Atmosphere Ocean Science Colloquium
Towards a unified data-driven boundary layer momentum flux parameterization for ocean and atmosphere
Speaker: Renaud Falga, NYU
Location: Warren Weaver Hall 1302
Date: Wednesday, September 24, 2025, 3:30 p.m.
Synopsis:
Boundary layer turbulence, particularly the vertical flux of momentum, shapes the evolution of winds and currents and plays a critical role in weather, climate, and biogeochemical processes. In this work, a unified, data-driven parameterization of turbulent momentum fluxes is introduced for both the oceanic and atmospheric convective boundary layers. An artificial neural network (ANN) is trained offline on coarse-grained large-eddy simulation (LES) data representing a wide range of convective regimes in both fluids. By normalizing momentum flux profiles with their surface values, we reveal a self-similar structure across regimes and fluids, enabling joint training. The ANN learns to predict vertical profiles of subgrid momentum fluxes from mean wind or current profiles, and our results show that such a machine-learning based unified parameterization has the potential to outperform traditional first-order schemes.