Articles | Volume 13, issue 10
Atmos. Meas. Tech., 13, 5537–5550, 2020
https://doi.org/10.5194/amt-13-5537-2020
Atmos. Meas. Tech., 13, 5537–5550, 2020
https://doi.org/10.5194/amt-13-5537-2020

Research article 16 Oct 2020

Research article | 16 Oct 2020

A feasibility study to use machine learning as an inversion algorithm for aerosol profile and property retrieval from multi-axis differential absorption spectroscopy measurements

Yun Dong et al.

Viewed

Total article views: 1,756 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,485 253 18 1,756 19 26 20
  • HTML: 1,485
  • PDF: 253
  • XML: 18
  • Total: 1,756
  • Supplement: 19
  • BibTeX: 26
  • EndNote: 20
Views and downloads (calculated since 21 Oct 2019)
Cumulative views and downloads (calculated since 21 Oct 2019)

Viewed (geographical distribution)

Total article views: 1,434 (including HTML, PDF, and XML) Thereof 1,431 with geography defined and 3 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 25 Feb 2021
Download
Short summary
This paper is about a feasibility study of applying a machine learning technique to derive aerosol properties from a single MAX-DOAS sky scan, which detects sky-scattered UV–visible photons at multiple elevation angles. Evaluation of retrieved aerosol properties shows good performance of the ML algorithm, suggesting several advantages of a ML-based inversion algorithm such as fast data inversion, simple implementation and the ability to extract information not available using other algorithms.