Transport businesses aim to provide reliable services in a booming market but often face inflexibility due to disruptions and unavoidable situations. These disruptions can quickly affect the efficiency of the network, and disruption management is necessary to revise the original operating plan. Artificial intelligence and machine learning can help planners and managers understand transportation system performance. This research study focuses on using machine learning algorithms to predict arrival times in real time for a reliable intermodal transport network. The study develops new models that integrate multiple prediction models to create a structured prediction model for the entire network, which is unusual in current literature. Additionally, capacity utilization will be taken into account to determine the connected mode of transportation, with a learning-based route selection model being introduced.
Elham Ahmadi is a Research Associate and PhD candidate at the Kühne Logistics University, working under the supervision of Prof. Dr. André Ludwig and Prof. Dr Henrik Leopold since April 2022. Her research focuses on the application of Machine Learning in Logistics and Supply Chain Management. She is currently contributing to the "CargoSurfer" project funded by the Federal Ministry of Transport and Digital Infrastructure, which aims to develop a digital platform based on machine learning prediction for an intermodal transportation system.