HRW: Hybrid Residual and Weak Form Loss for Solving Elliptic Interface Problems with Neural Network

HRW: Hybrid Residual and Weak Form Loss for Solving Elliptic Interface Problems with Neural Network

Year:    2023

Author:    Yinghao Chen, Muzhou Hou, Shen Cao, Yinghao Chen, Yuntian Chen, Jinyong Ying, Shen Cao, Yuntian Chen, Jinyong Ying

Numerical Mathematics: Theory, Methods and Applications, Vol. 16 (2023), Iss. 4 : pp. 883–913

Abstract

Deep learning techniques for solving elliptic interface problems have gained significant attentions. In this paper, we introduce a hybrid residual and weak form (HRW) loss aimed at mitigating the challenge of model training. HRW utilizes the functions residual loss and Ritz method in an adversary-system, which enhances the probability of jumping out of the local optimum even when the loss landscape comprises multiple soft constraints (regularization terms), thus improving model’s capability and robustness. For the problem with interface conditions, unlike existing methods that use the domain decomposition, we design a Pre-activated ResNet of ResNet (PRoR) network structure employing a single network to feed both coordinates and corresponding subdomain indicators, thus reduces the number of parameters. The effectiveness and improvements of the PRoR with HRW are verified on two-dimensional interface problems with regular or irregular interfaces. We then apply the PRoR with HRW to solve the size-modified Poisson-Boltzmann equation, an improved dielectric continuum model for predicting the electrostatic potentials in an ionic solvent by considering the steric effects. Our findings demonstrate that the PRoR with HRW accurately approximates solvation free-energies of three proteins with irregular interfaces, showing the competitive results compared to the ones obtained using the finite element method.

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-2023-0097

Numerical Mathematics: Theory, Methods and Applications, Vol. 16 (2023), Iss. 4 : pp. 883–913

Published online:    2023-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    31

Keywords:    Deep learning method elliptic interface problem size-modified Poisson-Boltzmann equation solvation free energy

Author Details

Yinghao Chen

Muzhou Hou

Shen Cao

Yinghao Chen

Yuntian Chen

Jinyong Ying

Shen Cao

Yuntian Chen

Jinyong Ying

  1. Improved multi-scale fusion network for solving non-smooth elliptic interface problems with applications

    Ying, Jinyong

    Li, Jiao

    Liu, Qiong

    Chen, Yinghao

    Applied Mathematical Modelling, Vol. 132 (2024), Iss. P.274

    https://doi.org/10.1016/j.apm.2024.04.039 [Citations: 0]