Conditional diffusion models for downscaling and bias correction of Earth system model precipitation

TL;DR

This paper introduces a conditional diffusion model that improves high-resolution precipitation simulation by simultaneously bias correcting and downscaling Earth System Model outputs, outperforming existing methods especially for extreme events.

Contribution

It presents a novel machine learning framework that uses a shared embedding space and a conditional diffusion model for bias correction and downscaling without retraining for new ESM data.

Findings

Outperforms existing statistical and deep learning methods.

Preserves spatial patterns larger than a specified scale.

Effectively corrects biases and downscales precipitation data.

Abstract

Climate change exacerbates extreme weather events like heavy rainfall and flooding. As these events cause severe socioeconomic damage, accurate high-resolution simulation of precipitation is imperative. However, existing Earth System Models (ESMs) struggle to resolve 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 first map observational and ESM data to a shared embedding space, where both are unbiased towards each other, and then train a conditional diffusion model to reverse the mapping. Only observational data is used for the training, so that the diffusion model can be employed to correct and downscale any ESM field without need for retraining. Our approach ensures statistical fidelity and preserves spatial patterns larger than a chosen spatial correction scale. We demonstrate that our approach outperforms existing statistical and deep learning methods especially regarding extreme events.