Post-Doctoral Research Visit F/M Physics-Informed Learning Models for Forecasting E-Flexibility in Electric Vehicles (EVs)

The Centre Inria de l’Université de Grenoble groups together almost 450 people in 26 research teams and 9 research support departments.

Staff is present on three campuses in Grenoble, in close collaboration with other research and higher education institutions (Université Grenoble Alpes, CNRS, CEA, INRAE, …), but also with key economic players in the area.

The Centre Inria de l’Université Grenoble Alpes is active in the fields of high-performance computing, verification and embedded systems, modeling of the environment at multiple levels, and data science and artificial intelligence. The center is a top-level scientific institute with an extensive network of international collaborations in Europe and the rest of the world.

The research focuses on the development of hybrid modeling frameworks for electromobility,
combining physical models, graph-based representations, and data-driven approaches. It aims at
integrating large-scale mobility data to improve the prediction of vehicle flows, energy demand, and
flexibility of electric vehicle fleets, with applications to energy and transportation systems.

The work lies at the intersection of systems and control, data science, and energy systems, with
applications in smart mobility, electric vehicle integration, and power grid management. It contributes to
the design of decision-support tools for infrastructure planning, energy optimization, and sustainable
urban mobility.

The position focuses on the development of a hybrid electromobility model within the eMob-Twin
platform, combining large-scale mobility data from telecom operators with physics-informed and
data-driven approaches. The candidate will work on the calibration of models using Origin–
Destination data (high temporal and spatial resolution), aiming to improve the prediction of electric
vehicle (EV) mobility patterns, energy demand, and state of charge (SoC) over time and space.
The work will include the design of advanced modeling frameworks integrating graph-based
representations, system dynamics, and Physics-Informed Learning, as well as the implementation
and validation of these models using real-world data. The developed models will be integrated into
the eMob-Twin software platform (emob-twin.fr), enabling the simulation and evaluation of scenarios
related to charging infrastructure planning, grid integration, and vehicle-to-grid (V2G) services.
The project will initially focus on the Grenoble metropolitan area, with the objective of developing
methods that are scalable and transferable to other regions at the international level.
This position is part of a Linksium/UGA maturation program, with a strong emphasis on bridging
research and real-world applications, and contributing to the development of an operational tool for
decision-makers in mobility and energy systems.

• Process mobility data (from mobile telecom operators) to understand local mobility
patterns, Then Impute missing data and clean the dataset for model application.
• Build graphs representing mobility flows and EV trajectories from the collected data.
• Redesign the model to incorporate more complex, nonlinear trajectories by removing
constraints from the initial bipartite graph structure.
• Integrate charging stations as nodes within the model, considering their capacity and
pricing schemes.
• Calibrate the model using real-world data and PIL methods to improve its predictive
accuracy.
• Integrate the enhanced mode

The candidate should have a solid background in applied
mathematics, control, or related fields, with knowledge in several of the following areas:
Graph theory and network modeling
Dynamical systems and physical modeling (ODE/PDE, multi-agent systems)
Optimization and parameter identification methods
Data-driven modeling and machine learning
Physics-Informed Learning (or hybrid modeling approaches)
Handling and analysis of large-scale datasets (e.g., mobility data, OD matrices)
Programming skills for scientific computing (Python, MATLAB, or similar)
Familiarity with applications in mobility systems, transportation, or energy systems (e.g., electric
vehicles, smart grids) is a strong plus

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage

• 2788€ monthly gross salary