Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators

TL;DR

This paper demonstrates that machine-learning weather emulators trained on historical data can effectively simulate fast radiative feedback responses to greenhouse gas perturbations, aligning with full-physics Earth System Models.

Contribution

It shows that ML weather emulators trained on historical reanalyses can predict radiative feedbacks without retraining for future conditions.

Findings

ML emulators' responses agree with Earth System Models.

Fast precipitation responses to CO2 perturbations are captured.

Historical training suffices for studying radiative-convective equilibrium.

Abstract

The response of the climate system to increased greenhouse gases and other radiative perturbations is governed by a combination of fast and slow feedbacks. Slow feedbacks are typically activated in response to changes in ocean temperatures on decadal timescales and manifest as changes in climatic state with no recent historical analogue. However, fast feedbacks are activated in response to rapid atmospheric physical processes on weekly timescales, and they are already operative in the present-day climate. This distinction implies that the physics of fast radiative feedbacks is present in the historical meteorological reanalyses used to train many recent successful machine-learning-based (ML) emulators of weather and climate. In addition, these feedbacks are functional under the historical boundary conditions pertaining to the top-of-atmosphere radiative balance and sea-surface temperatures. Together, these factors imply that we can use historically trained ML weather emulators to study the response of radiative-convective equilibrium (RCE), and hence the global hydrological cycle, to perturbations in carbon dioxide and other well-mixed greenhouse gases. Without retraining on prospective Earth system conditions, we use ML weather emulators to quantify the fast precipitation response to reduced and elevated carbon dioxed concentrations with no recent historical precedent. We show that the responses from historically trained emulators agree with those produced by full-physics Earth System Models (ESMs). In conclusion, we discuss the prospects for and advantages from using ESMs and ML emulators to study fast processes in global climate.