Classification of iron oxide aerosols by a single particle soot photometer using supervised machine learning

Lamb, Kara D.

doi:https://doi.org/10.5194/amt-12-3885-2019

Articles | Volume 12, issue 7

https://doi.org/10.5194/amt-12-3885-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-12-3885-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 12, issue 7

Research article

|

15 Jul 2019

Research article |

| 15 Jul 2019

Classification of iron oxide aerosols by a single particle soot photometer using supervised machine learning

Kara D. Lamb

Download

Final revised paper (published on 15 Jul 2019)
Supplement to the final revised paper
Preprint (discussion started on 22 Mar 2019)

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC1: 'Referee comment to "Classification of iron oxide aerosols by a single particle soot photometer using supervised machine learning" by Lamb', Anonymous Referee #1, 20 Apr 2019
- AC1: 'Reply to "'Referee comment to "Classification of iron oxide aerosols by a single particle soot photometer using supervised machine learning" by Lamb'"', Kara Lamb, 20 Jun 2019
RC2: 'Review', Anonymous Referee #2, 29 Apr 2019
- AC2: 'Reply to "Review"', Kara Lamb, 20 Jun 2019

Peer-review completion

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

AR by Kara Lamb on behalf of the Authors (20 Jun 2019) Author's response Manuscript

ED: Publish as is (21 Jun 2019) by Mingjin Tang

Short summary

Recent atmospheric observations have indicated emissions of iron-oxide-containing aerosols from anthropogenic sources could be 8x higher than previous estimates, leading models to underestimate their climate impact. Previous studies have shown the single particle soot photometer (SP2) can quantify the atmospheric abundance of these aerosols. Here, I explore a machine learning approach to improve SP2 detection, significantly reducing misclassifications of other aerosols as iron oxide aerosols.