Identifying Hazardous Crash Locations Using Empirical Bayes and Spatial Autocorrelation

Abstract

Identifying and prioritizing hazardous road traffic crash locations is an efficient way to mitigate road traffic crashes, treat point locations, and introduce regulations for area-wide changes. A sound method to identify blackspots (BS) and area-wide hotspots (HS) would help increase the precision of intervention, reduce future crash incidents, and introduce proper measures. In this study, we implemented the operational definitions criterion in the Hungarian design guideline for road planning, reducing the huge number of crashes that occurred over three years for the accuracy and simplicity of the analysis. K-means and hierarchical clustering algorithms were compared for the segmentation process. K-means performed better, and it is selected after comparing the two algorithms with three indexes: Silhouette, Davies–Bouldin, and Calinski–Harabasz. The Empirical Bayes (EB) method was employed for the final process of the BS identification. Three BS were identified in Budapest, based on a three-year crash data set from 2016 to 2018. The optimized hotspot analysis (Getis-Ord Gi*) using the Geographic Information System (GIS) technique was conducted. The spatial autocorrelation analysis separates the hotspots, cold spots, and insignificant areas with 95% and 90% confidence levels.