Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations

06/21/2022
by   Marius Kurz, et al.
0

Over the last years, supervised learning (SL) has established itself as the state-of-the-art for data-driven turbulence modeling. In the SL paradigm, models are trained based on a dataset, which is typically computed a priori from a high-fidelity solution by applying the respective filter function, which separates the resolved and the unresolved flow scales. For implicitly filtered large eddy simulation (LES), this approach is infeasible, since here, the employed discretization itself acts as an implicit filter function. As a consequence, the exact filter form is generally not known and thus, the corresponding closure terms cannot be computed even if the full solution is available. The reinforcement learning (RL) paradigm can be used to avoid this inconsistency by training not on a previously obtained training dataset, but instead by interacting directly with the dynamical LES environment itself. This allows to incorporate the potentially complex implicit LES filter into the training process by design. In this work, we apply a reinforcement learning framework to find an optimal eddy-viscosity for implicitly filtered large eddy simulations of forced homogeneous isotropic turbulence. For this, we formulate the task of turbulence modeling as an RL task with a policy network based on convolutional neural networks that adapts the eddy-viscosity in LES dynamically in space and time based on the local flow state only. We demonstrate that the trained models can provide long-term stable simulations and that they outperform established analytical models in terms of accuracy. In addition, the models generalize well to other resolutions and discretizations. We thus demonstrate that RL can provide a framework for consistent, accurate and stable turbulence modeling especially for implicitly filtered LES.

READ FULL TEXT

page 5

page 7

page 9

page 10

research
09/12/2023

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

We propose a novel method for developing discretization-consistent closu...
research
10/01/2020

A machine learning framework for LES closure terms

In the present work, we explore the capability of artificial neural netw...
research
03/04/2023

Dynamic Deep Learning LES Closures: Online Optimization With Embedded DNS

Deep learning (DL) has recently emerged as a candidate for closure model...
research
06/11/2021

GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning

Deep Q Network (DQN) firstly kicked the door of deep reinforcement learn...
research
02/22/2020

Towards model discovery with reinforcement learning

We propose to learn (i) models expressed in analytical form, (ii) which...
research
12/29/2019

Computational model discovery with reinforcement learning

The motivation of this study is to leverage recent breakthroughs in arti...
research
05/18/2020

Automating Turbulence Modeling by Multi-Agent Reinforcement Learning

The modeling of turbulent flows is critical to scientific and engineerin...

Please sign up or login with your details

Forgot password? Click here to reset