Isabella Fumarola

Mastering turbulence remains one of physics’ most intractable challenges, with its chaotic, multi-scale dynamics driving energy dissipation across transport and energy systems. Here we report REACT (Reinforcement Learning for Environmental Adaptation and Control of Turbulence), a fully autonomous reinforcement learning framework that achieves real-time, adaptive, closed-loop turbulence control in real-world environments. Deployed on a road vehicle model equipped solely with onboard sensors and servo-actuated surfaces, REACT learns directly from sparse experimental measurements in a wind tunnel environment, bypassing intractable direct numerical simulations and empirical turbulence models. The agent autonomously converges to a policy that reduces aerodynamic drag while achieving net energy savings. Without prior knowledge of flow physics, it discovers that dynamically suppressing spatio-temporally coherent flow structures in the vehicle wake maximizes energy efficiency, achieving two to four times greater performance than model-based baseline controllers. Through a physics-informed training that recasts data in terms of dimensionless physical groups and parametric input spaces, REACT synthesizes offline a single generalizable agent that transfers across speeds without retraining. These results move agentic learning beyond simulation to robust, interpretable real-world control of high‑Reynolds turbulence, opening a path to self‑optimizing physical systems in transport, energy and environmental flows.

Mastering turbulence remains one of physics' most intractable challenges, with its chaotic, multi-scale dynamics driving energy dissipation across transport and energy systems. Here we report REACT (Reinforcement Learning for Environmental Adaptation and Control of Turbulence), a fully autonomous reinforcement learning framework that achieves real-time, adaptive, closed-loop turbulence control in real-world environments. Deployed on a road vehicle model equipped solely with onboard sensors and servo-actuated surfaces, REACT learns directly from sparse experimental measurements in a wind tunnel environment, bypassing intractable direct numerical simulations and empirical turbulence models. The agent autonomously converges to a policy that reduces aerodynamic drag while achieving net energy savings. Without prior knowledge of flow physics, it discovers that dynamically suppressing spatio-temporally coherent flow structures in the vehicle wake maximizes energy efficiency, achieving two to four times greater performance than model-based baseline controllers. Through a physics-informed training that recasts data in terms of dimensionless physical groups and parametric input spaces, REACT synthesizes offline a single generalizable agent that transfers across speeds without retraining. These results move agentic learning beyond simulation to robust, interpretable real-world control of high-Reynolds turbulence, opening a path to self-optimizing physical systems in transport, energy and environmental flows.

Among the different passive and active techniques for skin friction drag reduction for turbulent boundary layers, near wall forcing through moving walls is one of the most promising techniques at low Reτ. Fewer studies have looked at the mechanism at high Reτ, closer to flight conditions, largerly because, in this regime, numerical simulations become harder and experiments more challenging. To that end, there is the need of a systematic study for different surface waves and flow conditions. A new model using a kagome lattice is presented. It will be tested in the 10x5 wind tunnel at Reτ ≈ 8000. This work introduces an experimental setup which combines simultaneous measurements of surface displacement and velocity in the boundary layer. Here the results from a shorted version of the model at Reτ ≈ 1000 are presented to demonstrate the capability of the experimental setup.