Macroscopic Lane Change Model—A Flexible Event-Tree-Based Approach for the Prediction of Lane Change on Freeway Traffic

Binary logistic regression has been used to estimate the probability of lane change (LC) in Cell Transmission Model (CTM). These models remain rigid, as flexibility predict LC for different cell size configurations not accounted for. This paper introduces a relaxation method refine conventional binary model using an event-tree approach. The increasing and length was estimated by expanding pre-defined generated from speed density differences. reliability proposed validated with NGSIM trajectory data. results showed that could accurately slight difference between actual predicted (95% Confidence Interval). Furthermore, comparison prediction performance observations verified model’s ability accuracy 0.69 Area Under Curve (AUC) value above 0.6. able accommodate presence multiple LCs when changes. is worthwhile explore importance such consequences affecting CTM model.