Deep Unfitted Nitsche Method for Elliptic Interface Problems

Deep Unfitted Nitsche Method for Elliptic Interface Problems

Year:    2022

Author:    Hailong Guo, Xu Yang

Communications in Computational Physics, Vol. 31 (2022), Iss. 4 : pp. 1162–1179

Abstract

This paper proposes a deep unfitted Nitsche method for solving elliptic interface problems with high contrasts in high dimensions. To capture discontinuities of the solution caused by interfaces, we reformulate the problem as an energy minimization problem involving two weakly coupled components. This enables us to train two deep neural networks to represent two components of the solution in high-dimensional space. The curse of dimensionality is alleviated by using the Monte-Carlo method to discretize the unfitted Nitsche energy functional. We present several numerical examples to show the performance of the proposed 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/cicp.OA-2021-0201

Communications in Computational Physics, Vol. 31 (2022), Iss. 4 : pp. 1162–1179

Published online:    2022-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    18

Keywords:    Deep learning unfitted Nitsche method interface problem deep neural network.

Author Details

Hailong Guo

Xu Yang

  1. An Accurate and Efficient Continuity-Preserved Method Based on Randomized Neural Networks for Elliptic Interface Problems

    Ying, Jinyong | Hu, Jingying | Shi, Zuoshunhua | Li, Jiao

    SIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 5 P.C633

    https://doi.org/10.1137/24M1632309 [Citations: 0]
  2. Solving parametric elliptic interface problems via interfaced operator network

    Wu, Sidi | Zhu, Aiqing | Tang, Yifa | Lu, Benzhuo

    Journal of Computational Physics, Vol. 514 (2024), Iss. P.113217

    https://doi.org/10.1016/j.jcp.2024.113217 [Citations: 1]
  3. A Compact Coupling Interface Method with Second-Order Gradient Approximation for Elliptic Interface Problems

    Zhang, Ray Zirui | Cheng, Li-Tien

    Journal of Scientific Computing, Vol. 100 (2024), Iss. 2

    https://doi.org/10.1007/s10915-024-02587-1 [Citations: 0]
  4. 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]
  5. Multi-scale fusion network: A new deep learning structure for elliptic interface problems

    Ying, Jinyong | Liu, Jiaxuan | Chen, Jiaxin | Cao, Shen | Hou, Muzhou | Chen, Yinghao

    Applied Mathematical Modelling, Vol. 114 (2023), Iss. P.252

    https://doi.org/10.1016/j.apm.2022.10.006 [Citations: 6]
  6. An immersed interface neural network for elliptic interface problems

    Zhang, Xinru | He, Qiaolin

    Journal of Computational and Applied Mathematics, Vol. 459 (2025), Iss. P.116372

    https://doi.org/10.1016/j.cam.2024.116372 [Citations: 0]
  7. A shallow Ritz method for elliptic problems with singular sources

    Lai, Ming-Chih | Chang, Che-Chia | Lin, Wei-Syuan | Hu, Wei-Fan | Lin, Te-Sheng

    Journal of Computational Physics, Vol. 469 (2022), Iss. P.111547

    https://doi.org/10.1016/j.jcp.2022.111547 [Citations: 6]
  8. Artificial Neural Networks and Machine Learning – ICANN 2024

    Tailored Finite Point Operator Networks for Interface Problems

    Li, Ye | Du, Ting | Huang, Zhongyi

    2024

    https://doi.org/10.1007/978-3-031-72332-2_5 [Citations: 0]
  9. A meshless method based on the generalized finite difference method for three-dimensional elliptic interface problems

    Qin, Qiushuo | Song, Lina | Liu, Fan

    Computers & Mathematics with Applications, Vol. 131 (2023), Iss. P.26

    https://doi.org/10.1016/j.camwa.2022.11.020 [Citations: 12]
  10. A cusp-capturing PINN for elliptic interface problems

    Tseng, Yu-Hau | Lin, Te-Sheng | Hu, Wei-Fan | Lai, Ming-Chih

    Journal of Computational Physics, Vol. 491 (2023), Iss. P.112359

    https://doi.org/10.1016/j.jcp.2023.112359 [Citations: 8]