Articles | Volume 22, issue 2
Research article
25 Jan 2022
Research article |  | 25 Jan 2022

New particle formation event detection with Mask R-CNN

Peifeng Su, Jorma Joutsensaari, Lubna Dada, Martha Arbayani Zaidan, Tuomo Nieminen, Xinyang Li, Yusheng Wu, Stefano Decesari, Sasu Tarkoma, Tuukka Petäjä, Markku Kulmala, and Petri Pellikka


Total article views: 2,526 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,862 630 34 2,526 18 29
  • HTML: 1,862
  • PDF: 630
  • XML: 34
  • Total: 2,526
  • BibTeX: 18
  • EndNote: 29
Views and downloads (calculated since 13 Sep 2021)
Cumulative views and downloads (calculated since 13 Sep 2021)

Viewed (geographical distribution)

Total article views: 2,526 (including HTML, PDF, and XML) Thereof 2,925 with geography defined and -399 with unknown origin.
Country # Views %
  • 1


Latest update: 26 Sep 2023
Short summary
We regarded the banana shapes in the surface plots as a special kind of object (similar to cats) and applied an instance segmentation technique to automatically identify the new particle formation (NPF) events (especially the strongest ones), in addition to their growth rates, start times, and end times. The automatic method generalized well on datasets collected in different sites, which is useful for long-term data series analysis and obtaining statistical properties of NPF events.
Final-revised paper