People have numerous mobility options for how they can travel to cities like London; however, there isn’t a single mobile application that helps them make their decision that considers cost, journey times, and ease of travel, for example, across multiple modes and to suit personal preferences.
Extensive digital data on different transport modes isn’t readily available at the moment. For instance, if someone chooses to drive to a local railway station and take a train into London, will a parking space be available? And how much will they pay for parking? Or if instead they drive all the way into the city, how much traffic will they encounter, and how will they know where to park?
As part of a pilot study on multimodality transport initiated by the World Business Council for Sustainable Development (WBCSD), Arcadis and Fujitsu used data from multiple sources, including Transport for the South East, Beryl, and CoMoUK to look at how digital technology solutions and city policies could be introduced and leveraged to improve travel experiences for commuters and lower carbon emissions by reducing car use and encouraging sustainable urban mobility choices.
Leveraging big data and AI, we modeled travel demand using Fujitsu's 'Smart Space powered by Social Digital Twin' solution to test different measures that could be introduced to positively influence customer behavior in Reading, a town outside London. Social Digital Twin offers a new technology that combines behavioral economics models and AI to generate simulations that mirror the behavior of people in the real world. We used it to predict the impact of different policies and intervention scenarios on the customer’s choice of transport mode.
Our first step was understanding existing commuting behavior, and we carried out an initial survey across businesses in London to understand commuting habits and private car use, as well as influencing factors. We asked what policy interventions could encourage people to shift their choices and use more sustainable methods of transport for their commute.
The study provides valuable insights into commuting patterns and how mobility hubs and other measures can influence travel behavior towards more sustainable modes of travel that also deliver better experiences for people and reduce the impact on the environment.
The project shows how using AI and Social Digital Twin to model transport scenarios—and having a strong culture of digital collaboration and sharing data between organizations and service providers—we can better understand policy levers that will reduce private car use and thus carbon emissions in South East London.
It also demonstrates how digital tools, such as Arcadis’ ArcGIS Pro Scenario Tool, can improve optimization of transport infrastructure and capital investments by leveraging data to select the ideal locations for mobility hubs. By incorporating demographic data with locations of key transportation services using GIS modelling, we’ve shown how planners and service providers can match mobility hub locations to a more precise picture of the local travel needs of commuters.
We are proud of our pilot providing the value of integrating data shared by multiple MaaS stakeholders, achieving both decarbonization and enhanced transportation convenience.
Create a better future with us
