Invariant Data-Driven Subgrid Stress Modeling on Anisotropic Grids for Large Eddy Simulation

TL;DR

This paper introduces a novel invariant data-driven subgrid stress model for large eddy simulation on anisotropic grids, demonstrating good generalization with limited training data and simple neural networks.

Contribution

It develops a physically invariant model form that incorporates filter anisotropy and trains it using minimal DNS data, advancing LES modeling techniques.

Findings

Model generalizes well across different flow conditions.

Uses a simple neural network architecture.

Satisfies important subgrid stress identities.

Abstract

We present a new approach for constructing data-driven subgrid stress models for large eddy simulation of turbulent flows using anisotropic grids. The key to our approach is a Galilean, rotationally, reflectionally and unit invariant model form that also embeds filter anisotropy in such a way that an important subgrid stress identity is satisfied. We use this model form to train a data-driven subgrid stress model using only a small amount of anisotropically filtered DNS data and a simple and inexpensive neural network architecture. A priori and a posteriori tests indicate that the trained data-driven model generalizes well to filter anisotropy ratios, Reynolds numbers and flow physics outside the training dataset.