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

Abstract

This study proposes a novel method for developing discretization-consistent closure schemes for implicitly filtered Large Eddy Simulation (LES). Here, the induced filter kernel, and thus the closure terms, are determined by the properties of the grid and the discretization operator, leading to additional computational subgrid terms that are generally unknown in a priori analysis. In this work, the task of adapting the coefficients of LES closure models is thus framed as a Markov decision process and solved in an a posteriori manner with Reinforcement Learning (RL). This optimization framework is applied to both explicit and implicit closure models. The explicit model is based on an element-local eddy viscosity model. The optimized model is found to adapt its induced viscosity within discontinuous Galerkin (DG) methods to homogenize the dissipation within an element by adding more viscosity near its center. For the implicit modeling, RL is applied to identify an optimal blending strategy for a hybrid DG and Finite Volume (FV) scheme. The resulting optimized discretization yields more accurate results in LES than either the pure DG or FV method and renders itself as a viable modeling ansatz that could initiate a novel class of high-order schemes for compressible turbulence by combining turbulence modeling with shock capturing in a single framework. All newly derived models achieve accurate results that either match or outperform traditional models for different discretizations and resolutions. Overall, the results demonstrate that the proposed RL optimization can provide discretization-consistent closures that could reduce the uncertainty in implicitly filtered LES.

arXiv comment24 pages, 14 figures. Accepted Manuscript. This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Physics of Fluids 35 (2023) and may be found at https://doi.org/10.1063/5.0176223

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• Artificial Neural Networks trained through Deep Reinforcement Learning discover control strategies for active flow control
• Split Form Nodal Discontinuous Galerkin Schemes with Summation-By-Parts Property for the Compressible Euler Equations
• Deep Neural Networks for Data-Driven Turbulence Models
• PyFR: An Open Source Framework for Solving Advection-Diffusion Type Problems on Streaming Architectures using the Flux Reconstruction Approach
• Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach
• Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning
• Meta-Reinforcement Learning of Structured Exploration Strategies
• Scientific multi-agent reinforcement learning for wall-models of turbulent flows
• Recent advances in applying deep reinforcement learning for flow control: perspectives and future directions
• Transfer Learning in Deep Reinforcement Learning: A Survey
• A provably entropy stable subcell shock capturing approach for high order split form DG for the compressible Euler Equations
• On the use of kinetic energy preserving DG-schemes for large eddy simulation
• Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations
• A Neural Network based Shock Detection and Localization Approach for Discontinuous Galerkin Methods
• Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
• HORSES3D: a high-order discontinuous Galerkin solver for flow simulations and multi-physics applications
• Subcell limiting strategies for discontinuous Galerkin spectral element methods
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• Effects of resolution inhomogeneity in large-eddy simulation
• A large eddy simulation method for DGSEM using non-linearly optimized relaxation filters

Cited by in corpus (5)

• OpenFOAMGPT: a RAG-Augmented LLM Agent for OpenFOAM-Based Computational Fluid Dynamics
• GALÆXI: Solving complex compressible flows with high-order discontinuous Galerkin methods on accelerator-based systems
• Discretize first, filter next: learning divergence-consistent closure models for large-eddy simulation
• A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics