Identification of traffic crash hot spots is of great importance for improving roadway safety and maintaining the transportation system’s sustainability. Traditionally, police crash reports (PCR) have been used as the primary source of crash data in safety studies. However, using PCR as the sole source of information has several drawbacks. For example, some crashes, which do not cause extensive property damage, are mostly underreported. Underreporting of crashes can significantly influence the effectiveness of data-driven safety analysis and prevent safety analysts from reaching statistically meaningful results. Crowdsourced traffic incident data such as Waze have great potential to complement traditional safety analysis by providing user-captured crash and traffic incident data. However, using these data sources also has some challenges. One of the major problems is data redundancy because many people may report the same event. In this paper, the authors explore the potential of using crowdsourced Waze incident reports (WIRs) to identify high-risk road segments. The researchers first propose a new methodology to eliminate redundant WIRs. Then, the researchers use WIRs and PCRs from an I-35 corridor in North Texas to conduct the safety analysis. Results demonstrated that WIRs and PCRs are spatially correlated; however, their temporal distributions are significantly different. WIRs have broader coverage, with 60.24 percent of road segments in the study site receiving more WIRs than PCRs. Moreover, by combining WIRs with PCRs, more high-risk road segments can be identified (14 miles) than the results generated from PCRs (8 miles).
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited