Articles | Volume 22, issue 8
Research article
20 Apr 2022
Research article |  | 20 Apr 2022

Understanding aerosol microphysical properties from 10 years of data collected at Cabo Verde based on an unsupervised machine learning classification

Xianda Gong, Heike Wex, Thomas Müller, Silvia Henning, Jens Voigtländer, Alfred Wiedensohler, and Frank Stratmann


Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on acp-2021-743', Anonymous Referee #1, 01 Nov 2021
  • RC2: 'Comment on acp-2021-743', Anonymous Referee #2, 07 Jan 2022

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Xianda Gong on behalf of the Authors (19 Mar 2022)  Author's response    Author's tracked changes    Manuscript
ED: Publish as is (23 Mar 2022) by Manuela van Pinxteren
Short summary
We conducted 10 yr measurements to characterize the atmospheric aerosol at Cabo Verde. An unsupervised machine learning algorithm, K-means, was implemented to study the aerosol types. Cloud condensation nuclei number concentrations during dust periods were 2.5 times higher than marine periods. The long-term data sets, together with the aerosol classification, can be used as a basis to improve understanding of annual cycles of aerosol, and aerosol-cloud interactions in the North Atlantic.
Final-revised paper