Biogeosciences
Biogeosciences
BG
Articles | Volume 23, issue 1
Articles | Volume 23, issue 1
https://doi.org/10.5194/bg-23-233-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/bg-23-233-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 23, issue 1
Research article
 | 
09 Jan 2026
Research article |  | 09 Jan 2026

High-resolution remote sensing and machine-learning-based upscaling of methane fluxes: a case study in the Western Canadian tundra

Kseniia Ivanova, Anna-Maria Virkkala, Victor Brovkin, Tobias Stacke, Barbara Widhalm, Annett Bartsch, Carolina Voigt, Oliver Sonnentag, and Mathias Göckede

Viewed

Total article views: 8,432 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
7,068 1,142 222 8,432 148 288 244
  • HTML: 7,068
  • PDF: 1,142
  • XML: 222
  • Total: 8,432
  • Supplement: 148
  • BibTeX: 288
  • EndNote: 244
Views and downloads (calculated since 28 Aug 2025)
Cumulative views and downloads (calculated since 28 Aug 2025)

Viewed (geographical distribution)

Total article views: 8,432 (including HTML, PDF, and XML) Thereof 8,414 with geography defined and 18 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved (final revised paper)

Latest update: 05 Sep 2026
Download
Short summary
We measured over 13,000 methane fluxes at a site in the Canadian Arctic and linked them with drone and free satellite images. We tested four machine-learning methods and two map scales. Metre-scale maps captured small wet and dry features that strongly affect methane release, while coarser maps blurred them. Different models shifted the monthly methane estimate. This helps choose the right data and tools to map methane, design monitoring networks, and check climate models.
Read more
Share
Altmetrics
Final-revised paper
Preprint