On the use of Deep Generative Models for Perfect Prognosis Climate Downscaling
This work addresses the need for spatially consistent climate downscaling for sectoral applications, representing an incremental improvement over existing methods.
The study tackled the problem of deficient spatial structures in climate downscaling by using deep generative models, resulting in improved spatial consistency for high-resolution fields, which is crucial for applications like hydrology.
Deep Learning has recently emerged as a perfect prognosis downscaling technique to compute high-resolution fields from large-scale coarse atmospheric data. Despite their promising results to reproduce the observed local variability, they are based on the estimation of independent distributions at each location, which leads to deficient spatial structures, especially when downscaling precipitation. This study proposes the use of generative models to improve the spatial consistency of the high-resolution fields, very demanded by some sectoral applications (e.g., hydrology) to tackle climate change.