Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods

Si, Minxing; Xiong, Ying; Du, Shan; Du, Ke

doi:https://doi.org/10.5194/amt-13-1693-2020

Articles | Volume 13, issue 4

https://doi.org/10.5194/amt-13-1693-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-13-1693-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 13, issue 4

Research article

|

07 Apr 2020

Research article |

| 07 Apr 2020

Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods

Minxing Si, Ying Xiong, Shan Du, and Ke Du

Download

Final revised paper (published on 07 Apr 2020)
Preprint (discussion started on 20 Dec 2019)

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC1: 'Comments to amt-2019-393', Anonymous Referee #3, 13 Jan 2020
- AC1: 'Responses to Anonymous Referee No. 3 Comments from the Public Discussion', Ke Du, 29 Feb 2020
RC2: 'Comment', Anonymous Referee #4, 24 Feb 2020
- AC2: 'Responses to Anonymous Referee No. 4 Comments from the Public Discussion', Ke Du, 29 Feb 2020

Peer-review completion

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

AR by Ke Du on behalf of the Authors (29 Feb 2020) Author's response

ED: Publish as is (09 Mar 2020) by Keding Lu

AR by Ke Du on behalf of the Authors (11 Mar 2020)

Short summary

The study evaluated the performance of a low-cost PM sensor in ambient conditions and calibrated its readings using simple linear regression (SLR), multiple linear regression (MLR), and two more powerful machine-learning algorithms with random search techniques for the best model architectures. The two machine-learning algorithms are XGBoost and a feedforward neural network (NN).