Key points are not available for this paper at this time.
Intermodal transport is essential for optimizing supply chains and promoting sustainability. However, previous studies often treat demand forecasts, efficiency evaluation, and delivery scheduling separately, lacking an integrated approach. This study aims to develop a data-driven framework optimizing intermodal transport route selection by integrating three modules:(1) a rolling demand forecasting model based on XGBoost to predict demands, (2) a Range Adjusted Measure (RAM) model to evaluate intermodal route efficiency considering operating cost, fuel consumption, customer satisfaction, and carbon emissions, and (3) a Dynamic Delivery Point (DDP) model to determine optimal dispatch times. A real case study from Qingdao to Chongqing verifies the framework’s effectiveness. The optimal route, leveraging water and rail transport, achieves a super-efficiency score of 1.1189, outperforming road-based alternatives. The results confirm that the framework improves forecast accuracy, enhances efficiency, supports just-in-time delivery, and reduces costs and emissions. This paper provides valuable insights into intermodal transport route selection.
Xiang et al. (Mon,) studied this question.