Deep Domain Decomposition Methods: Helmholtz Equation

Deep Domain Decomposition Methods: Helmholtz Equation

Year:    2023

Author:    Wuyang Li, Ziming Wang, Tao Cui, Yingxiang Xu, Xueshuang Xiang

Advances in Applied Mathematics and Mechanics, Vol. 15 (2023), Iss. 1 : pp. 118–138

Abstract

This paper proposes a deep-learning-based Robin-Robin domain decomposition method (DeepDDM) for Helmholtz equations. We first present the plane wave activation-based neural network (PWNN), which is more efficient for solving Helmholtz equations with constant coefficients and wavenumber $k$ than finite difference methods (FDM). On this basis, we use PWNN to discretize the subproblems divided by domain decomposition methods (DDM), which is the main idea of DeepDDM. This paper will investigate the number of iterations of using DeepDDM for continuous and discontinuous Helmholtz equations. The results demonstrate that: DeepDDM exhibits behaviors consistent with conventional robust FDM-based domain decomposition method (FDM-DDM) under the same Robin parameters, i.e., the number of iterations by DeepDDM is almost the same as that of FDM-DDM. By choosing suitable Robin parameters on different subdomains, the convergence rate is almost constant with the rise of wavenumber in both continuous and discontinuous cases. The performance of DeepDDM on Helmholtz equations may provide new insights for improving the PDE solver by deep learning.

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/aamm.OA-2021-0305

Advances in Applied Mathematics and Mechanics, Vol. 15 (2023), Iss. 1 : pp. 118–138

Published online:    2023-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    21

Keywords:    Helmholtz equation deep learning domain decomposition method plane wave method.

Author Details

Wuyang Li

Ziming Wang

Tao Cui

Yingxiang Xu

Xueshuang Xiang

  1. Multilevel domain decomposition-based architectures for physics-informed neural networks

    Dolean, Victorita | Heinlein, Alexander | Mishra, Siddhartha | Moseley, Ben

    Computer Methods in Applied Mechanics and Engineering, Vol. 429 (2024), Iss. P.117116

    https://doi.org/10.1016/j.cma.2024.117116 [Citations: 6]
  2. Sparse-regularized high-frequency enhanced neural network for solving high-frequency problems

    Huang, Qilin | Fang, Mingjin | Cheng, Dongsheng | Lu, Chunyuan | Zeng, Taishan

    Journal of Computational Physics, Vol. (2024), Iss. P.113676

    https://doi.org/10.1016/j.jcp.2024.113676 [Citations: 0]