Use-case of Deep Generative Models for Perfect Prognosis Climate Downscaling

Abstract

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. We propose the use of generative models to improve the spatial consistency of the highresolution fields, very demanded by some sectoral applications (e.g., hydrology) to tackle climate change. To illustrate these points we develop a simple use-case of Perfect Prognosis Downscaling over Europe using a Generative Model, more specifically a Conditional Variational Autoencoder (CVAE).