Well-posedness of neural turbulence closures and tangent dissipation

arXiv:2609.19647 · physics.flu-dyn, cs.LG · Submitted 2026-09-17 · Read on arXiv

physics.flu-dyn, cs.LG

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: 20 pages, 4 figures

Code: https://github.com/zhangzhen117/coupled_PDE_NN_closure

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 13× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Admissibility — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Frozen model — 1× in this paper · explained in 3 episodes
• Physical Constraints — 1× in this paper · explained in 7 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Related papers

• Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
• Fast localized urban microclimate emulator: wind and temperatures in unseen urban morphologies
• Reward hacking in physical reinforcement learning revealed by turbulent drag reduction
• Diffraction of walking drops by a standing Faraday wave
• Linear causality and stability constraints on relativistic second-order magnetohydrodynamics
• Adjoint-based shape optimization of a ship hull using a Conditional Variational Autoencoder (CVAE) assisted propulsion surrogate model