This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Improving Air Quality Prediction via Self-Supervision Masked Air Modeling
by
Shuang Chen
Shuang Chen 1,
Li He
Li He 2,
Shinan Shen
Shinan Shen 1,
Yan Zhang
Yan Zhang 1,3,4,* and
Weichun Ma
Weichun Ma 1,3,4,5,*
1
Department of Environmental Science and Engineering, Fudan University, Shanghai 200438, China
2
Environment and Energy, Peking University Shenzhen Graduate School, Shenzhen 518055, China
3
Shanghai Key Laboratory of Atmospheric Particle Pollution and Prevention (LAP3), Fudan University, Shanghai 200433, China
4
Shanghai Key Laboratory of Policy Simulation and Assessment for Ecology and Environment Governance, Shanghai 200433, China
5
Institute of Eco-Chongming (IEC), No. 3663 Northern Zhongshan Road, Shanghai 200062, China
*
Authors to whom correspondence should be addressed.
Atmosphere 2024, 15(7), 856; https://doi.org/10.3390/atmos15070856 (registering DOI)
Submission received: 9 June 2024
/
Revised: 13 July 2024
/
Accepted: 17 July 2024
/
Published: 19 July 2024
Abstract
Presently, the harm to human health created by air pollution has greatly drawn public attention, in particular, vehicle emissions including nitrogen oxides as well as particulate matter. How to predict air quality, e.g., pollutant concentration, efficiently and accurately is a core problem in environmental research. Developing a robust air quality predictive model has become an increasingly important task, holding practical significance in the formulation of effective control policies. Recently, deep learning has progressed significantly in air quality prediction. In this paper, we go one step further and present a neat scheme of masked autoencoders, termed as masked air modeling (MAM), for sequence data self-supervised learning, which addresses the challenges posed by missing data. Specifically, the front end of our pipeline integrates a WRF-CAMx numerical model, which can simulate the process of emission, diffusion, transformation, and removal of pollutants based on atmospheric physics and chemical reactions. Then, the predicted results of WRF-CAMx are concatenated into a time series, and fed into an asymmetric Transformer-based encoder–decoder architecture for pre-training via random masking. Finally, we fine-tune an additional regression network, based on the pre-trained encoder, to predict ozone (O) concentration. Coupling these two designs enables us to consider the atmospheric physics and chemical reactions of pollutants while inheriting the long-range dependency modeling capabilities of the Transformer. The experimental results indicated that our approach effectively enhances the WRF-CAMx model’s predictive capabilities and outperforms pure supervised network solutions. Overall, using advanced self-supervision approaches, our work provides a novel perspective for further improving air quality forecasting, which allows us to increase the smartness and resilience of the air prediction systems. This is due to the fact that accurate prediction of air pollutant concentrations is essential for detecting pollution events and implementing effective response strategies, thereby promoting environmentally sustainable development.
Share and Cite
MDPI and ACS Style
Chen, S.; He, L.; Shen, S.; Zhang, Y.; Ma, W.
Improving Air Quality Prediction via Self-Supervision Masked Air Modeling. Atmosphere 2024, 15, 856.
https://doi.org/10.3390/atmos15070856
AMA Style
Chen S, He L, Shen S, Zhang Y, Ma W.
Improving Air Quality Prediction via Self-Supervision Masked Air Modeling. Atmosphere. 2024; 15(7):856.
https://doi.org/10.3390/atmos15070856
Chicago/Turabian Style
Chen, Shuang, Li He, Shinan Shen, Yan Zhang, and Weichun Ma.
2024. "Improving Air Quality Prediction via Self-Supervision Masked Air Modeling" Atmosphere 15, no. 7: 856.
https://doi.org/10.3390/atmos15070856
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.