Identification of new particle formation events with deep learning

Joutsensaari, Jorma; Ozon, Matthew; Nieminen, Tuomo; Mikkonen, Santtu; Lähivaara, Timo; Decesari, Stefano; Facchini, M. Cristina; Laaksonen, Ari; Lehtinen, Kari E. J.

doi:https://doi.org/10.5194/acp-18-9597-2018

Articles | Volume 18, issue 13

https://doi.org/10.5194/acp-18-9597-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/acp-18-9597-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 13

Research article

|

09 Jul 2018

Research article |

| 09 Jul 2018

Identification of new particle formation events with deep learning

Jorma Joutsensaari, Matthew Ozon, Tuomo Nieminen, Santtu Mikkonen, Timo Lähivaara, Stefano Decesari, M. Cristina Facchini, Ari Laaksonen, and Kari E. J. Lehtinen

Download

Final revised paper (published on 09 Jul 2018)
Preprint (discussion started on 29 Jan 2018)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'The review of “Identification of new particle formation events with deep learning” by Joutsensaari et al., 2018', Anonymous Referee #1, 19 Feb 2018
- AC1: 'Response to the Referee #1 comments', Jorma Joutsensaari, 18 Jun 2018
RC2: '2nd review of Joutsensaari et al., 2018', Anonymous Referee #3, 07 May 2018
- AC2: 'Response to the Referee #3 comments', Jorma Joutsensaari, 18 Jun 2018

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Jorma Joutsensaari on behalf of the Authors (18 Jun 2018) Author's response Manuscript

ED: Publish as is (26 Jun 2018) by Fangqun Yu

AR by Jorma Joutsensaari on behalf of the Authors (26 Jun 2018)

Short summary

New particle formation (NPF) in the atmosphere is globally an important source of aerosol particles. NPF events are typically identified and analyzed manually by researchers from particle size distribution data day by day, which is time consuming and might be inconsistent. We have developed an automatic analysis method based on deep learning for NPF event identification. The developed method can be easily utilized to analyze any long-term datasets more accurately and consistently.