Zhang Kefei, Yang Xiaolin, Cao Hua, Thé Jesse, Tan Zhongchao, Yu Hesheng
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; Lakes Environmental Research Inc., 170 Columbia St. W. Suite 1, Waterloo, Ontario N2L 3L3, Canada.
Environ Int. 2023 Jan;171:107691. doi: 10.1016/j.envint.2022.107691. Epub 2022 Dec 10.
Accurate and reliable forecasting of PM and PM concentrations is important to the public to reasonably avoid air pollution and for the governmental policy responses. However, the prediction of PM and PM 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 and PM 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 and PM, 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.
准确可靠地预测细颗粒物（PM）和颗粒物（PM）浓度，对于公众合理避免空气污染以及政府制定政策应对措施而言至关重要。然而，由于大气流动的动态变化，PM和PM浓度的预测具有很大的不确定性和不稳定性，这使得单一模型难以有效地提取时空依赖性。本文报告了一种稳健的预测系统，以实现对PM和PM浓度的准确多步超前预测。首先，采用相关性分析来筛选有关污染和气象的空间信息，这些信息可能有助于预测目标城市的浓度。然后，使用时空注意力机制从空间和时间维度对原始输入进行加权，以增强关键信息。随后，采用具有特征提取能力的基于残差的卷积神经网络对精炼后的输入进行建模。最后，应用五个准确性指标和另外两个统计检验来全面评估所提出的预测系统的性能。此外，对长江三角洲城市群地区三个主要城市的实验研究表明，该预测系统在准确性和稳定性方面优于各种流行的基线模型。定量分析表明，与基线模型相比，所提出的时空注意力残差卷积神经网络（STA-ResCNN）模型在三个主要城市对PM和PM提前1 - 4小时预测的平均值上，分别将均方根误差降低了5.595% - 15.247%和6.827% - 16.906%。通过在整个地区其他23个城市的扩展应用，进一步验证了所提出的预测系统的适用性和泛化能力。结果证明，该预测系统在空气污染的预警、区域预防和控制方面具有广阔前景。
