Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning


Loading...

Date

2024-07

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Physics-informed neural networks (PINNs) and their variants have been very popular in recent years as algorithms for the numerical simulation of both forward and inverse problems for partial differential equations. This article aims to provide a comprehensive review of currently available results on the numerical analysis of PINNs and related models that constitute the backbone of physics-informed machine learning. We provide a unified framework in which analysis of the various components of the error incurred by PINNs in approximating PDEs can be effectively carried out. We present a detailed review of available results on approximation, generalization and training errors and their behaviour with respect to the type of the PDE and the dimension of the underlying domain. In particular, we elucidate the role of the regularity of the solutions and their stability to perturbations in the error analysis. Numerical results are also presented to illustrate the theory. We identify training errors as a key bottleneck which can adversely affect the overall performance of various models in physics-informed machine learning.

Publication status

published

Editor

Book title

Journal / series

Volume

33

Pages / Article No.

633 - 713

Publisher

Cambridge University Press

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03851 - Mishra, Siddhartha / Mishra, Siddhartha check_circle

Notes

Funding

Related publications and datasets