This study presents a model to characterize changes in network traffic flows as a result of implementing connected and autonomous vehicle (CAV) technology based on traffic network and built-environment characteristics. To develop such a model, first, the POLARIS agent-based modeling platform is used to predict changes in average daily traffic (ADT) under CAV scenario in the road network of Chicago metropolitan area as the dependent variable of the model. Second, a comprehensive set of variables and indicators representing network characteristics and urban structure patterns are generated. Finally, three machine learning techniques, namely, K-Nearest neighbors, Random Forest, and eXtreme Gradient Boosting, are used to characterize changes in ADT based on network characteristics under a CAV scenario. The estimated models are validated and are found to yield acceptable performance. In addition, SHapley Additive exPlanations (SHAP) analysis tool is employed to investigate the impact of important features on changes in ADT.
13 August 2025 in Transportation Research Part D: Transport and Environment
The supplier selection process is one of the main components of the Freight Activity Microsimulation Estimator (FAME), which is a disaggregated and comprehensive framework that simulates the freight movements for all industries and all commodities in the U.S. However, the supplier selection and supplier evaluation models in the FAME face computational issues. Using the result of a nationwide establishment survey, this study analyzes the supplier selection problem by evaluating the potential suppliers. The buyer’s behavior on selecting the distance range in which the trade forms is analyzed using both machine-learning and statistical approaches. A decision-tree model and an ordered probit model are estimated and compared to better comprehend the supplier evaluation process. The results indicate that several factors such as the type of the business, commodity type, number of orders, and the value of orders are significant factors. In addition, the decision-tree model is reliable in forecasting the consumer’s behavior.
18 September 2026 in Sustainable Cities and Society