Hybrid neural-network FEM approximation of diffusion coefficient in elliptic and parabolic problems
IMA Journal of Numerical Analysis · 03.10.2024 · 44 (5) · 3059-3093
DOI: 10.1093/imanum/drad073 ↗Kurz gefasst
Fachartikel in der Zeitschrift IMA Journal of Numerical Analysis, online erschienen am 18.09.2023. Verfasst von Siyu Cen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 42 Literaturangaben.
Abstract (Originalsprache)
In this work we investigate the numerical identification of the diffusion coefficient in elliptic and parabolic problems using neural networks (NNs). 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 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 a priori error estimates in the standard $L^2(\varOmega )$ 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.
Zitieren
APA
Cen, S., Jin, B., Quan, Q., & Zhou, Z. (2024). Hybrid neural-network FEM approximation of diffusion coefficient in elliptic and parabolic problems. IMA Journal of Numerical Analysis, 44(5), 3059-3093. https://doi.org/10.1093/imanum/drad073
Vancouver
Cen S, Jin B, Quan Q, Zhou Z. Hybrid neural-network FEM approximation of diffusion coefficient in elliptic and parabolic problems. IMA Journal of Numerical Analysis. 2024;44(5):3059-3093. doi:10.1093/imanum/drad073
BibTeX
@article{Cen2024,
author = {Cen, Siyu and Jin, Bangti and Quan, Qimeng and Zhou, Zhi},
title = {Hybrid neural-network FEM approximation of diffusion coefficient in elliptic and parabolic problems},
journal = {IMA Journal of Numerical Analysis},
year = {2024},
volume = {44},
number = {5},
pages = {3059--3093},
doi = {10.1093/imanum/drad073}
}
EUVIMED