Emulating the Forced Response of Climate Models with Generative Machine Learning

Global climate models are essential tools to simulate past and potential future pathways of climate change, as well as associated climate impacts. Shared Socioeconomic Pathways (SSPs) describe a range of future scenarios of global economic and demographic development. These SSPs are intrinsically linked to changes in climate forcings—the external drivers, such as greenhouse gas and aerosol emissions, which change Earth’s energy balance over time. These forcings act as boundary conditions in Earth System Models (ESM), providing insight into the potential climatic impacts of each SSP. Running an ESM, however, is extremely computationally expensive, conflicting with the need for large ensemble runs to provide robust estimates in the presence of internal variability and scenario uncertainty. Machine Learning emulators provide a promising avenue toward fast and cheap scenario generation, but until recently lacked uncertainty quantification and the ability to condition on external forcings. Here, we build upon recent work \cite{clyneArchesClimateProbabilisticDecadal2025} and extend it by training on multiple SSPs. We successfully generate scenarios of IPSL-CM6A-LR unseen during training and that remain largely physically consistent with the underlying climate model, including under moderate extrapolation. Under an abrupt-4$\times$CO$_2$ step, however, the model does not reproduce the transient climate response. Our emulator is validated against MESMER-M, a statistical emulator of land surface temperature. Our research demonstrates that our model, ArchesClimate-SSP, does not simply imitate scenarios seen during training, but is actually capable of modeling the response of a climate state to diverse forcings. This is an important step toward reliable and rapid climate model scenario generation.