Predicting Real-time Crash Risks during Hurricane Evacuation Using Connected Vehicle Data

Hurricane evacuations generate high traffic demand with increased crash risk. To mitigate such risk, transportation agencies can adopt high-resolution vehicle data to predict real-time crash risks. Previous crash risk prediction models mainly used limited infrastructure sensor data without covering many road segments. In this article, we present methods to determine potential crash risks during hurricane evacuation from an emerging alternative data source known as connected vehicle data that contain vehicle speed and acceleration information collected at a high frequency (mean = 14.32, standard deviation = 6.82 s). The dataset was extracted from a database of connected vehicle data for the evacuation period of Hurricane Ida on Interstate-10 in Louisiana. Five machine learning models were trained considering weather features and different traffic characteristics extracted from the connected vehicle data. The results indicate that the Gaussian process boosting and extreme gradient boosting models outperform (recall = 0.91) other models. Such real-time crash prediction models, leveraging connected vehicle data, could enable transportation agencies to implement proactive countermeasures, such as dynamic speed limit or lane management, during emergency evacuations, thereby enhancing road safety.