Online learning in idealized ocean gyres

TL;DR

This paper explores online learning for data-driven eddy parameterization in idealized ocean gyres, demonstrating that neural networks can be trained to produce stable, accurate, and variable coarse-resolution models of ocean dynamics.

Contribution

It introduces an end-to-end differentiable dynamical system trained via online learning for ocean turbulence modeling, a novel approach in this context.

Findings

Neural network parameterizations can produce stable coarse models.

Trained models capture mean state and variability.

Approach is effective in a challenging idealized test case.

Abstract

Ocean turbulence parameterization has principally been based on processed-based approaches, seeking to embed physical principles so that coarser resolution calculations can capture the net influence of smaller scale unresolved processes. More recently there has been an increasing focus on the application of data-driven approaches to this problem. Here we consider the application of online learning to data-driven eddy parameterization, constructing an end-to-end differentiable dynamical solver forced by a neural network, and training the neural network based on the dynamics of the combined hybrid system. This approach is applied to the classic barotropic Stommel-Munk gyre problem -- a highly idealized configuration which nevertheless includes multiple flow regimes, boundary dynamics, and a separating jet, and therefore presents a challenging test case for the online learning approach. It is found that a neural network which is suitably trained can lead to a coarse resolution neural network parameterized model which is stable, and has both a reasonable mean state and intrinsic variability. This suggests that online learning is a powerful tool for studying the problem of ocean turbulence parameterization.