Leveraging Social Digital Twin Technology to Maximise Sustainable Transformation from Multimodality: A Case Study of Commuters to Greater London

Mobility hubs facilitate the transition to sustainable modes of transportation providing new multimodal options to travellers by offering better alternatives to private car usage. However, designing mobility hub schemes to maximise sustainable transformation remains a challenge for transport planners, especially in complex transportation environments like commuter towns servicing large urban centres. In this work, we demonstrate a methodology that combines spatial modelling of commuter mobility with human behaviour predicted by a deep learning component (Behaviour Selection Modelling). Our methodology models travel behaviour and can be used to predict how travellers react to mobility interventions whilst considering the objectives of multiple stakeholders. We present a case study in Reading, United Kingdom, in which we investigate the impact of introducing a new multimodal scheme for commuters travelling to Greater London. With this framework, we can predict the impact of a proposed mobility hub network, determine usage across the network, and survey the parameter space to maximise the shift from private car usage towards sustainable transportation. Leveraging our methodology supports mobility planning and enables transport planners and governments to assess and optimise mobility plans and policies that better promote sustainable mobility.