Probabilistic Emulation of a Global Climate Model with Spherical DYffusion

TL;DR

This paper introduces a novel probabilistic deep learning model that emulates a global climate model, achieving stable long-term simulations with high accuracy and physical consistency, thus advancing data-driven climate modeling capabilities.

Contribution

It presents the first conditional generative model combining DYffusion and SFNO for stable, long-term climate emulation with low computational cost.

Findings

Achieves near gold-standard performance in climate model emulation

Outperforms existing approaches in accuracy and efficiency

Enables 100-year stable climate simulations at 6-hour intervals

Abstract

Data-driven deep learning models are transforming global weather forecasting. It is an open question if this success can extend to climate modeling, where the complexity of the data and long inference rollouts pose significant challenges. Here, we present the first conditional generative model that produces accurate and physically consistent global climate ensemble simulations by emulating a coarse version of the United States' primary operational global forecast model, FV3GFS. Our model integrates the dynamics-informed diffusion framework (DYffusion) with the Spherical Fourier Neural Operator (SFNO) architecture, enabling stable 100-year simulations at 6-hourly timesteps while maintaining low computational overhead compared to single-step deterministic baselines. The model achieves near gold-standard performance for climate model emulation, outperforming existing approaches and demonstrating promising ensemble skill. This work represents a significant advance towards efficient, data-driven climate simulations that can enhance our understanding of the climate system and inform adaptation strategies.