Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 19, issue 6
Articles | Volume 19, issue 6
https://doi.org/10.5194/amt-19-2225-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-19-2225-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 6
Research article
 | 
01 Apr 2026
Research article |  | 01 Apr 2026

A Physics-Constrained Deep-Learning Framework based on Long-Term Remote-Sensing Data for Retrieving Vertical Distribution of PM2.5 Chemical Components

Hongyi Li, Ting Yang, Yele Sun, and Zifa Wang

Viewed

Total article views: 5,023 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
4,130 787 106 5,023 28 120 122
  • HTML: 4,130
  • PDF: 787
  • XML: 106
  • Total: 5,023
  • Supplement: 28
  • BibTeX: 120
  • EndNote: 122
Views and downloads (calculated since 15 Sep 2025)
Cumulative views and downloads (calculated since 15 Sep 2025)

Viewed (geographical distribution)

Total article views: 5,023 (including HTML, PDF, and XML) Thereof 5,023 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 13 May 2026
Download
Short summary
We develop a physics-constrained deep-learning framework to retrieve vertical profiles of particulate matter <2.5 µm chemical components from lidar measurements. Comparisons with surface, tower, and aircraft measurements validate the performance of the framework. A six-year vertical profile dataset generated for Beijing reveals that organic matter and nitrate are dominant chemical components. This work offers a new perspective on the lidar inversion of chemical component profiles.
Read more
Share