Unsupervised Operator Learning Approach for Dissipative Equations via Onsager Principle
SIAM Journal on Scientific Computing · 31.08.2026 · 48 (4) · C1060-C1085
DOI: 10.1137/25m1786763 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 07.08.2026. Verfasst von Zhipeng Chang und 2 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National MCF Energy R&D Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Existing operator learning methods rely on supervised training with high-fidelity simulation data, introducing significant computational cost. In this work, we propose the deep Onsager operator learning (DOOL) method, a novel unsupervised framework for solving dissipative equations. Rooted in the Onsager variational principle (OVP), DOOL trains a deep operator network by directly minimizing the OVP-defined Rayleighian functional, requiring no labeled data, and then proceeds in time explicitly through conservation/change laws for the solution. Another key innovation here lies in the spatiotemporal decoupling strategy: the operator’s trunk network processes spatial coordinates exclusively, thereby enhancing training efficiency, while integrated external time stepping enables temporal extrapolation. Numerical experiments on typical dissipative equations validate the effectiveness of the DOOL method, and systematic comparisons with supervised DeepONet and MIONet demonstrate its enhanced performance. Extensions are made to cover the second-order wave models with dissipation that do not directly follow OVP. 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/wzhy0777/DOOL and in the supplementary material ( DOOL-main.zip [367KB]). [Formula: see text]
Förderung
- National Key Research and Development Program of China
- National MCF Energy R&D Program
- National Natural Science Foundation of China
Zitieren
APA
Chang, Z., Wen, Z., & Zhao, X. (2026). Unsupervised Operator Learning Approach for Dissipative Equations via Onsager Principle. SIAM Journal on Scientific Computing, 48(4), C1060-C1085. https://doi.org/10.1137/25m1786763
Vancouver
Chang Z, Wen Z, Zhao X. Unsupervised Operator Learning Approach for Dissipative Equations via Onsager Principle. SIAM Journal on Scientific Computing. 2026;48(4):C1060-C1085. doi:10.1137/25m1786763
BibTeX
@article{Chang2026,
author = {Chang, Zhipeng and Wen, Zhenye and Zhao, Xiaofei},
title = {Unsupervised Operator Learning Approach for Dissipative Equations via Onsager Principle},
journal = {SIAM Journal on Scientific Computing},
year = {2026},
volume = {48},
number = {4},
pages = {C1060--C1085},
doi = {10.1137/25m1786763}
}
EUVIMED