Preprints
https://doi.org/10.5194/hess-2020-464
https://doi.org/10.5194/hess-2020-464

  30 Sep 2020

30 Sep 2020

Review status: a revised version of this preprint was accepted for the journal HESS.

Technical Note: Temporal Disaggregation of Spatial Rainfall Fields with Generative Adversarial Networks

Sebastian Scher1 and Stefanie Peßenteiner2 Sebastian Scher and Stefanie Peßenteiner
  • 1Stockholm University, Department of Meteorology and Bolin Centre for Climate Research, Stockholm, Sweden
  • 2University of Graz, Department of Geography and Regional Science, Graz, Austria

Abstract. Creating spatially coherent rainfall patterns with high temporal resolution from data with lower temporal resolution is necessary in many geoscientific applications. From a statistical perspective, this presents a high- dimensional, highly under-determined problem. Recent advances in machine learning provide methods for learning such probability distributions. We test the usage of Generative Adversarial Networks (GANs) for estimating the full probability distribution of spatial rainfall patterns with high temporal resolution, conditioned on a field of lower temporal resolution. The GAN is trained on rainfall radar data with hourly resolution. Given a new field of daily precipitation sums, it can sample scenarios of spatiotemporal patterns with sub-daily resolution. While the generated patterns do not perfectly reproduce the statistics of observations, they are visually hardly distinguishable from real patterns. Limitations that we found are that providing additional input (such as geographical information) to the GAN surprisingly lead to worse results, showing that it is not trivial to increase the amount of used input information. Additionally, while in principle the GAN should learn the probability distribution in itself, we still needed expert judgment to determine at which point the training should stop, because longer training leads to worse results.

Sebastian Scher and Stefanie Peßenteiner

 
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for authors/editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Sebastian Scher and Stefanie Peßenteiner

Sebastian Scher and Stefanie Peßenteiner

Viewed

Total article views: 455 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
343 107 5 455 11 6
  • HTML: 343
  • PDF: 107
  • XML: 5
  • Total: 455
  • BibTeX: 11
  • EndNote: 6
Views and downloads (calculated since 30 Sep 2020)
Cumulative views and downloads (calculated since 30 Sep 2020)

Viewed (geographical distribution)

Total article views: 396 (including HTML, PDF, and XML) Thereof 394 with geography defined and 2 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 11 Apr 2021
Download
Short summary
In hydrology, it is often necessary to infer from a daily sum of precipitation a possible distribution over the day – for example how much it rained in each hour. In principle, for a given daily sum, there are endless possibilities. However, some are more likely than others. We show that a method from artificial intelligence called GAN can learn what a typical distribution over the day looks like.