Enhanced resilience in multimodal passenger transport through digital technologies and generative and discriminative AI

Expected Outcome: Project results are expected to contribute to all the following expected outcomes: Development of systems that utilize real-time data analytics to dynamically respond to disruptions, allowing transport and infrastructure operators to adjust operations swiftly and efficiently; Development of predictive maintenance strategies applying innovative Generative AI solutions and utilizing other digital technologies to anticipate and prevent infrastructure and equipment failures; Development of guidelines and tools to support passenger transport operators and authorities to ensure minimal disruption in unexpected and critical situations and organise real life emergency simulations; Deployment of training programme for transport and infrastructure operators on how to handle transport disruption, including tools and catalogue with contingency planning for specific transport disruptions; Reduction of average passenger delay at corridor level (at least 20%) during planned disruptions, compared to the baseline and of (at least 40%) time needed from the generation to the dissemination of a response plan to different stakeholders (e.g. transport operators, passengers, citizens) during unplanned and critical events, compared to the baseline. Scope: Passenger transport systems are a critical component of urban, sub-urban, and long-distance travel, facilitating connectivity, reducing traffic congestion, and supporting environmental sustainability. However, these systems face…