Public transport digitalization: leveraging AI and Digital Twins for smarter urban mobility management
TL;DR
Three European pilot cases from the Interreg CE4CE project are presented to demonstrate that integrating digital monitoring and simulation tools into public transport operations facilitates a shift from reactive to predictive management, directly supporting resource efficiency, asset longevity, and the transition toward a circular urban mobility system.
Abstract
Urban transport systems face mounting pressures from climate change, rising energy prices, and ageing assets. Meeting these challenges sustainably requires extending the useful life of infrastructure, improving energy efficiency, and reducing waste across the whole lifecycle. Circular economy principles offer a systemic approach: design for longevity, maintainability, and reuse, while favouring interventions that avoid resource-intensive renewals. Digitalisation is a key enabler of this shift, as Artificial Intelligence-assisted analytics, edge sensing, and Digital Twins make hidden conditions visible and reduce diagnostic costs. This paper presents three European pilot cases from the Interreg CE4CE project to demonstrate these capabilities. In Leipzig, a layered infrastructure monitoring system enabled the detection of eight critical overhead line faults and three previously undetected broken rails during regular passenger service. In Bergamo, high-frequency onboard sensing and Energy Flow Simulations optimized energy recuperation and identified pantograph-infrastructure “hot spots.” In Gdynia, a Digital Twin environment was used to simulate over 110 electrification scenarios, optimizing fleet size and infrastructure investment needs. The results confirm that integrating digital monitoring and simulation tools into public transport operations facilitates a shift from reactive to predictive management, directly supporting resource efficiency, asset longevity, and the transition toward a circular urban mobility system.