Spatial Association Between Near-Misses and Accident Blackspots in Sydney, Australia: A Getis-Ord $G_i^*$ Analysis

Abstract: Road safety management teams utilize on historical accident logs to identify blackspots, which are inherently rare and sparse in space and time. Near-miss events captured through vehicle telematics and transmitted in real-time by connected vehicles reveal a unique potential of prevention due to their high frequency nature and driving engagement on the road. There is currently a lack of understanding of the high potential of near-miss data in real-time to proactively detect potential risky driving areas, in advance of a fatal collision. This paper aims to spatially identify clusters of reported accidents (A) versus high-severity near-misses (High-G) within an urban environment (Sydney, Australia) and showcase how the presence of near-misses can significantly lead to future crashes in identified risky hotspots. First, by utilizing a 400m grid framework, we identify significant crash hotspots using the Getis-Ord $G_i^*$ statistical approach. Second, we employ a Bivariate Local Moran's I (LISA) approach to assess and map the spatial concordance and discordance between official crash counts (A) and High-G counts from nearmiss data (High-G). Third, we classify areas based on their joint spatial patterns into: a) High-High (HH) as the most riskiest areas in both historical logs and nearmiss events, High-Low (HL) for high crash logs but low nearmiss records, c) Low-High (LH) for low past crash records but high nearmiss events, and d) Low-Low (LL) for safe areas. Finally, we run a feature importance ranking on all area patterns by using a contextual Point of Interest (POI) count features and we showcase which factors are the most critical to the occurrence of crash blackspots.