Articles | Volume 15, issue 19
https://doi.org/10.5194/gmd-15-7353-2022
https://doi.org/10.5194/gmd-15-7353-2022
Development and technical paper
 | 
05 Oct 2022
Development and technical paper |  | 05 Oct 2022

Repeatable high-resolution statistical downscaling through deep learning

Dánnell Quesada-Chacón, Klemens Barfus, and Christian Bernhofer

Viewed

Total article views: 3,031 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,127 834 70 3,031 58 60
  • HTML: 2,127
  • PDF: 834
  • XML: 70
  • Total: 3,031
  • BibTeX: 58
  • EndNote: 60
Views and downloads (calculated since 26 Apr 2022)
Cumulative views and downloads (calculated since 26 Apr 2022)

Viewed (geographical distribution)

Total article views: 3,031 (including HTML, PDF, and XML) Thereof 2,913 with geography defined and 118 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 20 Nov 2024
Download
Short summary
We improved the performance of past perfect prognosis statistical downscaling methods while achieving full model repeatability with GPU-calculated deep learning models using the TensorFlow, climate4R, and VALUE frameworks. We employed the ERA5 reanalysis as predictors and ReKIS (eastern Ore Mountains, Germany, 1 km resolution) as precipitation predictand, while incorporating modern deep learning architectures. The achieved repeatability is key to accomplish further milestones with deep learning.