INDIUM

Nom du projet :
INtelligent Data orIented sUstainable Metropolis

Financement :
CY Initiative

Durée du projet :
2025 - 2028

Responsable du projet au sein du laboratoire MATRiS :
Liu Liu
 

In the Greater Paris Region, 32% of Greenhouse Gas (GHG) emissions come from road transport. More than half of these emissions owes to private personal vehicles, and only the other little half is linked to the use of heavyweight and commercial vehicles. This large amount of emissions is directly due to the emission characteristics of vehicles, but induced inherently from the dispersal of economic activities to increasingly distant suburbs. Since Covid19, families tend to choose more remote suburbs, which may leads to more kilometres travelled, thus more emissions.
The relocation phenomenon is, indeed, an essential indicator of lifestyles modifications. With parallel phenomena (such as transport mode change, e-commerce, remote working), they might have conjoint effects over our territory: not only on emissions, but also on social interactions – that is – the way that we produce and consume, as well as the inefficiency of land use. While decision-makers are aware of the urgent need to reorganize our metropolis spatially, they are rarely equipped with suitable tools, thus, appropriate data to manage the mobility demand, as well as to control immobility.

We would support decision-makers by developing necessary methodologies and datasets to support long-term prospective studies, based on scenarios involving reliable hypotheses. Firstly, through a collection, organization, quality control, correlation and analysis of selected datasets, we complete the current Activity-Mobility-Chain by adding the emissions characteristics of vehicles and functional use of land to the existed Synthetic Population. Secondly, our elaboration of future hypotheses is based on most advanced methods in data engineering such as Machine Learning (ML) and Artificial Intelligence (AI), requiring a real methodological transformation in urban sciences. By preparing and training vehicle data and functional use of land data, we combine the predictive and analytical powers of ML and AI tools, in order to model and assess choices made by economic entities (individuals, households and businesses) and their emissions’ features, especially the potential effects of location-mobility choices towards sustainability.
Two questions are addressed in INDIUM:
How (re)location choices of households and firms, accompanied by mobility choices, generate
environmental externalities ? What planning mechanisms are determinant in relocation choices and mobility choices that lead to sustainability ?
Thanks to INDIUM, we expect to better understand our Greater Paris Region, and extend our knowledge to other megalopolis in terms of strategic planning and prospective evaluations.


 
Membres impliqués
  • Liu Liu
  • Geneviève Zembri-Mary
  • Rémy Le Boennec
Partenaires
  • ETIS (UMR CY CNRS)