La réalisation de simulations numériques précises des écoulements fluviaux, tant à l’échelle territoriale que mondiale, ainsi que des inondations marines, est devenue cruciale pour les sociétés modernes pour de multiples raisons. Les inondations — qu’elles soient continentales ou côtières — et les écoulements d’eau à l’échelle territoriale résultent de processus complexes pouvant être décrits par des modèles mathématiques non linéaires fondés sur des équations différentielles.
Purely physics-based approaches face intrinsic limitations in representing such multi-scale (spatio-temporal) and multi-physics phenomena. In the case of watershed flows, they often rely on highly empirical parameterizations. Moreover, the computational cost of these models generally prevents their use in real-time applications.
Purely data-driven approaches may provide complementary information, but they typically require very large datasets and remain difficult to certify and interpret. Hybrid approaches that combine physics-based modeling with data-driven techniques (hybrid AI) offer a promising framework to overcome these limitations.
The objective of this project is to investigate and develop hybrid AI algorithms for estimating continental-scale water flows (river networks), including extreme events such as floods and marine inundation in coastal regions.
Significant improvements are expected in terms of computational performance, predictive accuracy, and model explainability.
The research outcomes will be illustrated through case studies based on real-world scenarios. The databases employed will be multi-source, combining in situ measurements with complementary satellite observations.
The research program is structured around five interconnected axes:
- Physics-informed learning methods: hybridization of two well-established model classes—neural networks and Gaussian processes—with physical knowledge. The resulting surrogate models and associated data assimilation strategies will be studied.
- Reduced-basis methods: model reduction techniques based on hybrid encoders and neural network approaches.
- Multi-fidelity models: methodologies designed to exploit hierarchies of numerical simulators with varying levels of accuracy and computational cost.
- Uncertainty quantification: risk assessment and global sensitivity analysis aimed at improving model robustness and interpretability.
- Design of experiments: strategies for generating new data through numerical simulations.
The chair team brings together researchers and experts from both academia and industry with complementary expertise in mathematical modeling (PDEs, probability theory, and statistics), computational sciences, scientific AI, and the relevant applied sciences (hydrology and oceanography).
Industrial Applications
- SHOM : coastal flooding
- CNES : spatial hydrology, inundations
- BRGM : floodings
- CS Group (Groupe SOPRA STERIA) : spatial hydrology, floodings
- SERTIT : spatial hydrology, floodings.
- HydroMatters : spatial hydrology
Scientific Results
- Axis 1 – Physics-informed learning methods
- Axis 2 – Reduced-basis methods – Surrogates
- Axis 3 – Multi-fidelity models
- Axis 4 – Uncertainty quantification
- Axis 5 – Design of experiments
Collaborators
- COUDERC Frédéric (CNRS – IMT)
- DUMAS LoÏc (CS Lab / CS Group)
- GAMBOA Fabrice (UT-IMT)
- HENDERSON Iain (ISAE-Sup’Aero)
- IDIER Deborah (BRGM)
- JOULIN Aldéric (INSA-IMT)
- LARNIER Kevin (HydroMatters)
- LELEUX Philippe (INSA-LAAS)
- PUJOL Leo (SERTIT)
- RENARD Benjamin (INRAE Aix-en-Provence)
- ROHMER Jérémy (BRGM)
Fellows
- ALLABOU Mustapha (INSA)
- BAEHR Yann (METEO France)
- BOULENC Hugo (INSA)
- EL BOUKKOURI Fatima Zahrae (INSA / X )
- ETTABI Mouad (INRAe)
- GOMEZ Damien (INSA / CS Lab)
- GORSE Nathan (INSA)
- HEREDIA David (INSA)
- LAURIER Romain (INSA)
- NGUYEN Thao Van (INSA / CNES)
- PADILLA SEGURA Adrian (INSA)
- SAN Bun-Kim (INSA / CNES)
- TRUYEN Ngho Ngi (INRAE)
Guest collaborators
- BACHOC François (Univ. Lille)
- BAEHR Christophe (Météo France)
- CASTELLE Bruno (Univ. Bordeaux)
- FILIPPINI A. (BRGM)
- KOPANICAKOVA Alena (INPT – IRIT)
- NOVELLO Paul (IRT)
- RISSER Laurent (CNRS-IMT)
- ZHANG Sixin (INPT – IRIT)