Decision Tree–Based Model for Estimation of Work Zone Capacity

The ability to accurately estimate work zone capacity is imperative, as it is a key input to estimate queue length and traffic delay at work zone. This paper thus aims to develop a decision tree-based model considering 16 influencing factors to accurately estimate work zone capacity. The F-test splitting criterion and the post-pruning approach are employed to grow and prune decision tree, respectively. Work zone capacity data collected from 14 states and cities are used to train, validate and test the decision tree-based capacity estimation model. Statistical comparison results demonstrate that the decision tree-based model outperforms existing short-term and long-term work zone capacity estimation models, especially when the input values of influencing factors are partially available for the existing models. The comparison with the current Highway Capacity Manual also indicates that the decision tree-based model can provide a more accurate estimate of work zone capacity. From the decision tree-based model, traffic engineers can easily estimate work zone capacity for a given work zone by tracing a path down the tree to a terminal node. Because of the high estimation accuracy and ease of use, the proposed decision tree-based capacity model is a good alternative for traffic engineers to estimate work zone capacity.