Technical Report: Towards Unified Diffusion Models for Multi-Model Climate Emulation at Scale

TL;DR

This paper introduces a unified diffusion model for climate emulation that efficiently generates large ensembles of temperature projections across multiple climate models and scenarios, reducing computational costs and enabling comprehensive uncertainty analysis.

Contribution

The paper presents a novel shared diffusion framework that models multiple climate models simultaneously, improving efficiency and generalization in climate projection emulation.

Findings

Reliable generalization to unseen models and future climates

Rapid generation of large climate ensembles

Enhanced uncertainty quantification across scenarios

Abstract

Large ensembles of climate projections are essential for characterizing uncertainty in future climate and extreme weather events, yet computational constraints of numerical climate models limit ensemble sizes to a small number of realizations per model. We present a unified conditional diffusion model that dramatically reduces this computational barrier by learning shared distributional patterns across multiple Coupled Model Intercomparison Project phase 6 models and emission scenarios. Rather than training separate emulators for each model-scenario combination, our approach captures the common statistical structures underlying nine CMIP6 models, generating daily temperature maps with a global coverage for historical and future periods. This unified framework enables: (i) efficient probabilistic sampling for comprehensive uncertainty quantification across models and scenarios; (ii) rapid generation of large ensembles that would be computationally intractable with traditional climate models; (iii) variance-reduced treatment effect analysis via fixed-seed generation that disentangles forced climate responses from internal variability. Evaluations on held-out models demonstrate reliable generalization to unseen future climates, enabling rapid exploration of different emission pathways.