Articles | Volume 19, issue 20
https://doi.org/10.5194/acp-19-12935-2019
https://doi.org/10.5194/acp-19-12935-2019
Research article
 | 
18 Oct 2019
Research article |  | 18 Oct 2019

Development of a daily PM10 and PM2.5 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

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

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
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 PM2.5 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.
Altmetrics
Final-revised paper
Preprint