixed-effects ordered logit model. Transportation Research Record, 2514(1), 149–157.
-Retallack, A. E., & Ostendorf, B. (2020). Relationship between traffic volume and accident frequency at intersections. International Journal of Environmental Research and Public Health, 17(4), 1393.
-Safari, M., Effati, M., & Arabani, M. (2024). Spatial analysis of daytime and nighttime crash severity on horizontal curves of mountainous rural highways: A case study in Northern Iran. Results in Engineering, 24, 103344.
-Santos, K., Dias, J. P., & Amado, C. (2022). A literature review of machine learning algorithms for crash injury severity prediction. Journal of Safety Research, 80, 254–269.
-Shahi, S., Brussel, M., & Grigolon, A. (2023). Spatial analysis of road traffic crashes and user based assessment of road safety: A case study of Rotterdam. Traffic Injury Prevention, 1–10.
-Tamakloe, R. (2023). Risk Factors Influencing Fatal Powered Two-Wheeler At-Fault and Not-at-Fault Crashes: An Application of Spatio-Temporal Hotspot and Association Rule Mining Techniques. Informatics, 10(2), 43.
-Tamakloe, R., & Park, D. (2023). Factors influencing fatal vehicle-involved crash consequence metrics at spatio-temporal hotspots in South Korea: Application of GIS and machine learning techniques. International Journal of Urban Sciences, 27(3), 483–517.
-Vahedi Saheli, M., & Effati, M. (2021). Segment-based count regression geospatial modeling of the effect of roadside land uses on pedestrian crash frequency in rural roads. International Journal of Intelligent Transportation Systems Research, 19, 347-365.
-Wen, H., Ma, Z., Chen, Z., & Luo, C. (2023). Analyzing the impact of curve and slope on multi-vehicle truck crash severity on mountainous freeways. Accident Analysis & Prevention, 181, 106951.
-Wen, H., & Xue, G. (2020a). Exploring the relationships between single-vehicle traffic accident and driver’s route familiarity on the mountainous highways. Cognition, Technology & Work, 22, 815–824.
-Wen, H., & Xue, G. (2020b). Exploring the relationships between single-vehicle traffic accident and driver’s route familiarity on the mountainous highways. Cognition, Technology & Work, 22, 815–824.
-Wen, H., & Xue, G. (2020c). How to Measure Driver’s Route Familiarity. In CICTP 2020,  4620–4632.
-Wen, H., & Xue, G. (2020d). Injury severity analysis of familiar drivers and unfamiliar drivers in single-vehicle crashes on the mountainous highways. Accident Analysis & Prevention, 144, 105667.
-World Health Organization (WHO). Available from https://www.who.int. (n.d.).
-Wu, L., Lord, D., & Geedipally, S. R. (2017). Developing crash modification factors for horizontal curves on rural two-lane undivided highways using a cross-sectional study. Transportation Research Record, 2636(1), 53–61.
-Yang, J., Han, S., & Chen, Y. (2023). Prediction of Traffic Accident Severity Based on Random Forest. Journal of Advanced Transportation.
-Zegeer, C., Reinfurt, D., Neuman, T., Stewart, R., & Council, F. (1991). Safety improvements on horizontal curves for two-lane rural roads-Informational guide.
-Zegeer, C. v, Stewart, J. R., Council, F. M., Reinfurt, D. W., & Hamilton, E. (1992). Safety effects of geometric improvements on horizontal curves. Transportation Research Record, 1356.