MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs

MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs

Year:    2022

Author:    Lulu Zhang, Tao Luo, Yaoyu Zhang, Weinan E, Zhi-Qin John Xu, Zheng Ma

Communications in Computational Physics, Vol. 32 (2022), Iss. 2 : pp. 299–335

Abstract

In this paper, we propose a machine learning approach via model-operator-data network (MOD-Net) for solving PDEs. A MOD-Net is driven by a model to solve PDEs based on operator representation with regularization from data. For linear PDEs, we use a DNN to parameterize the Green’s function and obtain the neural operator to approximate the solution according to the Green’s method. To train the DNN, the empirical risk consists of the mean squared loss with the least square formulation or the variational formulation of the governing equation and boundary conditions. For complicated problems, the empirical risk also includes a few labels, which are computed on coarse grid points with cheap computation cost and significantly improves the model accuracy. Intuitively, the labeled dataset works as a regularization in addition to the model constraints. The MOD-Net solves a family of PDEs rather than a specific one and is much more efficient than original neural operator because few expensive labels are required. We numerically show MOD-Net is very efficient in solving Poisson equation and one-dimensional radiative transfer equation. For nonlinear PDEs, the nonlinear MOD-Net can be similarly used as an ansatz for solving nonlinear PDEs, exemplified by solving several nonlinear PDE problems, such as the Burgers equation.

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/cicp.OA-2021-0257

Communications in Computational Physics, Vol. 32 (2022), Iss. 2 : pp. 299–335

Published online:    2022-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    37

Keywords:    Deep neural network radiative transfer equation Green’s method neural operator.

Author Details

Lulu Zhang

Tao Luo

Yaoyu Zhang

Weinan E

Zhi-Qin John Xu

Zheng Ma

  1. Physics-Informed Neural Operator for Learning Partial Differential Equations

    Li, Zongyi | Zheng, Hongkai | Kovachki, Nikola | Jin, David | Chen, Haoxuan | Liu, Burigede | Azizzadenesheli, Kamyar | Anandkumar, Anima

    ACM / IMS Journal of Data Science, Vol. 1 (2024), Iss. 3 P.1

    https://doi.org/10.1145/3648506 [Citations: 25]
  2. DNN-HDG: A deep learning hybridized discontinuous Galerkin method for solving some elliptic problems

    Baharlouei, S. | Mokhtari, R. | Mostajeran, F.

    Engineering Analysis with Boundary Elements, Vol. 151 (2023), Iss. P.656

    https://doi.org/10.1016/j.enganabound.2023.03.039 [Citations: 4]
  3. Overview Frequency Principle/Spectral Bias in Deep Learning

    Xu, Zhi-Qin John | Zhang, Yaoyu | Luo, Tao

    Communications on Applied Mathematics and Computation, Vol. (2024), Iss.

    https://doi.org/10.1007/s42967-024-00398-7 [Citations: 2]
  4. Bayesian Inversion with Neural Operator (BINO) for modeling subdiffusion: Forward and inverse problems

    Yan, Xiong-Bin | Xu, Zhi-Qin John | Ma, Zheng

    Journal of Computational and Applied Mathematics, Vol. 454 (2025), Iss. P.116191

    https://doi.org/10.1016/j.cam.2024.116191 [Citations: 0]
  5. Render unto Numerics: Orthogonal Polynomial Neural Operator for PDEs with Nonperiodic Boundary Conditions

    Liu, Ziyuan | Wang, Haifeng | Zhang, Hong | Bao, Kaijun | Qian, Xu | Song, Songhe

    SIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 4 P.C323

    https://doi.org/10.1137/23M1556320 [Citations: 0]
  6. Capturing the diffusive behavior of the multiscale linear transport equations by Asymptotic-Preserving Convolutional DeepONets

    Wu, Keke | Yan, Xiong-Bin | Jin, Shi | Ma, Zheng

    Computer Methods in Applied Mechanics and Engineering, Vol. 418 (2024), Iss. P.116531

    https://doi.org/10.1016/j.cma.2023.116531 [Citations: 3]