An Atms Accident Prediction Model Using Traffic And Rain Data

Growing concern over traffic safety has led to research efforts directed towards predicting freeway accidents in ATMS (advanced traffic management systems) environment. This study aims at developing accident likelihood prediction model using real-time traffic flow variables and rain data potentially associated with accident occurrence. Archived loop detector and rain data and historical accident data have been used to calibrate the model. This model can be implemented using on-line loop and rain data to identify high accident potential in real-time. Principal Component Analysis (PCA) and Logistic Regression have been used to estimate a weather model that determines a rain index based on the rain readings at the weather station in the proximity of the freeway. A logit model has also been used to model the accident potential based on traffic loop data and the rain index. The 5-minute average occupancy and standard deviation of volume observed at the downstream station, and the 5-minute coefficient of variation in speed at the station closest to the accident, all during 5-10 minutes prior to the accident occurrence along with the rain index have been found to affect the accident occurrence most significantly.