Natural Hazards and Earth System Sciences
Natural Hazards and Earth System Sciences
NHESS
Articles | Volume 25, issue 1
Articles | Volume 25, issue 1
https://doi.org/10.5194/nhess-25-41-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/nhess-25-41-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 25, issue 1
Brief communication
 | 
03 Jan 2025
Brief communication |  | 03 Jan 2025

Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements

Georgy Ayzel and Maik Heistermann

Viewed

Total article views: 4,136 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
2,826 973 337 4,136 107 166 235
  • HTML: 2,826
  • PDF: 973
  • XML: 337
  • Total: 4,136
  • Supplement: 107
  • BibTeX: 166
  • EndNote: 235
Views and downloads (calculated since 29 Jul 2024)
Cumulative views and downloads (calculated since 29 Jul 2024)

Viewed (geographical distribution)

Total article views: 4,136 (including HTML, PDF, and XML) Thereof 4,097 with geography defined and 39 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved (final revised paper)

Latest update: 25 Jun 2026
Download
Short summary
Forecasting rainfall over the next hour is an essential feature of early warning systems. Deep learning (DL) has emerged as a powerful alternative to conventional nowcasting technologies, but it still struggles to adequately predict impact-relevant heavy rainfall. We think that DL could do much better if the training tasks were defined more specifically and that such specification presents an opportunity to better align the output of nowcasting models with actual user requirements.
Read more
Share
Altmetrics
Final-revised paper
Preprint