Projects

Research projects

PDE-AI

PDE-AI

A national research initiative on AI methods for PDEs. Some of the algorithms developed for Scimba feed into PDE-AI — not the project as a whole.

ANR

ANR INFERNO

IRMA, Inria Rennes, Sorbonne Université, École des Ponts ParisTech

Details coming soon.

PEPR Numpex

PEPR NumPEx — Exa-MA

A methods-and-algorithms-for-exascale project. A number of contributions on PINNs and surrogate models are integrated into Scimba.

Papers

Publications

2026

Non-linear control variate in δf particle-in-cell methods using symplectic neural networks

V. Fournet, M. Campos Pinto, E. Franck, V. Michel-Dansac

A δf particle-in-cell approach for kinetic plasma simulations in which the bulk density, used as a control variate, is evolved with symplectic neural networks (SympNets) approximating the backward flow, with a periodic SympNet variant validated on 1D1V and 3D3V Vlasov-Poisson configurations.

2026

Enriching continuous Lagrange finite element approximation spaces using neural networks

H. Barucq, M. Duprez, F. Faucher, E. Franck, F. Lecourtier, V. Lleras, V. Michel-Dansac, N. Victorion

A pipeline that enriches classical FEM approximation spaces with a neural network prior, with error estimates showing the enriched scheme reaches a given accuracy on coarser meshes than standard FEM, validated on parametric 1D, 2D and 3D problems.

2026

Neural semi-Lagrangian method for high-dimensional advection-diffusion problems

E. Franck, V. Michel-Dansac, L. Navoret, V. Vigon

A semi-Lagrangian scheme for high-dimensional advection-diffusion equations that projects the solution onto a finite-dimensional neural space at each time step, combining the unconditional stability of semi-Lagrangian methods with neural approaches that avoid the curse of dimensionality.

2025

Neural network-driven domain decomposition for efficient solutions to the Helmholtz equation

V. Dolean, D. Hrebenshchykova, S. Lanteri, V. Michel-Dansac

An assessment of Finite Basis Physics-Informed Neural Networks and their multilevel variants for the homogeneous Helmholtz equation in complex 2D domains, partitioning the computational domain into overlapping sub-domains each governed by a local network, and comparing the approach against conventional finite difference and finite element methods on high-frequency wave problems.

2025

Volume-preserving geometric shape optimization of the Dirichlet energy using variational neural networks

A. Bélières Frendo, E. Franck, V. Michel-Dansac, Y. Privat

A variational neural network approach to volume-constrained shape optimization of the Dirichlet energy, parametrizing admissible shapes so that the constraint is preserved throughout training instead of enforced through penalization.

2025

Neural non-canonical Hamiltonian dynamics for long-time simulations

C. Courtès, E. Franck, M. Kraus, L. Navoret, L. Trémant

A study of learning non-canonical Hamiltonian dynamics from data while preserving structure in both the learned model and its numerical integration, identifying a gauge-dependency instability that arises when combining the two and proposing two training strategies (learning the vector field directly, or the time-discrete map through the integration scheme), validated on guiding-center dynamics from gyrokinetic plasma physics.

2024

Approximately well-balanced Discontinuous Galerkin methods using bases enriched with Physics-Informed Neural Networks

E. Franck, V. Michel-Dansac, L. Navoret

An enrichment of Discontinuous Galerkin bases with a Physics-Informed Neural Network prior approximating the steady solution, yielding schemes that are approximately well-balanced for hyperbolic systems of balance laws.