Today, the data on mobility choices, available options and the contexts in which they are taken is split across data silos in different organizational networks and requires efficient knowledge extraction to be turned into actionable information.
Based on AI models for prediction of future mobility behaviour, citizens can be incentivised to choose more sustainable mobility options in the place of remaining barriers to more sustainable behaviour.
Given the ability to simulate mobility behaviour in different contexts, we can learn which incentive schemes effectively promote sustainable mobility behaviour and will pilot the incentivisation of more sustainable mobility in Industrial Research through the UMM mobile app for citizens and the webLyzard technology visual analytics dashboard for professional stakeholders. To achieve this, we need accurate AI models for mobility and weather prediction.
All AI-based prediction models are making statements about the future based on their input data and the connections found in that data, making explainability important to ensure Trustworthy AI and avoid bias in the training. Allowing for data security and privacy, the sharing and merging of this data via a common mobility data ecosystem would allow new AI models to be trained by Intelligent Systems which learn how and why citizens make certain mobility choices and predict their future mobility choices based on varying contexts such as the availability of more environmentally friendly options.