Articles | Volume 19, issue 21
https://doi.org/10.5194/amt-19-7231-2026
https://doi.org/10.5194/amt-19-7231-2026
Research article
 | 
12 Nov 2026
Research article |  | 12 Nov 2026

Two decades of kilometer-scale daily PM2.5 from satellite observations and machine learning reveal geographically diverging exposure in Ghana

Abhishek Anand, Joe A. Amooli, Selina Amoah, Esi Nerquaye Tetteh, Nana Ama Browne Klutse, Clement Mensah Ackaah, Benjamin Essien, Kingsley Mawuli Amegah, and Daniel M. Westervelt

Viewed

Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.

Total article views: 279 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
275 0 4 279 0 0
  • HTML: 275
  • PDF: 0
  • XML: 4
  • Total: 279
  • BibTeX: 0
  • EndNote: 0
Views and downloads (calculated since 15 Jul 2026)
Cumulative views and downloads (calculated since 15 Jul 2026)

Viewed (geographical distribution)

Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.

Total article views: 279 (including HTML, PDF, and XML) Thereof 219 with geography defined and 60 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 12 Nov 2026
Download
Short summary
Air pollution remains poorly characterized across sub-Saharan Africa due to sparse monitoring infrastructure. We developed a multi-model machine learning framework to generate a 21-year, high-resolution PM2.5 dataset for Ghana, revealing pronounced spatial and seasonal variability, persistent geographic exposure disparities, and contrasting long-term trends. These findings provide new evidence to support air-quality management, health assessments, and environmental policy in data-sparse regions.
Share
Altmetrics
Final-revised paper
Preprint