Calibration of a neural network ocean closure for improved mean state and variability

TL;DR

This paper presents a neural network-based parameterization for mesoscale eddies in ocean models, calibrated via Ensemble Kalman Inversion to significantly reduce biases and improve variability in coarse-resolution simulations.

Contribution

It introduces a systematic calibration method using EKI for neural network ocean closures, enhancing model accuracy over ad hoc tuning.

Findings

Calibration reduces errors by factors of 1.7-3.3 in mean state and variability.

EKI method is robust to chaotic noise in ocean dynamics.

Proposes an efficient calibration protocol avoiding equilibrium integration.

Abstract

Global ocean models exhibit biases in the mean state and variability, particularly at coarse resolution, where mesoscale eddies are unresolved. To address these biases, parameterization coefficients are typically tuned ad hoc. Here, we formulate parameter tuning as a calibration problem using Ensemble Kalman Inversion (EKI). We optimize parameters of a neural network parameterization of mesoscale eddies in two idealized ocean models at coarse resolution. The calibrated parameterization reduces errors by factors of 1.7-3.3 in the time-averaged fluid interfaces and their variability compared to the unparameterized model, depending on the metric and configuration. The EKI method is robust to noise in time-averaged statistics arising from chaotic ocean dynamics. Furthermore, we propose an efficient calibration protocol that bypasses integration to statistical equilibrium by carefully choosing an initial condition. These results demonstrate that systematic calibration can substantially improve coarse-resolution ocean simulations and provide a practical pathway for reducing biases in global ocean models.