Global spatio-temporal downscaling of ERA5 precipitation through generative AI

TL;DR

This paper introduces spateGAN-ERA5, a deep learning model that significantly enhances the resolution of global precipitation data, capturing extreme events and spatio-temporal variability for improved climate and hazard analysis.

Contribution

It presents the first global-scale spatio-temporal downscaling method for ERA5 precipitation data using a conditional GAN, achieving high resolution and realistic patterns with strong generalization.

Findings

Successfully downscales ERA5 data from 24 km/1 hr to 2 km/10 min resolution.

Captures extreme rainfall events and realistic spatio-temporal variability.

Demonstrates strong generalization across different climate zones.

Abstract

The spatial and temporal distribution of precipitation has a significant impact on human lives by determining freshwater resources and agricultural yield, but also rainfall-driven hazards like flooding or landslides. While the ERA5 reanalysis dataset provides consistent long-term global precipitation information that allows investigations of these impacts, it lacks the resolution to capture the high spatio-temporal variability of precipitation. ERA5 misses intense local rainfall events that are crucial drivers of devastating flooding - a critical limitation since extreme weather events become increasingly frequent. Here, we introduce spateGAN-ERA5, the first deep learning based spatio-temporal downscaling of precipitation data on a global scale. SpateGAN-ERA5 uses a conditional generative adversarial neural network (cGAN) that enhances the resolution of ERA5 precipitation data from 24 km and 1 hour to 2 km and 10 minutes, delivering high-resolution rainfall fields with realistic spatio-temporal patterns and accurate rain rate distribution including extremes. Its computational efficiency enables the generation of a large ensemble of solutions, addressing uncertainties inherent to the challenges of downscaling. Trained solely on data from Germany and validated in the US and Australia considering diverse climate zones, spateGAN-ERA5 demonstrates strong generalization indicating a robust global applicability. SpateGAN-ERA5 fulfils a critical need for high-resolution precipitation data in hydrological and meteorological research, offering new capabilities for flood risk assessment, AI-enhanced weather forecasting, and impact modelling to address climate-driven challenges worldwide.