5
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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. 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 solutions 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.

          Related collections

          Author and article information

          Journal
          20 May 2020
          Article
          2005.10374
          299dc215-78c1-4741-a0aa-1c9eed927e16

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          Submitted to IEEE Transactions in Geoscience and Remote Sensing
          eess.IV cs.LG physics.ao-ph stat.ML

          Machine learning,Atmospheric, Oceanic and Environmental physics,Artificial intelligence,Electrical engineering

          Comments

          Comment on this article