CombineDeepNet: A Deep Network for Multistep Prediction of Near-Surface PM2.5 Concentration

Authors

Prasanjit Dey, Technological University Dublin, IrelandFollow
Soumyabrata Dev, University College Dublin, Ireland
Bianca Schoen-Phelan, Technological University Dublin

Author ORCID Identifier

https://orcid.org/0000-0002-2248-1701

Document Type

Conference Paper

Disciplines

Computer Sciences, Environmental sciences, Remote sensing

Publication Details

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ( Volume: 17), Page(s): 788 - 807.

DOI:10.1109/JSTARS.2023.3333269

Abstract

PM_2.5 is a type of air pollutant that can cause respiratory and cardiovascular problems. Precise PM_2.5 ( μg/m³ ) concentration prediction may help reduce health concerns and provide early warnings. To better understand air pollution, a number of approaches have been presented for predicting PM_2.5 concentrations. Previous research used deep learning models for hourly predictions of air pollutants due to their success in pattern recognition, however, these models were unsuitable for multisite, long-term predictions, particularly in regard to the correlation between pollutants and meteorological data. This article proposes the combine deep network (CombineDeepNet), which combines multiple deep networks, including a bidirectional long short-term memory, bidirectional gated recurrent units, and a shallow model represented by fully connected layers, to create a hybrid forecasting system. It can effectively capture the complex relationships between air pollutants and various influencing factors to predict hourly PM_2.5 concentrations in multiple monitoring sites based in China. The best root mean square error achieved was 22.0 μg/m³ (long-term) and 6.2 μg/m³ (short-term), with mean absolute error values of 3.4 μg/m³ (long-term) and 2.2 μg/m³ (short-term). In addition, the correlation coefficient (R²) reached 0.96 (long-term) and 0.83 (short-term) across six monitoring sites. These results demonstrate that CombineDeepNet enhances prediction accuracy compared with popular deep learning methods. Therefore, CombineDeepNet proves to be a important framework for predicting PM_2.5 concentration.

DOI

https://doi.org/10.1109/JSTARS.2023.3333269

Recommended Citation

Dey, Prasanjit; Dev, Soumyabrata; and Schoen-Phelan, Bianca, "CombineDeepNet: A Deep Network for Multistep Prediction of Near-Surface PM2.5 Concentration" (2023). Conference papers. 26.
https://arrow.tudublin.ie/diraacon/26

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.