Learning to generate physical ocean states: Towards hybrid climate modeling

TL;DR

This paper introduces a hybrid climate modeling approach that combines deep generative models with physical constraints to generate consistent ocean states, aiming to reduce computational costs and improve climate projection accuracy.

Contribution

It proposes a novel hybrid method integrating deep learning and physical modeling to produce physically consistent ocean states for climate simulations.

Findings

Physical constraints improve generative model accuracy.

Hybrid approach reduces computational costs.

Potential to decrease uncertainties in climate projections.

Abstract

Ocean General Circulation Models require extensive computational resources to reach equilibrium states, while deep learning emulators, despite offering fast predictions, lack the physical interpretability and long-term stability necessary for climate scientists to understand climate sensitivity (to greenhouse gas emissions) and mechanisms of abrupt % variability such as tipping points. We propose to take the best from both worlds by leveraging deep generative models to produce physically consistent oceanic states that can serve as initial conditions for climate projections. We assess the viability of this hybrid approach through both physical metrics and numerical experiments, and highlight the benefits of enforcing physical constraints during generation. Although we train here on ocean variables from idealized numerical simulations, we claim that this hybrid approach, combining the computational efficiency of deep learning with the physical accuracy of numerical models, can effectively reduce the computational burden of running climate models to equilibrium, and reduce uncertainties in climate projections by minimizing drifts in baseline simulations.