The Coordinated Project  ACoSeM@SusTran aims to expand the frontier of knowledge in Transport Science, contributing to the general goals of defining a demand-oriented supply of transport services and increasing the reliability, connectivity and efficiency of the infrastructure and transport operations. Both will be found in a context of strong competition, uncertainty on socioeconomic variables, and rapidly evolving contour conditions, as regulations and restrictions imposed by the sanitary or government authorities. These goals will be pursued through developing the following descriptive, predictive and prescriptive tasks:

• On the descriptive side, mathematical and simulation models will be designed to describe troublesome issues such as Nash equilibrium at different and variable environment settings. At the same time, these models will be able to address entries of new competitors and model the behaviour of complex systems to perform further analysis and validations.
• In the predictive area, holistic demand modelling and forecasting approaches will be addressed, including awareness of substantial uncertainty on socioeconomic variables, regulations, and restrictions. Similarly, stochastic techniques at the strategic level will be employed such that long-term decisions can be made informed with accurate predictions.
• In the prescriptive field, designing and implementing plans considering competition effects and uncertainty will enable operators to diversify their offers and adapt to deregulated and highly variable contexts. Similarly, the infrastructure manager can adapt to this uncertainty and competition effects from strategic and tactical points of view. 

This project also contributes at an operational level, providing solutions to increase the efficiency and reliability of the route management and then reduce costs and environmental impact.

This Coordinated Project is composed by 3 subprojects:

• PID2020-112967GB-C31: Meeting Optimization and Machine Learning for Railway Transport and Urban Mobility Planning and Management.
• PID2020-112967GB-C32: Meeting Artificial Intelligence and Machine Learning for Rail Passenger Service Planning under Competition.
• PID2020-112967GB-C33: Meeting Operations Research and Machine Learning for Efficient Planning, Management and Control at Air Transport Mobility.

• Meet the team →