Eddy Viscosity

Eddy viscosity models aim to represent the effects of unresolved turbulent scales on larger-scale flows, primarily within computational fluid dynamics simulations like Large Eddy Simulation (LES). Current research focuses on improving these models using machine learning techniques, particularly reinforcement learning (RL) and physics-informed neural networks (PINNs), to adapt eddy viscosity dynamically based on local flow conditions and even to optimize discretization schemes. This work is significant because it promises more accurate and robust simulations of turbulent flows, impacting diverse fields from weather forecasting and ocean modeling to aerospace engineering and industrial design.

Papers

December 25, 2024

Implicit factorized transformer approach to fast prediction of turbulent channel flows
Huiyu Yang, Yunpeng Wang, Jianchun Wang
Fourier Neural Operator Transformer Based Approach Implicit Language Channel Quality Large Eddy Simulation Prediction Speed Eddy Viscosity General Neural Operator Transformer

September 12, 2023

Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning
Andrea Beck, Marius Kurz
Large Eddy Simulation Discretization Method Discontinuous Galerkin Eddy Viscosity

July 3, 2023

On the choice of training data for machine learning of geostrophic mesoscale turbulence
F. E. Yan, J. Mak, Y. Wang
Machine Learning Training Data Data Driven Value Laden Choice Stratified Turbulence Quasi Geostrophic Eddy Detection Eddy Viscosity

June 9, 2023

RANS-PINN based Simulation Surrogates for Predicting Turbulent Flows
Shinjan Ghosh, Amit Chakraborty, Georgia Olympia Brikis, Biswadip Dey
Physic Informed Neural Network Turbulent Flow PINN Method Reynolds Averaged Navier Stokes Surrogate Dynamic Eddy Viscosity

November 29, 2022

Multi-agent reinforcement learning for wall modeling in LES of flow over periodic hills
Di Zhou, Michael P. Whitmore, Kevin P. Griffin, H. Jane Bae
Multi Agent Reinforcement Learning Flow Mood Large Eddy Simulation Eddy Viscosity

June 21, 2022

Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations
Marius Kurz, Philipp Offenhäuser, Andrea Beck
Deep Reinforcement Learning Turbulence Model Large Eddy Simulation Differentiable Turbulence Eddy Viscosity

May 13, 2022

Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems
Marius Kurz, Philipp Offenhäuser, Dominic Viola, Oleksandr Shcherbakov, Michael Resch, Andrea Beck
Reinforcement Learning Deep Reinforcement Learning Computational Fluid Dynamic High Performance Computing System Eddy Viscosity

Eddy Viscosity

Papers

Implicit factorized transformer approach to fast prediction of turbulent channel flows

Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning

On the choice of training data for machine learning of geostrophic mesoscale turbulence

RANS-PINN based Simulation Surrogates for Predicting Turbulent Flows

Multi-agent reinforcement learning for wall modeling in LES of flow over periodic hills

Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations

Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems