Atmospheric Chemistry and Physics
Atmospheric Chemistry and Physics
ACP
Articles | Volume 24, issue 5
Articles | Volume 24, issue 5
https://doi.org/10.5194/acp-24-3163-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/acp-24-3163-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 24, issue 5
Research article
 | 
13 Mar 2024
Research article |  | 13 Mar 2024

A machine learning approach to downscale EMEP4UK: analysis of UK ozone variability and trends

Lily Gouldsbrough, Ryan Hossaini, Emma Eastoe, Paul J. Young, and Massimo Vieno

Viewed

Total article views: 4,644 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,937 1,523 184 4,644 176 259
  • HTML: 2,937
  • PDF: 1,523
  • XML: 184
  • Total: 4,644
  • BibTeX: 176
  • EndNote: 259
Views and downloads (calculated since 16 May 2023)
Cumulative views and downloads (calculated since 16 May 2023)

Viewed (geographical distribution)

Total article views: 4,644 (including HTML, PDF, and XML) Thereof 4,644 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 20 May 2026
Download
Short summary
High-resolution spatial fields of surface ozone are used to understand spikes in ozone concentration and predict their impact on public health. Such fields are routinely output from complex mathematical models for atmospheric conditions. These outputs are on a coarse spatial resolution and the highest concentrations tend to be biased. Using a novel data-driven machine learning methodology, we show how such output can be corrected to produce fields with both lower bias and higher resolution.
Read more
Share
Altmetrics
Final-revised paper
Preprint