Conditional diffusion models for downscaling & bias correction of Earth system model precipitation
Michael Aich, Philipp Hess, Baoxiang Pan, Sebastian Bathiany, Yu Huang, Niklas Boers
Abstract
Abstract. Climate change exacerbates extreme weather events like heavy rainfall and flooding. As these events cause severe socioeconomic damages, accurate high-resolution simulation of precipitation is imperative. However, existing Earth System Models (ESMs) struggle resolving small-scale dynamics and suffer from biases. Traditional statistical bias correction and downscaling methods fall short in improving spatial structure, while recent deep learning methods lack controllability and suffer from unstable training. Here, we propose a machine learning framework for simultaneous bias correction and downscaling. We train a generative diffusion model purely on observational data. We map observational and ESM data to a shared embedding space, where both are unbiased towards each other and train a conditional diffusion model to reverse the mapping. Our method can correct any ESM field, as the training is independent of the ESM. Our approach ensures statistical fidelity, preserves large-scale spatial patterns and outperforms existing methods especially regarding extreme events.