Neural Entropy-stable conservative flux form neural networks for learning hyperbolic conservation laws
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916822514663424 |
|---|---|
| author | Liu, Lizuo Zhang, Lu Gelb, Anne |
| author_facet | Liu, Lizuo Zhang, Lu Gelb, Anne |
| contents | We propose a neural entropy-stable conservative flux form neural network (NESCFN) for learning hyperbolic conservation laws and their associated entropy functions directly from solution trajectories, without requiring any predefined numerical discretization. While recent neural network architectures have successfully integrated classical numerical principles into learned models, most rely on prior knowledge of the governing equations or assume a fixed discretization. Our approach removes this dependency by embedding entropy-stable design principles into the learning process itself, enabling the discovery of physically consistent dynamics in a fully data-driven setting. By jointly learning both the numerical flux function and a corresponding entropy, the proposed method ensures conservation and entropy dissipation, critical for long-term stability and fidelity in the system of hyperbolic conservation laws. Numerical results demonstrate that the method achieves stability and conservation over extended time horizons and accurately captures shock propagation speeds, even without oracle access to future-time solution profiles in the training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01795 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Entropy-stable conservative flux form neural networks for learning hyperbolic conservation laws Liu, Lizuo Zhang, Lu Gelb, Anne Numerical Analysis Machine Learning Mathematical Physics 65M08, 68T07, 65M22, 65M32, 65D25 We propose a neural entropy-stable conservative flux form neural network (NESCFN) for learning hyperbolic conservation laws and their associated entropy functions directly from solution trajectories, without requiring any predefined numerical discretization. While recent neural network architectures have successfully integrated classical numerical principles into learned models, most rely on prior knowledge of the governing equations or assume a fixed discretization. Our approach removes this dependency by embedding entropy-stable design principles into the learning process itself, enabling the discovery of physically consistent dynamics in a fully data-driven setting. By jointly learning both the numerical flux function and a corresponding entropy, the proposed method ensures conservation and entropy dissipation, critical for long-term stability and fidelity in the system of hyperbolic conservation laws. Numerical results demonstrate that the method achieves stability and conservation over extended time horizons and accurately captures shock propagation speeds, even without oracle access to future-time solution profiles in the training data. |
| title | Neural Entropy-stable conservative flux form neural networks for learning hyperbolic conservation laws |
| topic | Numerical Analysis Machine Learning Mathematical Physics 65M08, 68T07, 65M22, 65M32, 65D25 |
| url | https://arxiv.org/abs/2507.01795 |