Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.13847 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917408004898816 |
|---|---|
| author | Falasca, Fabrizio Zanna, Laure |
| author_facet | Falasca, Fabrizio Zanna, Laure |
| contents | We present a framework for constructing physics and causally constrained neural models of turbulent dynamical systems from data. We first formulate a finite-time flow map with strict energy-preserving nonlinearities for stable modeling of temporally discrete trajectories. We then impose causal constraints to suppress spurious interactions across degrees of freedom. The resulting neural models accurately capture stationary statistics and responses to both small and large external forcings. We demonstrate the framework on the stochastic Charney-DeVore equations and on a symmetry-broken Lorenz-96 system. The framework is broadly applicable to reduced-order modeling of turbulent dynamical systems from observational data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13847 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Physics and causally constrained discrete-time neural models of turbulent dynamical systems Falasca, Fabrizio Zanna, Laure Chaotic Dynamics Statistical Mechanics Machine Learning Atmospheric and Oceanic Physics We present a framework for constructing physics and causally constrained neural models of turbulent dynamical systems from data. We first formulate a finite-time flow map with strict energy-preserving nonlinearities for stable modeling of temporally discrete trajectories. We then impose causal constraints to suppress spurious interactions across degrees of freedom. The resulting neural models accurately capture stationary statistics and responses to both small and large external forcings. We demonstrate the framework on the stochastic Charney-DeVore equations and on a symmetry-broken Lorenz-96 system. The framework is broadly applicable to reduced-order modeling of turbulent dynamical systems from observational data. |
| title | Physics and causally constrained discrete-time neural models of turbulent dynamical systems |
| topic | Chaotic Dynamics Statistical Mechanics Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2602.13847 |