NORi: An ML-Augmented Ocean Boundary Layer Parameterization
This addresses the challenge of accurate and stable turbulence parameterization for climate models, offering a robust paradigm that reduces data requirements and optimizes inference performance, though it is incremental in combining existing methods.
The paper tackles the problem of parameterizing ocean boundary layer turbulence in climate models by introducing NORi, a physics-based machine-learned parameterization that uses neural ordinary differential equations to capture entrainment dynamics. It demonstrates excellent prediction and generalization across various conditions, achieving numerical stability for at least 100 years of integration with time steps up to one hour.
NORi is a machine-learned (ML) parameterization of ocean boundary layer turbulence that is physics-based and augmented with neural networks. NORi stands for neural ordinary differential equations (NODEs) Richardson number (Ri) closure. The physical parameterization is controlled by a Richardson number-dependent diffusivity and viscosity. The NODEs are trained to capture the entrainment through the base of the boundary layer, which cannot be represented with a local diffusive closure. The parameterization is trained using large-eddy simulations in an "a posteriori" fashion, where parameters are calibrated with a loss function that explicitly depends on the actual time-integrated variables of interest rather than the instantaneous subgrid fluxes, which are inherently noisy. NORi is designed for the realistic nonlinear equation of state of seawater and demonstrates excellent prediction and generalization capabilities in capturing entrainment dynamics under different convective strengths, oceanic background stratifications, rotation strengths, and surface wind forcings. NORi is numerically stable for at least 100 years of integration time in large-scale simulations, despite only being trained on 2-day horizons, and can be run with time steps as long as one hour. The highly expressive neural networks, combined with a physically-rigorous base closure, prove to be a robust paradigm for designing parameterizations for climate models where data requirements are drastically reduced, inference performance can be directly targeted and optimized, and numerical stability is implicitly encouraged during training.