Preprints
https://doi.org/10.5194/acp-2021-771
https://doi.org/10.5194/acp-2021-771

  13 Sep 2021

13 Sep 2021

Review status: this preprint is currently under review for the journal ACP.

New Particle Formation Events Detection with Deep Learning

Peifeng Su1,2, Jorma Joutsensaari3, Lubna Dada4,5, Martha Arbayani Zaidan2,6, Tuomo Nieminen2,7, Xinyang Li2, Yusheng Wu2, Stefano Decesari8, Sasu Tarkoma9, Tuukka Petäjä2,6, Markku Kulmala2,6, and Petri Pellikka1,2 Peifeng Su et al.
  • 1Department of Geosciences and Geography, University of Helsinki, FI-00014 Helsinki, Finland
  • 2Institute for Atmospheric and Earth System Research (INAR/Physics), Faculty of Science, University of Helsinki, FI-00014 Helsinki, Finland
  • 3Department of Applied Physics, University of Eastern Finland, P.O. Box 1627, 70211 Kuopio, Finland
  • 4Extreme Environments Research Laboratory, Ecole Polytechnique Fédérale de Lausanne (EPFL) Valais, Sion, 1951, Switzerland
  • 5Laboratory of Atmospheric Chemistry, Paul Scherrer Institute, Villigen, 5232, Switzerland
  • 6Joint International Research Laboratory of Atmospheric and Earth System Sciences, School of Atmospheric Sciences, Nanjing University, Nanjing 210023, China
  • 7Institute for Atmospheric and Earth System Research (INAR/Forest Sciences), Faculty of Agriculture and Forestry, University of Helsinki, FI-00014 Helsinki, Finland
  • 8Italian National Research Council Institute of Atmospheric Sciences and Climate (CNR-ISAC), Bologna 40129, Italy
  • 9Department of Computer Science, Faculty of Science, University of Helsinki, FI-00014 Helsinki, Finland

Abstract. Atmospheric new particle formation (NPF) is an important source of climate-relevant aerosol particles which has been observed at many locations globally. To study this phenomenon, the first step is to identify whether an NPF event occurs or not on a given day. In practice, NPF event identification is performed visually by classifying the NPF event or non-event days from the particle number size distribution surface plots. Unfortunately, this day-by-day visual classification is time-consuming, labor-intensive, and the identification process renders subjective results. To detect NPF events automatically, we regard the visual signature (banana shape) which has been observed all over the world in NPF surface plots as a special kind of object, and a deep learning model called Mask R-CNN is applied to localize the spatial layouts of NPF events in their surface plots. Utilizing only 358 human-annotated masks on data from the Station for Measuring Ecosystem and Atmospheric Relations (SMEAR) II station (Hyytiälä, Finland), the Mask R-CNN model was successfully generalized for three SMEAR stations in Finland and the San Pietro Capofiume (SPC) station in Italy. In addition to the detection of NPF events (especially the strongest events), the presented method can determine the growth rates, start times, and end times for NPF events automatically. The automatically determined growth rates agree with the growth rates determined by the maximum concentration and mode fitting methods. The statistical results valid the potential of applying the proposed method on different sites, which will improve the automatic level for NPF events detection and analysis. Furthermore, the proposed automatic NPF event analysis method provides more consistent results compared with human-made analysis, especially when long-term data series are analyzed and statistically comparisons between different sites are needed for event characteristics such as the start and end times, thereby saving time and effort of scientists studying NPF events.

Peifeng Su et al.

Status: open (until 25 Oct 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Peifeng Su et al.

Peifeng Su et al.

Viewed

Total article views: 157 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
102 51 4 157 2 2
  • HTML: 102
  • PDF: 51
  • XML: 4
  • Total: 157
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 13 Sep 2021)
Cumulative views and downloads (calculated since 13 Sep 2021)

Viewed (geographical distribution)

Total article views: 272 (including HTML, PDF, and XML) Thereof 272 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 19 Sep 2021
Download
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.
Altmetrics