Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910641325867008 |
|---|---|
| author | Huang, Zijie Zhao, Wanjia Gao, Jingdong Hu, Ziniu Luo, Xiao Cao, Yadi Chen, Yuanzhou Sun, Yizhou Wang, Wei |
| author_facet | Huang, Zijie Zhao, Wanjia Gao, Jingdong Hu, Ziniu Luo, Xiao Cao, Yadi Chen, Yuanzhou Sun, Yizhou Wang, Wei |
| contents | Learning complex physical dynamics purely from data is challenging due to the intrinsic properties of systems to be satisfied. Incorporating physics-informed priors, such as in Hamiltonian Neural Networks (HNNs), achieves high-precision modeling for energy-conservative systems. However, real-world systems often deviate from strict energy conservation and follow different physical priors. To address this, we present a framework that achieves high-precision modeling for a wide range of dynamical systems from the numerical aspect, by enforcing Time-Reversal Symmetry (TRS) via a novel regularization term. It helps preserve energies for conservative systems while serving as a strong inductive bias for non-conservative, reversible systems. While TRS is a domain-specific physical prior, we present the first theoretical proof that TRS loss can universally improve modeling accuracy by minimizing higher-order Taylor terms in ODE integration, which is numerically beneficial to various systems regardless of their properties, even for irreversible systems. By integrating the TRS loss within neural ordinary differential equation models, the proposed model TREAT demonstrates superior performance on diverse physical systems. It achieves a significant 11.5% MSE improvement in a challenging chaotic triple-pendulum scenario, underscoring TREAT's broad applicability and effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06366 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling Huang, Zijie Zhao, Wanjia Gao, Jingdong Hu, Ziniu Luo, Xiao Cao, Yadi Chen, Yuanzhou Sun, Yizhou Wang, Wei Machine Learning Artificial Intelligence Learning complex physical dynamics purely from data is challenging due to the intrinsic properties of systems to be satisfied. Incorporating physics-informed priors, such as in Hamiltonian Neural Networks (HNNs), achieves high-precision modeling for energy-conservative systems. However, real-world systems often deviate from strict energy conservation and follow different physical priors. To address this, we present a framework that achieves high-precision modeling for a wide range of dynamical systems from the numerical aspect, by enforcing Time-Reversal Symmetry (TRS) via a novel regularization term. It helps preserve energies for conservative systems while serving as a strong inductive bias for non-conservative, reversible systems. While TRS is a domain-specific physical prior, we present the first theoretical proof that TRS loss can universally improve modeling accuracy by minimizing higher-order Taylor terms in ODE integration, which is numerically beneficial to various systems regardless of their properties, even for irreversible systems. By integrating the TRS loss within neural ordinary differential equation models, the proposed model TREAT demonstrates superior performance on diverse physical systems. It achieves a significant 11.5% MSE improvement in a challenging chaotic triple-pendulum scenario, underscoring TREAT's broad applicability and effectiveness. |
| title | Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.06366 |