Earth System Models (ESMs) are essential tools for understanding the interaction of the human and Earth systems. One key application of these models is studying extreme weather events, such as heat waves or high intensity precipitation events, which have significant socioeconomic consequences. However, the computational demands of running a sufficient number of simulations to robustly characterize expected changes in these hazards, and therefore provide a strong basis to analyze the ensuing risks, are often prohibitive. In this paper we demonstrate that diffusion models – a class of generative deep learning models – can effectively emulate the spatio-temporal trends of ESM daily output. Trained on a handful of runs, reflecting a wide range of radiative forcings, our DiffESM model takes monthly mean precipitation or temperature as input and is capable of producing daily values of temperature and precipitation that have statistical characteristics close to the ESM output. This approach requires only a small fraction of the computational resources that would be needed to run a large ensemble under any scenario of interest. We evaluate model behavior over a range of scenarios, time horizons and two ESMs, using a number of extreme metrics, including ones that have been long established in the climate modeling and analysis community. Our results show that the samples produced by DiffESM closely matches the spatio-temporal behavior of the ESM output it emulates in terms of the frequency and spatial characteristics of phenomena such as heat waves, dry spells, or rainfall intensity.

Understanding equilibrium climate sensitivity (ECS, warming in response to a doubling of CO2) uncertainty is fundamental for making reliable climate projections. We leverage the Hector simple climate model in a probabilistic framework to explore how different ECS priors influence long-term (2081-2100) temperature anomalies. Specifically, we quantify how different ECS prior distributions broaden the uncertainty in temperature projections. This method demonstrates a computationally efficient probabilistic workflow that explores the effects of parameter priors on climate projections. Excluding process and paleoclimate evidence widens the resulting temperature projection uncertainty (1.12-3.03 ℃ and 1.09-3.33 ℃, respectively) while using priors that synthesize all lines of evidence leads to narrowed temperature projection uncertainty (1.24-2.89 ℃). Our study shows that excluding paleoclimate and process data in ECS priors broadens temperature projection uncertainty. In contrast, synthesized evidence provides a narrower and potentially more robust range of future temperature outcomes.