Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence

Junhyuk Kim, Hyojin Kim, Jiyeon Kim, Changhoon Lee

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


The development of a reliable subgrid-scale (SGS) model for large-eddy simulation (LES) is of great importance for many scientific and engineering applications. Recently, deep learning approaches have been tested for this purpose using high-fidelity data such as direct numerical simulation (DNS) in a supervised learning process. However, such data are generally not available in practice. Deep reinforcement learning (DRL) using only limited target statistics can be an alternative algorithm in which the training and testing of the model are conducted in the same LES environment. The DRL of turbulence modeling remains challenging owing to its chaotic nature, high dimensionality of the action space, and large computational cost. In this study, we propose a physics-constrained DRL framework that can develop a deep neural network-based SGS model for LES of turbulent channel flow. The DRL models that produce the SGS stress were trained based on the local gradient of the filtered velocities. The developed SGS model automatically satisfies the reflectional invariance and wall boundary conditions without an extra training process so that DRL can quickly find the optimal policy. Furthermore, direct accumulation of reward, spatially and temporally correlated exploration, and the pre-training process are applied for efficient and effective learning. In various environments, our DRL could discover SGS models that produce the viscous and Reynolds stress statistics perfectly consistent with the filtered DNS. By comparing various statistics obtained by the trained models and conventional SGS models, we present a possible interpretation of better performance of the DRL model.

Original languageEnglish
Article number105132
JournalPhysics of Fluids
Issue number10
Publication statusPublished - 2022 Oct 1

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korean Government MSIT (Grant Nos. 2017R1E1A1A03070282 and 2022R1A2C2005538).

Publisher Copyright:
© 2022 Author(s).

All Science Journal Classification (ASJC) codes

  • Computational Mechanics
  • Condensed Matter Physics
  • Mechanics of Materials
  • Mechanical Engineering
  • Fluid Flow and Transfer Processes


Dive into the research topics of 'Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence'. Together they form a unique fingerprint.

Cite this