Articles | Volume 15, issue 22
https://doi.org/10.5194/gmd-15-8439-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-15-8439-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model description paper
| 
21 Nov 2022
Model description paper |
| 21 Nov 2022
| 21 Nov 2022
Development of an LSTM broadcasting deep-learning framework for regional air pollution forecast improvement
Haochen Sun
Department of Mathematics, Hong Kong University of Science and
Technology, Clear Water Bay, Hong Kong SAR, China
Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong SAR, China
Jimmy C. H. Fung
Department of Mathematics, Hong Kong University of Science and
Technology, Clear Water Bay, Hong Kong SAR, China
Division of Environment and Sustainability, Hong Kong University of
Science and Technology, Clear Water Bay, Hong Kong SAR, China
Atmospheric Research Center, HKUST Fok Ying Tung Research Institute, Guangzhou, China
Yiang Chen
Division of Environment and Sustainability, Hong Kong University of
Science and Technology, Clear Water Bay, Hong Kong SAR, China
Zhenning Li
Division of Environment and Sustainability, Hong Kong University of
Science and Technology, Clear Water Bay, Hong Kong SAR, China
Dehao Yuan
Department of Computer Science, University of Maryland, College Park, Maryland, USA
Wanying Chen
Division of Environment and Sustainability, Hong Kong University of
Science and Technology, Clear Water Bay, Hong Kong SAR, China
Department of Geography and Resource Management, Chinese University of Hong Kong, Sha Tin, Hong Kong SAR, China
Viewed
Total article views: 4,309 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 25 Jul 2022)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 3,031 | 1,139 | 139 | 4,309 | 408 | 134 | 218 |
- HTML: 3,031
- PDF: 1,139
- XML: 139
- Total: 4,309
- Supplement: 408
- BibTeX: 134
- EndNote: 218
Total article views: 2,916 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 21 Nov 2022)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,097 | 714 | 105 | 2,916 | 163 | 115 | 199 |
- HTML: 2,097
- PDF: 714
- XML: 105
- Total: 2,916
- Supplement: 163
- BibTeX: 115
- EndNote: 199
Total article views: 1,393 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 25 Jul 2022)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 934 | 425 | 34 | 1,393 | 245 | 19 | 19 |
- HTML: 934
- PDF: 425
- XML: 34
- Total: 1,393
- Supplement: 245
- BibTeX: 19
- EndNote: 19
Viewed (geographical distribution)
Total article views: 4,309 (including HTML, PDF, and XML)
Thereof 4,167 with geography defined
and 142 with unknown origin.
Total article views: 2,916 (including HTML, PDF, and XML)
Thereof 2,873 with geography defined
and 43 with unknown origin.
Total article views: 1,393 (including HTML, PDF, and XML)
Thereof 1,294 with geography defined
and 99 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
12 citations as recorded by crossref.
- Development of an LSTM broadcasting deep-learning framework for regional air pollution forecast improvement H. Sun et al. https://doi.org/10.5194/gmd-15-8439-2022
- Interpretable Data-Driven Ozone Prediction Using Statistical Diagnostics, XGBoost, SHAP and Temporal Fusion Transformers B. Hu et al. https://doi.org/10.3390/su18021009
- Advances in air quality modeling through artificial intelligence, machine learning, and deep learning: A comprehensive review D. Nelson et al. https://doi.org/10.1016/j.scitotenv.2026.181593
- FastCTM (v1.0): Atmospheric chemical transport modelling with a principle-informed neural network for air quality simulations B. Lyu et al. https://doi.org/10.5194/gmd-18-6295-2025
- Application of artificial intelligence in air pollution monitoring and forecasting: A systematic review S. Chadalavada et al. https://doi.org/10.1016/j.envsoft.2024.106312
- Machine learning-enabled estimation and high-resolution forecasting of atmospheric VOCs B. Lu et al. https://doi.org/10.1016/j.atmosenv.2025.121364
- Improving PM2.5 simulations using LSTM: a study on spatiotemporal generalization X. Chen et al. https://doi.org/10.1016/j.apr.2025.102647
- A hybrid deep learning model for O3 forecasting and explaining in the Yangtze River Delta Region of China L. Wu et al. https://doi.org/10.1016/j.scitotenv.2025.180901
- MIPV-NWP-PINNs V1.0: development of a multi-scale photovoltaic power forecasting framework integrating numerical weather prediction with physics-informed neural networks F. Zhang et al. https://doi.org/10.5194/gmd-19-4999-2026
- Multimodal PM2.5 Forecasting Using Satellite Imagery and Sensor Data with Semi-supervised Deep Learning T. Srimanee et al. https://doi.org/10.1007/s41748-026-01109-3
- Air Pollution Forecasting Using Autoencoders: A Classification-Based Prediction of NO2, PM10, and SO2 Concentrations M. Rodríguez-García et al. https://doi.org/10.3390/nitrogen6040101
- Cross-scale prediction of oxidation behavior of uranium alloys based on deep learning W. Zhang et al. https://doi.org/10.1016/j.commatsci.2025.114422
12 citations as recorded by crossref.
- Development of an LSTM broadcasting deep-learning framework for regional air pollution forecast improvement H. Sun et al. https://doi.org/10.5194/gmd-15-8439-2022
- Interpretable Data-Driven Ozone Prediction Using Statistical Diagnostics, XGBoost, SHAP and Temporal Fusion Transformers B. Hu et al. https://doi.org/10.3390/su18021009
- Advances in air quality modeling through artificial intelligence, machine learning, and deep learning: A comprehensive review D. Nelson et al. https://doi.org/10.1016/j.scitotenv.2026.181593
- FastCTM (v1.0): Atmospheric chemical transport modelling with a principle-informed neural network for air quality simulations B. Lyu et al. https://doi.org/10.5194/gmd-18-6295-2025
- Application of artificial intelligence in air pollution monitoring and forecasting: A systematic review S. Chadalavada et al. https://doi.org/10.1016/j.envsoft.2024.106312
- Machine learning-enabled estimation and high-resolution forecasting of atmospheric VOCs B. Lu et al. https://doi.org/10.1016/j.atmosenv.2025.121364
- Improving PM2.5 simulations using LSTM: a study on spatiotemporal generalization X. Chen et al. https://doi.org/10.1016/j.apr.2025.102647
- A hybrid deep learning model for O3 forecasting and explaining in the Yangtze River Delta Region of China L. Wu et al. https://doi.org/10.1016/j.scitotenv.2025.180901
- MIPV-NWP-PINNs V1.0: development of a multi-scale photovoltaic power forecasting framework integrating numerical weather prediction with physics-informed neural networks F. Zhang et al. https://doi.org/10.5194/gmd-19-4999-2026
- Multimodal PM2.5 Forecasting Using Satellite Imagery and Sensor Data with Semi-supervised Deep Learning T. Srimanee et al. https://doi.org/10.1007/s41748-026-01109-3
- Air Pollution Forecasting Using Autoencoders: A Classification-Based Prediction of NO2, PM10, and SO2 Concentrations M. Rodríguez-García et al. https://doi.org/10.3390/nitrogen6040101
- Cross-scale prediction of oxidation behavior of uranium alloys based on deep learning W. Zhang et al. https://doi.org/10.1016/j.commatsci.2025.114422
Saved (final revised paper)
Latest update: 06 Jul 2026
Short summary
This study developed a novel deep-learning layer, the broadcasting layer, to build an end-to-end LSTM-based deep-learning model for regional air pollution forecast. By combining the ground observation, WRF-CMAQ simulation, and the broadcasting LSTM deep-learning model, forecast accuracy has been significantly improved when compared to other methods. The broadcasting layer and its variants can also be applied in other research areas to supersede the traditional numerical interpolation methods.
This study developed a novel deep-learning layer, the broadcasting layer, to build an end-to-end...
