Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 19, issue 19
Articles | Volume 19, issue 19
https://doi.org/10.5194/amt-19-6341-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-19-6341-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 19
Research article
 | 
06 Oct 2026
Research article |  | 06 Oct 2026

Research on deep learning-based missing echo restoration method for weather radar mosaic data

Husong Guo, Muyun Du, Xiangyu Fan, Cuihong Wu, Anwei Lai, and Hedi Ma

Viewed

Total article views: 608 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
415 156 37 608 35 36
  • HTML: 415
  • PDF: 156
  • XML: 37
  • Total: 608
  • BibTeX: 35
  • EndNote: 36
Views and downloads (calculated since 11 May 2026)
Cumulative views and downloads (calculated since 11 May 2026)

Viewed (geographical distribution)

Total article views: 608 (including HTML, PDF, and XML) Thereof 571 with geography defined and 37 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Oct 2026
Download
Short summary
Radar mosaic data is crucial for accurate and timely disaster weather warnings. However, missing regional data – caused by hardware failures or delayed file transfers, severely limits its quantitative use. Existing methods either struggle with complex and diverse missing patterns; or rely on known missing masks. To address this, We propose a deep learning–based radar echo restoration method that requires no explicit missing-data prior and delivers reliable, real-time performance.
Read more
Share