Collaborative Research: CAIG: Multi-scale AI-powered modeling of small-scale turbulence within the coupled air-sea boundary layers

Southern Methodist University, Dallas TX

Investigators

Abstract

Surface waves and their resulting turbulent processes play a central role in regulating the exchanges of mass, momentum, and energy between the atmosphere and ocean, directly influencing sea states, weather patterns, and climate systems. Although integrating the dynamics of surface waves into the coupled atmospheric-oceanic models is crucial for accurate weather and climate forecasts, the current understanding of fundamental processes that link the turbulent flow structures above and below the surface within the coupled air-sea boundary layers is limited. This is due to challenges in resolving the dynamics of small-scale turbulence in the vicinity of the air-sea interface. This project will combine high-resolution laboratory experiments, high-fidelity numerical simulations, and foundational AI techniques to examine the multiscale turbulence above and below ocean surface waves and quantify the two-way coupled air-sea momentum and energy fluxes at the air-sea interface. This project will examine the coupling of wave-induced flow structures above and below the air-sea interface. A synergistic experimental and AI-driven approach will be used to develop a comprehensive parameterization of wave and turbulent stresses at the air-sea interface. The aim is to address the turbulent closure problem in the governing equations and improve predictive models of air-sea fluxes. A combination of novel experiments that concurrently measure air- and water-side flow velocities and an advanced multiscale AI-driven framework that completes the partially measured statistical signatures of the flow will be employed. The AI model will integrate attention mechanisms with physics-informed neural networks (PINNs) to enhance the two-dimensional planar velocity measurements by reconstructing the third velocity component and the pressure field. The resulting dataset will support the development of data-driven surrogate models for air-sea fluxes with enhanced physical consistency and superior generalizability. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.