A Local Deep Learning Method for Solving High Order Partial Differential Equations

A Local Deep Learning Method for Solving High Order Partial Differential Equations

Year:    2022

Author:    Jiang Yang, Quanhui Zhu

Numerical Mathematics: Theory, Methods and Applications, Vol. 15 (2022), Iss. 1 : pp. 42–67

Abstract

At present, deep learning based methods are being employed to resolve the computational challenges of high-dimensional partial differential equations (PDEs). But the computation of the high order derivatives of neural networks is costly, and high order derivatives lack robustness for training purposes. We propose a novel approach to solving PDEs with high order derivatives by simultaneously approximating the function value and derivatives. We introduce intermediate variables to rewrite the PDEs into a system of low order differential equations as what is done in the local discontinuous Galerkin method. The intermediate variables and the solutions to the PDEs are simultaneously approximated by a multi-output deep neural network. By taking the residual of the system as a loss function, we can optimize the network parameters to approximate the solution. The whole process relies on low order derivatives. Numerous numerical examples are carried out to demonstrate that our local deep learning is efficient, robust, flexible, and is particularly well-suited for high-dimensional PDEs with high order derivatives.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/nmtma.OA-2021-0035

Numerical Mathematics: Theory, Methods and Applications, Vol. 15 (2022), Iss. 1 : pp. 42–67

Published online:    2022-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    26

Keywords:    Deep learning deep neural network high order PDEs reduction of order deep Galerkin method.

Author Details

Jiang Yang

Quanhui Zhu

  1. TDOR-MPINNs: Multi-output physics-informed neural networks based on time differential order reduction for solving coupled Klein–Gordon–Zakharov systems

    He, Jiahuan | Liu, Yang | Li, Hong

    Results in Applied Mathematics, Vol. 22 (2024), Iss. P.100462

    https://doi.org/10.1016/j.rinam.2024.100462 [Citations: 1]
  2. Physics-informed generator-encoder adversarial networks with latent space matching for stochastic differential equations

    Gao, Ruisong | Yang, Min | Zhang, Jin

    Journal of Computational Science, Vol. 79 (2024), Iss. P.102318

    https://doi.org/10.1016/j.jocs.2024.102318 [Citations: 0]
  3. A Priori Error Estimate of Deep Mixed Residual Method for Elliptic PDEs

    Li, Lingfeng | Tai, Xue-Cheng | Yang, Jiang | Zhu, Quanhui

    Journal of Scientific Computing, Vol. 98 (2024), Iss. 2

    https://doi.org/10.1007/s10915-023-02432-x [Citations: 2]