Scientific multi-agent reinforcement learning for wall-models of turbulent flows

Abstract

The predictive capabilities of turbulent flow simulations, critical for aerodynamic design and weather prediction, hinge on the choice of turbulence models. The abundance of data from experiments and simulations and the advent of machine learning have provided a boost to turbulence modeling efforts. However, simulations of turbulent flows remain hindered by the inability of heuristics and supervised learning to model the near-wall dynamics. We address this challenge by introducing scientific multi-agent reinforcement learning (SciMARL) for the discovery of wall models for large-eddy simulations (LES). In SciMARL, discretization points act also as cooperating agents that learn to supply the LES closure model. The agents self-learn using limited data and generalize to extreme Reynolds numbers and previously unseen geometries. The present simulations reduce by several orders of magnitude the computational cost over fully-resolved simulations while reproducing key flow quantities. We believe that SciMARL creates unprecedented capabilities for the simulation of turbulent flows.

References in corpus (1)

• A neural network approach for the blind deconvolution of turbulent flows

Cited by in corpus (27)

• Enhancing Computational Fluid Dynamics with Machine Learning
• Improving aircraft performance using machine learning: a review
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Recent advances in applying deep reinforcement learning for flow control: perspectives and future directions
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations
• Machine learning building-block-flow wall model for large-eddy simulation
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems
• Deep Learning Closure Models for Large-Eddy Simulation of Flows around Bluff Bodies
• Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges
• Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored structures
• Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning
• A wall model for separated flows: embedded learning to improve a posteriori performance
• Predicting the wall-shear stress and wall pressure through convolutional neural networks
• SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
• Adjoint-based variational optimal mixed models for large-eddy simulation of turbulence
• Variational data assimilation in wall turbulence: From outer observations to wall stress and pressure
• Deep reinforcement learning for tracking a moving target in jellyfish-like swimming
• Large Language Model Driven Development of Turbulence Models
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics
• Flux-controlled wall model for large eddy simulation integrating the compressible law of the wall
• Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress Models
• Reinforcement Learning Closures for Underresolved Partial Differential Equations using Synthetic Data
• Multi-Agent Learning of Numerical Methods for Hyperbolic PDEs with Factored Dec-MDP