Climate Variable Downscaling with Conditional Normalizing Flows

TL;DR

This paper introduces a novel application of conditional normalizing flows for climate variable downscaling, enabling more detailed regional climate predictions and uncertainty quantification from coarse global models.

Contribution

It demonstrates the effectiveness of conditional normalizing flows for climate downscaling and uncertainty estimation, a new approach in this domain.

Findings

Successful downscaling on ERA5 water content data

Effective uncertainty quantification through standard deviation

Applicable to various upsampling factors

Abstract

Predictions of global climate models typically operate on coarse spatial scales due to the large computational costs of climate simulations. This has led to a considerable interest in methods for statistical downscaling, a similar process to super-resolution in the computer vision context, to provide more local and regional climate information. In this work, we apply conditional normalizing flows to the task of climate variable downscaling. We showcase its successful performance on an ERA5 water content dataset for different upsampling factors. Additionally, we show that the method allows us to assess the predictive uncertainty in terms of standard deviation from the fitted conditional distribution mean.