Finite element interpolated neural networks for solving forward and inverse problems

Santiago Badia*, Wei Li, Alberto F. Martín

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    10 Citations (Scopus)

    Abstract

    We propose a general framework for solving forward and inverse problems constrained by partial differential equations, where we interpolate neural networks onto finite element spaces to represent the (partial) unknowns. The framework overcomes the challenges related to the imposition of boundary conditions, the choice of collocation points in physics-informed neural networks, and the integration of variational physics-informed neural networks. A numerical experiment set confirms the framework's capability of handling various forward and inverse problems. In particular, the trained neural network generalises well for smooth problems, beating finite element solutions by some orders of magnitude. We finally propose an effective one-loop solver with an initial data fitting step (to obtain a cheap initialisation) to solve inverse problems.

    Original languageEnglish
    Article number116505
    JournalComputer Methods in Applied Mechanics and Engineering
    Volume418
    DOIs
    Publication statusPublished - 1 Jan 2024

    Fingerprint

    Dive into the research topics of 'Finite element interpolated neural networks for solving forward and inverse problems'. Together they form a unique fingerprint.

    Cite this