Development of a daily PM<sub>10</sub> and PM<sub>2.5</sub> prediction system using a deep long short-term memory neural network model

Kim, Hyun S.; Park, Inyoung; Song, Chul H.; Lee, Kyunghwa; Yun, Jae W.; Kim, Hong K.; Jeon, Moongu; Lee, Jiwon; Han, Kyung M.

doi:https://doi.org/10.5194/acp-19-12935-2019

Articles | Volume 19, issue 20

https://doi.org/10.5194/acp-19-12935-2019

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

https://doi.org/10.5194/acp-19-12935-2019

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

Articles | Volume 19, issue 20

Research article

|

18 Oct 2019

Research article |

| 18 Oct 2019

Development of a daily PM₁₀ and PM_2.5 prediction system using a deep long short-term memory neural network model

Hyun S. Kim, Inyoung Park, Chul H. Song, Kyunghwa Lee, Jae W. Yun, Hong K. Kim, Moongu Jeon, Jiwon Lee, and Kyung M. Han

Download

Final revised paper (published on 18 Oct 2019)
Supplement to the final revised paper
Preprint (discussion started on 29 Mar 2019)
Supplement to the preprint

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC1: 'Referee Comment for Kim et al.', Anonymous Referee #1, 22 Apr 2019
- RC2: 'Comments on the manuscript', Anonymous Referee #2, 10 Jun 2019
- AC1: 'Author’s comments to anonymous referee #1', Hyun Soo Kim, 07 Aug 2019
- AC2: 'Author’s comments to anonymous referee #2', Hyun Soo Kim, 07 Aug 2019

Peer-review completion

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

AR by Hyun Soo Kim on behalf of the Authors (07 Aug 2019) Author's response Manuscript

ED: Publish subject to minor revisions (review by editor) (27 Aug 2019) by David Topping

AR by Hyun Soo Kim on behalf of the Authors (28 Aug 2019) Author's response Manuscript

ED: Publish as is (16 Sep 2019) by David Topping

AR by Hyun Soo Kim on behalf of the Authors (20 Sep 2019) Manuscript

Download

Article (10962 KB)
Full-text XML

Short summary

In this study, a deep recurrent neural network system based on a long short-term memory (LSTM) model was developed for daily PM₁₀ and PM_2.5 predictions in South Korea. In general, the accuracies of the LSTM-based predictions were superior to the 3-D CTM-based predictions. Based on this, we concluded that the LSTM-based system could be applied to daily operational PM forecasts in South Korea. We expect that similar AI systems can be applied to the predictions of other atmospheric pollutants.

Development of a daily PM10 and PM2.5 prediction system using a deep long short-term memory neural network model

Download

Interactive discussion

Peer-review completion

Development of a daily PM₁₀ and PM_2.5 prediction system using a deep long short-term memory neural network model