Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows
On the map: Deep reinforcement learning methods → RL with diffusion and flow models
Abstract (arXiv)
Assessing turbulence control effects for wall friction numerically is a significant challenge since it requires expensive simulations of turbulent fluid dynamics. We instead propose an efficient deep reinforcement learning (RL) framework for modeling and control of turbulent flows. It is model-based RL for predictive control (PC), where both the policy and the observer models for turbulence control are learned jointly using Physics Informed Neural Operators (PINO), which are discretization invariant and can capture fine scales in turbulent flows accurately. Our PINO-PC outperforms prior model-free reinforcement learning methods in various challenging scenarios where the flows are of high Reynolds numbers and unseen, i.e., not provided during model training. We find that PINO-PC achieves a drag reduction of 39.0% under a bulk-velocity Reynolds number of 15,000, outperforming previous fluid control methods by more than 32%.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods. Builds on 9 of its 50 references that are in the map. First posted on arXiv 3 Oct 2025.
Builds on
9 of 50 references.
References · 9
- 2014Adam: A Method for Stochastic Optimizationcited by 37,093
- 2015Continuous control with deep reinforcement learningcited by 3,290
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,857
- 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 522
- 2019Model-Based Reinforcement Learning for Ataricited by 499
- 2021Neural Operator: Learning Maps Between Function Spacescited by 414
- 2023Neural Operators for Accelerating Scientific Simulations and Designcited by 220
- 2020Convolutional-network models to predict wall-bounded turbulence from wall quantitiescited by 46
- 2023Tipping Point Forecasting in Non-Stationary Dynamics on Function Spacescited by 8
Built on by
Citing papers per year: 2026: 2.
2 papers.