Comparison of data-driven symmetry-preserving closure models for large-eddy simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Agdestein, Syver Døving, Sanderse, Benjamin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918372997857280
author Agdestein, Syver Døving
Sanderse, Benjamin
author_facet Agdestein, Syver Døving
Sanderse, Benjamin
contents Symmetries are fundamental to both turbulence and differential equations. The large-eddy simulation (LES) equations inherit these symmetries provided the LES closure respects them. Classical LES closures based on eddy viscosity or scale similarity preserve many of the original symmetries by design. Recently, data-driven neural network closures have been applied to LES to improve accuracy, but stability and generalizability remain challenges, as symmetries are not automatically enforced. In this work, we compare approaches for constructing symmetry-preserving data-driven LES closures, including tensor-basis neural networks (TBNNs) and group-convolutional neural networks, alongside unconstrained convolutional networks. All three data-driven closures outperform classical models in both the functional sense (producing the right amount of dissipation) and the structural sense (stress tensor prediction). While unconstrained networks achieve comparable prediction accuracy, symmetry-preserving models produce more physically consistent velocity-gradient statistics, suggesting that enforcing symmetries improves the quality of the learned closure beyond what aggregate error metrics such as relative tensor prediction errors capture.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05325
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Comparison of data-driven symmetry-preserving closure models for large-eddy simulation
Agdestein, Syver Døving
Sanderse, Benjamin
Numerical Analysis
Fluid Dynamics
Symmetries are fundamental to both turbulence and differential equations. The large-eddy simulation (LES) equations inherit these symmetries provided the LES closure respects them. Classical LES closures based on eddy viscosity or scale similarity preserve many of the original symmetries by design. Recently, data-driven neural network closures have been applied to LES to improve accuracy, but stability and generalizability remain challenges, as symmetries are not automatically enforced. In this work, we compare approaches for constructing symmetry-preserving data-driven LES closures, including tensor-basis neural networks (TBNNs) and group-convolutional neural networks, alongside unconstrained convolutional networks. All three data-driven closures outperform classical models in both the functional sense (producing the right amount of dissipation) and the structural sense (stress tensor prediction). While unconstrained networks achieve comparable prediction accuracy, symmetry-preserving models produce more physically consistent velocity-gradient statistics, suggesting that enforcing symmetries improves the quality of the learned closure beyond what aggregate error metrics such as relative tensor prediction errors capture.
title Comparison of data-driven symmetry-preserving closure models for large-eddy simulation
topic Numerical Analysis
Fluid Dynamics
url https://arxiv.org/abs/2603.05325