Multi-step forecast of PM2.5 and PM10 concentrations using convolutional neural network integrated with spatial-temporal attention and residual learning

Kefei Zhang; Xiaolin Yang; Hua Cao; Jesse Thé; Zhongchao Tan; Hesheng Yu

doi:10.1016/j.envint.2022.107691

Multi-step forecast of PM_2.5 and PM₁₀ concentrations using convolutional neural network integrated with spatial-temporal attention and residual learning

Environ Int. 2023 Jan:171:107691. doi: 10.1016/j.envint.2022.107691. Epub 2022 Dec 10.

Authors

Kefei Zhang¹, Xiaolin Yang¹, Hua Cao¹, Jesse Thé², Zhongchao Tan³, Hesheng Yu⁴

Affiliations

¹ School of Chemical Engineering and Technology, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China; Key Laboratory of Coal Processing and Efficient Utilization, Ministry of Education, Xuzhou, Jiangsu 221116, China.
² Department of Mechanical & Mechatronics Engineering, University of Waterloo, 200 University Avenue West, Waterloo, Ontario N2L 3G1, Canada; Lakes Environmental Research Inc., 170 Columbia St. W. Suite 1, Waterloo, Ontario N2L 3L3, Canada.
³ Department of Mechanical & Mechatronics Engineering, University of Waterloo, 200 University Avenue West, Waterloo, Ontario N2L 3G1, Canada; Department of Energy and Power Engineering, Tsinghua University, Beijing 100084, China.
⁴ School of Chemical Engineering and Technology, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China; Key Laboratory of Coal Processing and Efficient Utilization, Ministry of Education, Xuzhou, Jiangsu 221116, China; Department of Mechanical & Mechatronics Engineering, University of Waterloo, 200 University Avenue West, Waterloo, Ontario N2L 3G1, Canada. Electronic address: heshengyu@cumt.edu.cn.

PMID: 36516675
DOI: 10.1016/j.envint.2022.107691

Abstract

Accurate and reliable forecasting of PM_2.5 and PM₁₀ concentrations is important to the public to reasonably avoid air pollution and for the governmental policy responses. However, the prediction of PM_2.5 and PM₁₀ concentrations has great uncertainty and instability because of the dynamics of atmospheric flows, making it difficult for a single model to efficiently extract the spatial-temporal dependences. This paper reports a robust forecasting system to achieve accurate multi-step ahead forecasting of PM_2.5 and PM₁₀ concentrations. First, correlation analysis is adopted to screen the spatial information on pollution and meteorology that may facilitate the prediction of concentrations in a target city. Then, a spatial-temporal attention mechanism is used to assign weights to original inputs from both space and time dimensions to enhance the essential information. Subsequently, the residual-based convolutional neural network with feature extraction capabilities is employed to model the refined inputs. Finally, five accuracy metrics and two additional statistical tests are applied to comprehensively assess the performance of the proposed forecasting system. In addition, experimental studies of three major cities in the Yangtze River Delta urban agglomeration region indicate that the forecasting system outperforms various prevalent baseline models in terms of accuracy and stability. Quantitatively, the proposed STA-ResCNN model reduces root mean square error by 5.595 %-15.247 % and 6.827 %-16.906 % for the average of 1-4 h ahead predictions in three major cities of PM_2.5 and PM₁₀, respectively, compared to baseline models. The applicability and generalization of the proposed forecasting system are further verified by the extended applications in the other 23 cities in the entire region. The results prove that the forecasting system is promising in the early warning, regional prevention, and control of air pollution.

Keywords: Convolutional neural network; Deep learning; PM concentration forecasting; Residual learning; Spatial-temporal attention.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Air Pollutants* / analysis
Air Pollution* / analysis
Environmental Monitoring / methods
Neural Networks, Computer
Particulate Matter / analysis

Substances

Air Pollutants
Particulate Matter