ACE2-NEMO: Coupling an ML atmospheric emulator to a full-depth dynamical ocean model

TL;DR

This study introduces a novel hybrid Earth system model coupling a machine-learned atmospheric emulator with a full-depth ocean model, enabling multi-decadal climate simulations to evaluate emergent behaviors and climate responses.

Contribution

It presents the first multi-decadal coupled simulations of a machine-learned atmosphere with a full-depth dynamical ocean, assessing its realism and response to greenhouse gases.

Findings

Realistic fast timescale air-sea coupling in tropical Pacific

Unrealistic low amplitude variability due to weak atmospheric feedback

Initial CO2 response aligns with traditional models but shows deviations

Abstract

Understanding how fast atmospheric variability shapes slow climate variability and sensitivity remains a central challenge in Earth-system science. Recent advances in machine-learned (ML) atmospheric models have demonstrated remarkable skill on weather timescales, but their emergent behaviour in a fully coupled climate system remains largely unexplored. We present early results from a new hybrid modelling framework, in which the ACE2 ML atmospheric emulator is interactively coupled to the NEMO ocean model. We report on a set of 70-year coupled simulations (1950-2020 historical forcing and fixed-1950s control). These experiments represent, to our knowledge, the first multi-decadal integrations of a machine-learned atmosphere interacting with a full-depth dynamical ocean. Several historical and fixed-1950s control simulations from the fully dynamic global coupled climate model EC-Earth, which has the same ocean component used in ACE2-NEMO, are also considered for comparison. We assess the behaviour of the coupled system, with particular focus on low-frequency tropical variability and the climate response to greenhouse-gas forcing. Analysis of potentially emergent El Ni\~{n}o-like variability reveals realistic fast timescale air-sea coupling in the tropical Pacific, but the temporal variability is unrealistic, with very low amplitude oscillations; this appears to be due to weak atmospheric feedback in the tropical Pacific. The response to CO2 forcing shows initial agreement with EC-Earth3P, but deviates due to reduced downward short-wave radiation in ACE2. These results provide a unique test of physical realism for atmospheric emulators, and evaluate the possible role of entirely machine-learned components in next-generation Earth system models.