Render unto Numerics: Orthogonal Polynomial Neural Operator for PDEs with Nonperiodic Boundary Conditions
SIAM Journal on Scientific Computing · 31.08.2024 · 46 (4) · C323-C348
DOI: 10.1137/23m1556320 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 12.07.2024. Verfasst von Ziyuan Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Defense Science Foundation of China, National Key R&D Program of China.
Abstract (Originalsprache)
By learning the mappings between infinite function spaces using carefully designed neural networks, the operator learning methodology has exhibited significantly more efficiency than traditional methods in solving differential equations, but faces concerns about their accuracy and reliability. To overcome these limitations through robustly enforcing boundary conditions (BCs), a general neural architecture named spectral operator learning is introduced by combining with the structures of the spectral numerical method. One variant called the orthogonal polynomial neural operator (OPNO) is proposed later, aiming at PDEs with Dirichlet, Neumann, and Robin BCs. The strict BC satisfaction properties and the universal approximation capacity of the OPNO are theoretically proven. A variety of numerical experiments with physical backgrounds demonstrate that the OPNO outperforms other existing deep learning methodologies, showcasing potential of comparable accuracy with the traditional second-order finite difference method that employs a considerably fine mesh (with relative errors on the order of [Formula: see text]), and is up to almost 5 magnitudes faster over the traditional method. Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/liu-ziyuan-math/spectral_operator_learning/tree/main/OPNO/Reproduce and in the supplementary materials ( spectral_operator_learning-main.zip [669KB]). [Formula: see text]
Förderung
- National Natural Science Foundation of China
- Defense Science Foundation of China
- National Key R&D Program of China
- Science and Technology Innovation Program of Hunan Province
- Natural Science Foundation of Hunan
- National University of Defense Technology
- Postgraduate Scientific Research Innovation Program of Hunan Province
Zitieren
APA
Liu, Z., Wang, H., Zhang, H., Bao, K., Qian, X., & Song, S. (2024). Render unto Numerics: Orthogonal Polynomial Neural Operator for PDEs with Nonperiodic Boundary Conditions. SIAM Journal on Scientific Computing, 46(4), C323-C348. https://doi.org/10.1137/23m1556320
Vancouver
Liu Z, Wang H, Zhang H, Bao K, Qian X, Song S. Render unto Numerics: Orthogonal Polynomial Neural Operator for PDEs with Nonperiodic Boundary Conditions. SIAM Journal on Scientific Computing. 2024;46(4):C323-C348. doi:10.1137/23m1556320
BibTeX
@article{Liu2024,
author = {Liu, Ziyuan and Wang, Haifeng and Zhang, Hong and Bao, Kaijun and Qian, Xu and Song, Songhe},
title = {Render unto Numerics: Orthogonal Polynomial Neural Operator for PDEs with Nonperiodic Boundary Conditions},
journal = {SIAM Journal on Scientific Computing},
year = {2024},
volume = {46},
number = {4},
pages = {C323--C348},
doi = {10.1137/23m1556320}
}
EUVIMED