Assessing safety in horizontal curves using surrogate safety measures and machine learning

Abstract

Horizontal curves (HCs) are one of the most safety-critical elements of the road. Crashes are rare events and working with them is challenging. Surrogate safety measures (SSM) can be suitable substitutes for them. In this paper, with the help of a decision tree algorithm and SSMs; the impact of different variables is assessed on the safety of HCs. A variety of variables relevant to drivers' characteristics, HC specifications, and the environment are considered in order to assess the role they play in HC safety. SSMs and machine learning have not been used to assess the safety of HCs comprehensively. The method is applied for a case study on the rural roads in Iran. Results indicate that the curve radius and speed in the tangent section before the HC have the most significant impact on its safety. The critical threshold for these variables were determined as 358 m and 23 m/s, respectively. The most critical characteristics of a driver when it comes to safely handling HCs are their driving experience, their crash history and education level. The environmental condition did not have a significant impact on HC's safety.

Keywords: Decision tree; Horizontal curve; Modelling; Safety.

Fig. 1

The instrumented vehicle in the present study.

Fig. 2

Research flowchart.

Fig. 3

Gain and Index chart for CHAID model with MDR prediction.

Fig. 4

Gain and Index chart for CRT model with MSD prediction.