The Cryosphere
The Cryosphere
TC
Articles | Volume 20, issue 4
Articles | Volume 20, issue 4
https://doi.org/10.5194/tc-20-2295-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-20-2295-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 20, issue 4
Research article
 | 
21 Apr 2026
Research article |  | 21 Apr 2026

Identification and correction of snow depth bias in ERA5 datasets over Central Europe using machine learning

Gabiel Stachura and Zbigniew Ustrnul

Viewed

Total article views: 2,167 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,312 736 119 2,167 87 89
  • HTML: 1,312
  • PDF: 736
  • XML: 119
  • Total: 2,167
  • BibTeX: 87
  • EndNote: 89
Views and downloads (calculated since 24 Nov 2025)
Cumulative views and downloads (calculated since 24 Nov 2025)

Viewed (geographical distribution)

Total article views: 2,167 (including HTML, PDF, and XML) Thereof 2,127 with geography defined and 40 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved (final revised paper)

Latest update: 19 Aug 2026
Download
Short summary
Reanalyses still struggle to accurately estimate snow depth, mostly because their horizontal resolution is beyond the spatial scale of snow variability. A comparison of two Copernicus reanalyses ERA5 and ERA5-Land reveals systematic errors and highlights the importance of data assimilation. A Random Forests model is able to reduce the systematic error by around a half. Spatial downscaling in complex terrain reflects mainly elevation dependence but also shadowing effect of surrounding topography.
Read more
Share