Articles | Volume 13, issue 5
https://doi.org/10.5194/amt-13-2481-2020
https://doi.org/10.5194/amt-13-2481-2020
Research article
 | 
19 May 2020
Research article |  | 19 May 2020

Learning about the vertical structure of radar reflectivity using hydrometeor classes and neural networks in the Swiss Alps

Floor van den Heuvel, Loris Foresti, Marco Gabella, Urs Germann, and Alexis Berne

Viewed

Total article views: 3,053 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,392 605 56 3,053 46 45
  • HTML: 2,392
  • PDF: 605
  • XML: 56
  • Total: 3,053
  • BibTeX: 46
  • EndNote: 45
Views and downloads (calculated since 23 Oct 2019)
Cumulative views and downloads (calculated since 23 Oct 2019)

Viewed (geographical distribution)

Total article views: 3,053 (including HTML, PDF, and XML) Thereof 2,531 with geography defined and 522 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 16 Apr 2024
Download
Short summary
In areas with reduced visibility at the ground level, radar precipitation measurements higher up in the atmosphere need to be extrapolated to the ground and be corrected for the vertical change (i.e. growth and transformation) of precipitation. This study proposes a method based on hydrometeor proportions and machine learning (ML) to apply these corrections at smaller spatiotemporal scales. In comparison with existing techniques, the ML methods can make predictions from higher altitudes.