Abstract Although autoregressive machine learning‐based emulators have been trained to produce stable and accurate rollouts in the climate of the present‐day and recent past, none so far have been trained to emulate the sensitivity of climate to substantial changes in or other greenhouse gases. As an initial step we couple the Ai2 Climate Emulator version 2 to a slab ocean model (hereafter ACE2‐SOM) and train it on output from a collection of equilibrium‐climate physics‐based reference simulations with varying levels of . We test it in equilibrium and non‐equilibrium climate scenarios with concentrations seen and unseen in training. ACE2‐SOM performs well in equilibrium‐climate inference with both in‐sample and out‐of‐sample concentrations, accurately reproducing the emergent time‐mean spatial patterns of surface temperature and precipitation change with doubling, tripling, or quadrupling. In addition, the vertical profile of atmospheric warming and change in extreme precipitation rates up to the 99.9999th percentile closely agree with the reference model. Non‐equilibrium‐climate inference is more challenging. With increasing gradually at a rate of 2% year −1 , ACE2‐SOM can accurately emulate the global annual mean trends of surface and lower‐to‐middle atmosphere fields but produces unphysical jumps in stratospheric fields. With an abrupt quadrupling of , ML‐controlled fields transition unrealistically quickly to the regime. In doing so they violate global energy conservation and exhibit unphysical sensitivities of surface and top of atmosphere radiative fluxes to instantaneous changes in . Future emulator development needed to address these issues should improve its generalizability to diverse climate change scenarios.
Clark et al. (Tue,) studied this question.