Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 19, issue 20
Articles | Volume 19, issue 20
https://doi.org/10.5194/amt-19-6781-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-19-6781-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 20
Research article
 | 
28 Oct 2026
Research article |  | 28 Oct 2026

Enhancing weather radar data by removing non-meteorological echoes, using neural networks trained on synthetic weather data

Richard Bölz, Tom Kirstein, Lukas Fuchs, Lukas Josipović, Annette Böhm, Ulrich Blahak, and Volker Schmidt

Viewed

Total article views: 1,461 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
851 530 80 1,461 91 95
  • HTML: 851
  • PDF: 530
  • XML: 80
  • Total: 1,461
  • BibTeX: 91
  • EndNote: 95
Views and downloads (calculated since 18 Mar 2026)
Cumulative views and downloads (calculated since 18 Mar 2026)

Viewed (geographical distribution)

Total article views: 1,461 (including HTML, PDF, and XML) Thereof 1,443 with geography defined and 18 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 28 Oct 2026
Download
Short summary
We introduce an AI-based approach to identify unwanted signals in weather radar images using a neural network. To address the challenge of acquiring sufficient amounts of labeled radar images, the network is trained on synthetically generated radar images. By evaluating the segmentation performance of the trained network on experimentally measured radar images with expert-labeled ground truth, we demonstrate that it outperforms a state-of-the-art method currently used at Deutscher Wetterdienst.
Read more
Share
Altmetrics
Final-revised paper
Preprint