An Analytical and AI-discovered Stable, Accurate, and Generalizable Subgrid-scale Closure for Geophysical Turbulence

2025/09/05 by Jakhar, Karan, Guan, Yifei, Hassanzadeh, Pedram · 1 citation
#Atmospheric and Oceanic Physics (physics.ao-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2509.20365

Abstract

By combining AI and fluid physics, we discover a closed-form closure for 2D turbulence from small direct numerical simulation (DNS) data. Large-eddy simulation (LES) with this closure is accurate and stable, reproducing DNS statistics including those of extremes. We also show that the new closure could be derived from a 4th-order truncated Taylor expansion. Prior analytical and AI-based work only found the 2nd-order expansion, which led to unstable LES. The additional terms emerge only when inter-scale energy transfer is considered alongside standard reconstruction criterion in the sparse-equation discovery.

Citations

• Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models
• Model discovery on the fly using continuous data assimilation
• Online learning of eddy-viscosity and backscattering closures for geophysical turbulence using ensemble Kalman inversion
• Machine Learning for the Physics of Climate
• Coarse Graining with Neural Operators for Simulating Chaotic Systems
• Machine learning for climate physics and simulations
• Turbulence closure with small, local neural networks: Forced two-dimensional and β-plane flows
• Learning Stochastic Closures Using Ensemble Kalman Inversion
• AI Feynman: a Physics-Inspired Method for Symbolic Regression
• Machine Learning for Fluid Mechanics
• Eddy diffusivity in homogeneous isotropic turbulence
• Data-driven deconvolution for large eddy simulations of Kraichnan turbulence
• Turbulence Modeling in the Age of Data
• Large Eddy Simulation of Turbulent Channel Flows by the Rational LES Model

Cited by

• Modified Dynamic Mixed Subgrid-scale Models for Geophysical Flows: Forced Two-Dimensional and β-plane Turbulence

Related

• Semi-analytical eddy-viscosity and backscattering closures for 2D geophysical turbulence
• Connecting implicit and explicit large eddy simulations of\n two-dimensional turbulence through machine learning
• Differentiable Turbulence: Closure as a partial differential equation constrained optimization
• Modified Dynamic Mixed Subgrid-scale Models for Geophysical Flows: Forced Two-Dimensional and β-plane Turbulence
• Generative AI for subgrid turbulence in large-eddy simulations