Articles | Volume 17, issue 1
https://doi.org/10.5194/amt-17-299-2024
https://doi.org/10.5194/amt-17-299-2024
Research article
 | 
16 Jan 2024
Research article |  | 16 Jan 2024

Machine learning approaches for automatic classification of single-particle mass spectrometry data

Guanzhong Wang, Heinrich Ruser, Julian Schade, Johannes Passig, Thomas Adam, Günther Dollinger, and Ralf Zimmermann

Viewed

Total article views: 1,215 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
852 312 51 1,215 40 38
  • HTML: 852
  • PDF: 312
  • XML: 51
  • Total: 1,215
  • BibTeX: 40
  • EndNote: 38
Views and downloads (calculated since 09 May 2023)
Cumulative views and downloads (calculated since 09 May 2023)

Viewed (geographical distribution)

Total article views: 1,215 (including HTML, PDF, and XML) Thereof 1,182 with geography defined and 33 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 12 Jul 2024
Download
Short summary
This research aims to develop a novel warning system for the real-time monitoring of pollutants in the atmosphere. The system is capable of sampling and investigating airborne aerosol particles on-site, utilizing artificial intelligence to learn their chemical signatures and to classify them in real time. We applied single-particle mass spectrometry for analyzing the chemical composition of aerosol particles and suggest several supervised algorithms for highly reliable automatic classification.