Hybrid Neural-Network FEM Approximation of Diffusion Coefficient in Elliptic and Parabolic Problems

TL;DR

This paper introduces a hybrid neural network and finite element method approach for numerically identifying diffusion coefficients in elliptic and parabolic PDEs, providing rigorous error estimates and demonstrating robustness against noise.

Contribution

The work combines FEM and neural networks for diffusion coefficient identification, offering theoretical error bounds and practical robustness improvements over pure FEM methods.

Findings

Hybrid method achieves accurate reconstruction under high noise levels.

Error estimates depend explicitly on noise, regularization, and discretization.

Numerical experiments confirm robustness and effectiveness of the approach.

Abstract

In this work we investigate the numerical identification of the diffusion coefficient in elliptic and parabolic problems using neural networks. The numerical scheme is based on the standard output least-squares formulation where the Galerkin finite element method (FEM) is employed to approximate the state and neural networks (NNs) act as a smoothness prior to approximate the unknown diffusion coefficient. A projection operation is applied to the NN approximation in order to preserve the physical box constraint on the unknown coefficient. The hybrid approach enjoys both rigorous mathematical foundation of the FEM and inductive bias / approximation properties of NNs. We derive \textsl{a priori} error estimates in the standard $L^2(\Omega)$ norm for the numerical reconstruction, under a positivity condition which can be verified for a large class of problem data. The error bounds depend explicitly on the noise level, regularization parameter and discretization parameters (e.g., spatial mesh size, time step size, and depth, upper bound and number of nonzero parameters of NNs). We also provide extensive numerical experiments, indicating that the hybrid method is very robust for large noise when compared with the pure FEM approximation.