Articles | Volume 13, issue 6
https://doi.org/10.5194/gmd-13-2631-2020
https://doi.org/10.5194/gmd-13-2631-2020
Model description paper
 | Highlight paper
 | 
11 Jun 2020
Model description paper | Highlight paper |  | 11 Jun 2020

RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting

Georgy Ayzel, Tobias Scheffer, and Maik Heistermann

Viewed

Total article views: 11,649 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
8,153 3,391 105 11,649 435 158 78
  • HTML: 8,153
  • PDF: 3,391
  • XML: 105
  • Total: 11,649
  • Supplement: 435
  • BibTeX: 158
  • EndNote: 78
Views and downloads (calculated since 04 Mar 2020)
Cumulative views and downloads (calculated since 04 Mar 2020)

Viewed (geographical distribution)

Total article views: 11,649 (including HTML, PDF, and XML) Thereof 10,234 with geography defined and 1,415 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 15 Apr 2024
Download
Short summary
In this study, we present RainNet, a deep convolutional neural network for radar-based precipitation nowcasting, which was trained to predict continuous precipitation intensities at a lead time of 5 min. RainNet significantly outperformed the benchmark models at all lead times up to 60 min. Yet, an undesirable property of RainNet predictions is the level of spatial smoothing. Obviously, RainNet learned an optimal level of smoothing to produce a nowcast at 5 min lead time.