Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network

TL;DR

This paper presents a recurrent, stochastic GAN that generates realistic, temporally consistent high-resolution atmospheric fields from low-resolution sequences, enabling effective downscaling and long-term time series generation.

Contribution

It introduces a novel stochastic, recurrent GAN architecture for downscaling atmospheric data, capable of producing ensembles and long-duration sequences with realistic variability.

Findings

GAN produces realistic, temporally consistent super-resolution sequences.

The generated ensembles exhibit correct variability as per rank statistics.

The model can be applied to larger images and longer sequences than training data.

Abstract

Generative adversarial networks (GANs) have been recently adopted for super-resolution, an application closely related to what is referred to as "downscaling" in the atmospheric sciences: improving the spatial resolution of low-resolution images. The ability of conditional GANs to generate an ensemble of solutions for a given input lends itself naturally to stochastic downscaling, but the stochastic nature of GANs is not usually considered in super-resolution applications. Here, we introduce a recurrent, stochastic super-resolution GAN that can generate ensembles of time-evolving high-resolution atmospheric fields for an input consisting of a low-resolution sequence of images of the same field. We test the GAN using two datasets, one consisting of radar-measured precipitation from Switzerland, the other of cloud optical thickness derived from the Geostationary Earth Observing Satellite 16 (GOES-16). We find that the GAN can generate realistic, temporally consistent super-resolution sequences for both datasets. The statistical properties of the generated ensemble are analyzed using rank statistics, a method adapted from ensemble weather forecasting; these analyses indicate that the GAN produces close to the correct amount of variability in its outputs. As the GAN generator is fully convolutional, it can be applied after training to input images larger than the images used to train it. It is also able to generate time series much longer than the training sequences, as demonstrated by applying the generator to a three-month dataset of the precipitation radar data. The source code to our GAN is available at https://github.com/jleinonen/downscaling-rnn-gan.