Preprints
https://doi.org/10.5194/gmd-2021-356
https://doi.org/10.5194/gmd-2021-356

Submitted as: development and technical paper 15 Nov 2021

Submitted as: development and technical paper | 15 Nov 2021

Review status: this preprint is currently under review for the journal GMD.

Development of a deep neural network for predicting 6-hour average PM2.5 concentrations up to two subsequent days using various training data

Jeong-Beom Lee1, Jae-Bum Lee1, Youn-Seo Koo2, Hee-Yong Kwon3, Min-Hyeok Choi1, Hyun-Ju Park1, and Dae-Gyun Lee1 Jeong-Beom Lee et al.
  • 1Air Quality Forecasting Center, National Institute of Environmental Research (NIER), Incheon, 22689, South Korea
  • 2Department of Environmental and Energy Engineering, Anyang University, Gyeonggi, 14028, South Korea
  • 3Department of Computer Engineering, Anyang University, Gyeonggi, 14028, South Korea

Abstract. This study aims to develop a deep neural network (DNN) model as an artificial neural network (ANN) for the prediction of 6-hour average fine particulate matter (PM2.5) concentrations for a three-day period—the day of prediction (D+0), one day after prediction (D+1) and two days after prediction (D+2)—using observation data and forecast data obtained via numerical models. The performance of the DNN model was comparatively evaluated against that of the currently operational Community Multiscale Air Quality (CMAQ) modelling system for air quality forecasting in South Korea. In addition, the effect on predictive performance of the DNN model on using different training data was analyzed. For the D+0 forecast, the DNN model performance was superior to that of the CMAQ model, and there was no significant dependence on the training data. For the D+1 and D+2 forecasts, the DNN model that used the observation and forecast data (DNN-ALL) outperformed the CMAQ model. The root-mean-squared error (RMSE) of DNN-ALL was lower than that of the CMAQ model by 2.2 μgm−3, and 3.0 μgm−3 for the D+1 and D+2 forecasts, respectively, because the overprediction of higher concentrations was curtailed. An IOA increase of 0.46 for D+1 prediction and 0.59 for the D+2 prediction was observed in case of the DNN-ALL model compared to the IOA of the DNN model that used only observation data (DNN-OBS). In additionally, An RMSE decrease of 7.2 μgm−3 for the D+1 prediction and 6.3 μgm−3 for the D+2 prediction was observed in case of the DNN-ALL model, compared to the RMSE of DNN-OBS, indicating that the inclusion of forecast data in the training data greatly affected the DNN model performance. Considering the prediction of the 6-hour average PM2.5 concentration, the 8.8 μgm−3 RMSE of the DNN-ALL model was 2.7 μgm−3 lower than that of the CMAQ model, indicating the superior prediction performance of the former. These results suggest that the DNN model could be utilized as a better-performing air quality forecasting model than the CMAQ, and that observation data plays an important role in determining the prediction performance of the DNN model for D+0 forecasting, while prediction data does the same for D+1 and D+2 forecasting. The use of the proposed DNN model as a forecasting model may result in a reduction in the economic losses caused by pollution-mitigation policies and aid better protection of public health.

Jeong-Beom Lee et al.

Status: open (until 10 Jan 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Jeong-Beom Lee et al.

Jeong-Beom Lee et al.

Viewed

Total article views: 217 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
180 31 6 217 3 4
  • HTML: 180
  • PDF: 31
  • XML: 6
  • Total: 217
  • BibTeX: 3
  • EndNote: 4
Views and downloads (calculated since 15 Nov 2021)
Cumulative views and downloads (calculated since 15 Nov 2021)

Viewed (geographical distribution)

Total article views: 217 (including HTML, PDF, and XML) Thereof 217 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 29 Nov 2021
Download
Short summary
Korea's fine dust was forecasted using a physical-based numerical model with fundamental limits owing to uncertainty in input data and numerical equations. In this study, we developed a data-based model using a deep neural network (DNN) to overcome the limitations of numerical models. The high PM2.5 concentration prediction performance was considerably improved. These results are expected to help predicting public health and reduce economic losses.