VMVictor Michel-Dansac

Victor Michel-Dansac

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Victor Michel-Dansac has a total of 52 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

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

    by Victor Fournet, Martin Campos Pinto, Emmanuel Franck, Victor Michel-Dansac

    We present a novel 𝛿𝑓 particle-in-cell (PIC) method for the kinetic simulation of electrostatic plasmas in which the bulk density, acting as a control variate, is evolved using symplectic neural networks (SympNets). The SympNets are used as an approximation of the backward flow and trained using the particle trajectories. We introduce a periodic variant of the SympNet architecture that encodes the spatial periodicity of the problem into the network itself. We validate the approach with numerical results in 1D1V and 3D3V for the Vlasov-Poisson system.

  • Développement de schémas équilibre d'ordre élevé pour des modèles d'écoulements géophysiques

    by Victor Michel-Dansac

    L’objectif de ce travail est de proposer un schéma numérique pertinent pour les équations de Saint-Venant avec termes source de topographie et de friction de Manning. Le premier chapitre est dédié à l’étude du système de Saint- Venant muni des termes source. Dans un premier temps, les propriétés algébriques de ce système sont obtenues. Dans un second temps, nous nous intéressons à ses états stationnaires, qui sont étudiés pour les termes source individuels de topographie et de friction. Le deuxième chapitre permet de rappeler des notions concernant la méthode des volumes finis. Nous évoquons des schémas aux volumes finis pour des systèmes de lois de conservation unidimensionnels et bidimensionnels, et nous en proposons une extension permettant d’assurer un ordre élevé de précision. Le troisième chapitre concerne la dérivation d’un schéma numérique pour les équations de Saint-Venant avec topographie et friction. Ce schéma permet : de préserver tous les états stationnaires ; de préserver la positivité de la hauteur d’eau ; d’approcher les transitions entre zones mouillées et zones sèches, et ce même en présence de friction. Des cas-tests mettant en lumière les propriétés du schéma sont présentés. Le quatrième chapitre permet d’étendre le schéma proposé précédemment, pour prendre en compte des géométries bidimensionnelles et pour assurer un ordre élevé de précision. Des cas-tests numériques sont aussi présentés, y compris des simulations de phénomènes réels.

  • Open Access

    Enriching continuous lagrange finite element approximation spaces using neural networks

    by Hélène Barucq, Michel Duprez, Florian Faucher, Emmanuel Franck, Frédérique Lecourtier, Vanessa Lleras, Victor Michel-Dansac, Nicolas Victorion

    In this work, we present a study combining two approaches in the context of solving PDEs: the continuous finite element method (FEM) and more recent techniques based on neural networks. In recent years, physics-informed neural networks (PINNs) have become particularly interesting for rapidly solving PDEs, especially in high dimensions. However, their lack of accuracy can be a significant drawback in this context, hence the interest in combining them with FEM, for which error estimates are already known. The complete pipeline proposed here consists in modifying the classical FEM approximation spaces by taking information from a prior, chosen as the prediction of a neural network. On the one hand, this combination improves and certifies the prediction of neural networks, to obtain a fast and accurate solution. On the other hand, error estimates are proven, showing that such strategies outperform classical ones by a factor that depends only on the quality of the prior. We validate our approach with numerical results performed on parametric problems with 1D, 2D and 3D geometries. These experiments demonstrate that to achieve a given accuracy, a coarser mesh can be used with our enriched FEM compared to the standard FEM, leading to reduced computational time, particularly for parametric problems.

    • 1 October 2025
    • Published by HAL in HAL
    Open Access

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

    by Victorita Dolean, Daria Hrebenshchykova, Stéphane Lanteri, Victor Michel-Dansac

    Accurately simulating wave propagation is crucial in fields such as acoustics, electromagnetism, and seismic analysis. Traditional numerical methods, like finite difference and finite element approaches, are widely used to solve governing partial differential equations (PDEs) such as the Helmholtz equation. However, these methods face significant computational challenges when applied to high-frequency wave problems in complex two-dimensional domains. This work investigates Finite Basis Physics-Informed Neural Networks (FBPINNs) and their multilevel extensions as a promising alternative. These methods leverage domain decomposition, partitioning the computational domain into overlapping sub-domains, each governed by a local neural network. We assess their accuracy and computational efficiency in solving the Helmholtz equation for the homogeneous case, demonstrating their potential to mitigate the limitations of traditional approaches.

    • 1 October 2025
    • Published by HAL in HAL
    Open Access

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

    by Emmanuel Franck, Victor Michel-Dansac, Laurent Navoret, Vincent Vigon

    This work is devoted to the numerical approximation of high-dimensional advection-diffusion equations. It is well-known that classical methods, such as the finite volume method, suffer from the curse of dimensionality, and that their time step is constrained by a stability condition. The semi-Lagrangian method is known to overcome the stability issue, while recent time-discrete neural network-based approaches overcome the curse of dimensionality. In this work, we propose a novel neural semi-Lagrangian method that combines these last two approaches. It relies on projecting the initial condition onto a finite-dimensional neural space, and then solving an optimization problem, involving the backwards characteristic equation, at each time step. It is particularly well-suited for implementation on GPUs, as it is fully parallelizable and does not require a mesh. We provide rough error estimates, present several high-dimensional numerical experiments to assess the performance of our approach, and compare it to other neural methods.

  • Towards a fully well-balanced and entropy-stable scheme for the Euler equations with gravity: preserving isentropic steady solutions

    by Christophe Berthon, Victor Michel-Dansac, Andrea Thomann

    The present work concerns the derivation of a numerical scheme to approximate weak solutions of the Euler equations with a gravitational source term. The designed scheme is proved to be fully well-balanced since it is able to exactly preserve all moving equilibrium solutions, as well as the corresponding steady solutions at rest obtained when the velocity vanishes. Moreover, the proposed scheme is entropy-stable since it satisfies all fully discrete entropy inequalities. In addition, in order to satisfy the required admissibility of the approximate solutions, the positivity of both approximate density and pressure is established. Several numerical experiments attest the relevance of the developed numerical method. An extension to two-dimensional problems is given, applying the one-dimensional framework direction by direction on Cartesian grids.


  • Open Access

    Structural schemes for hamiltonian systems

    by Stéphane Clain, Emmanuel Franck, Victor Michel-Dansac

    We present an adaptation of the so-called structural method \cite{CMM23} for Hamiltonian systems, and redesign the method for this specific context, which involves two coupled differential systems. Structural schemes decompose the problem into two sets of equations: the physical equations, which describe the local dynamics of the system, and the structural equations, which only involve the discretization on a very compact stencil. They have desirable properties, such as unconditional stability or high-order accuracy. We first give a general description of the scheme for the scalar case (which corresponds to e.g. spring-mass interactions or pendulum motion), before extending the technique to the vector case (treating e.g. the $n$-body system). The scheme is also written in the case of a non-separable system (e.g. a charged particle in an electromagnetic field). We give numerical evidence of the method's efficiency, its capacity to preserve invariant quantities such as the total energy, and draw comparisons with the traditional symplectic methods.