Fast, scale-adaptive and uncertainty-aware downscaling of Earth system model fields with generative machine learning

Philipp Hess, Michael Aich, Baoxiang Pan, Niklas Boers

Abstract: Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socioeconomic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high spatial resolution. Recent machine learning approaches have shown promising results in downscaling ESM simulations, outperforming state-of-the-art statistical approaches. However, existing methods require computationally costly retraining for each ESM and extrapolate poorly to climates unseen during training. We address these shortcomings by learning a consistency model that efficiently and accurately downscales arbitrary ESM simulations without retraining in a zero-shot manner. Our approach yields probabilistic downscaled fields at a resolution only limited by the observational reference data. We show that the consistency model outperforms state-of-the-art diffusion models at a fraction of the computational cost and maintains high controllability on the downscaling task. Further, our method generalizes to climate states unseen during training without explicitly formulated physical constraints. A generative machine learning approach is proposed to improve the resolution of Earth system models in an efficient, adaptive and uncertainty-aware manner.