Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 19, issue 12
Articles | Volume 19, issue 12
https://doi.org/10.5194/amt-19-4049-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-19-4049-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 12
Research article
 | 
24 Jun 2026
Research article |  | 24 Jun 2026

Towards automated near-real-time global monitoring of atmospheric SO2 plumes from satellite data using U-Net segmentation

Douglas P. Finch and Paul I. Palmer

Viewed

Total article views: 2,796 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,599 1,011 186 2,796 118 93
  • HTML: 1,599
  • PDF: 1,011
  • XML: 186
  • Total: 2,796
  • BibTeX: 118
  • EndNote: 93
Views and downloads (calculated since 15 Jan 2026)
Cumulative views and downloads (calculated since 15 Jan 2026)

Viewed (geographical distribution)

Total article views: 2,796 (including HTML, PDF, and XML) Thereof 2,761 with geography defined and 35 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 24 Jun 2026
Download
Short summary
We have developed a machine learning tool to find emission plumes of sulphur dioxide (SO2) observed in satellite data. SO2 is an atmospheric pollutant from fuel combustion, metal smelting, and volcanic degassing, impacting health, acid deposition, and climate forcing. Over 6 years we find over 50 000 plumes, most of which are clustered around known sources (e.g. volcanoes or industrial hotspots). We show how this tool can be used to rapidly detect emissions across the globe.
Read more
Share