Parameterizing Vertical Mixing Coefficients in the Ocean Surface Boundary Layer using Neural Networks

TL;DR

This paper introduces a neural network-based approach to improve vertical mixing parameterizations in ocean models, leading to more accurate climate simulations by reducing biases in key ocean features.

Contribution

It develops a neural network-enhanced eddy diffusivity model that integrates data-driven methods into physical ocean modeling while preserving conservation principles.

Findings

Reduces biases in mixed-layer depth.

Improves upper ocean stratification predictions.

Maintains conservation principles in the enhanced scheme.

Abstract

Vertical mixing parameterizations in ocean models are formulated on the basis of the physical principles that govern turbulent mixing. However, many parameterizations include ad hoc components that are not well constrained by theory or data. One such component is the eddy diffusivity model, where vertical turbulent fluxes of a quantity are parameterized from a variable eddy diffusion coefficient and the mean vertical gradient of the quantity. In this work, we improve a parameterization of vertical mixing in the ocean surface boundary layer by enhancing its eddy diffusivity model using data-driven methods, specifically neural networks. The neural networks are designed to take extrinsic and intrinsic forcing parameters as input to predict the eddy diffusivity profile and are trained using output data from a second moment closure turbulent mixing scheme. The modified vertical mixing scheme predicts the eddy diffusivity profile through online inference of neural networks and maintains the conservation principles of the standard ocean model equations, which is particularly important for its targeted use in climate simulations. We describe the development and stable implementation of neural networks in an ocean general circulation model and demonstrate that the enhanced scheme outperforms its predecessor by reducing biases in the mixed-layer depth and upper ocean stratification. Our results demonstrate the potential for data-driven physics-aware parameterizations to improve global climate models.