Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions

doi:10.4209/aaqr.2020.03.0097

	Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions
	Guo, Qingehun 2,3; He, Zhenfang 1,2; Li, Shanshan 2; Li, Xinzhou 3,4; Meng, Jingjing 2; Hou, Zhanfang 2; Liu, Jiazhen 2; Chen, Yongjin 2
刊名	AEROSOL AND AIR QUALITY RESEARCH
	2020-06-01
卷号	20 期号:6 页码:1429-1439
关键词	Air pollution Wavelet artificial neural network Meteorological factor Forecast
ISSN号	1680-8584
DOI	10.4209/aaqr.2020.03.0097
通讯作者	Guo, Qingehun(guoqingchun@lcu.edu.cn) ; He, Zhenfang(hezhenfang@lcu.edu.cn)
英文摘要	Air quality forecasting is a significant method of protecting public health because it provides early warning of harmful air pollutants. In this study, we used correlation analysis and artificial neural networks (ANNs; including wavelet ANNs [WANNs]) to identify the linear and nonlinear associations, respectively, between the air pollution index (API) and meteorological variables in Xian and Lanzhou. Evaluating twelve algorithms and nineteen network topologies for the ANN and WANN models, we discovered that the optimal input variables for an API forecasting model were the APIs from the 3 preceding days and sixteen selected meteorological factors. Additionally, the API could be accurately predicted based solely on the value recorded 3 days earlier. Based on the correlation coefficients between the air pollution index of the targeted day and the tested variables, the API displayed the closest relationship with the API 1 day earlier as well as stronger correlations with the average temperature, average water vapor pressure, minimum temperature, maximum temperature, API 2 days earlier, and API 3 days earlier. When Bayesian regularization was applied as a training algorithm, the WANN and ANN models accurately reproduced the APIs in both Xian and Lanzhou, although the WANN model (R = 0.8846 for Xian and R = 0.8906 for Lanzhou) performed better than the ANN (R = 0.8037 for Xian and R = 0.7742 for Lanzhou) during the forecasting stage. These results demonstrate that WANNs are effective in short-term API forecasting because they can recognize historic patterns and thereby identify nonlinear relationships between the input and output variables. Thus, our study may provide a theoretical basis for environmental management policies.
资助项目	National Natural Science Foundation of China[41572150] ; National Natural Science Foundation of China[41472162] ; National Natural Science Foundation of China[41702373] ; Shandong Social Sciences Planning Research Program[18CKPJ34] ; Shandong Province Higher Educational Humanities and Social Science Program[J18RA196] ; State Key Laboratory of Loess and Quaternary Geology Foundation[SKLLQG1907]
WOS关键词	MACHINE LEARNING-METHOD ; PM2.5 ; MODEL ; PREDICTION ; POINT
WOS研究方向	Environmental Sciences & Ecology
语种	英语
出版者	TAIWAN ASSOC AEROSOL RES-TAAR
WOS记录号	WOS:000537943300022
资助机构	National Natural Science Foundation of China ; Shandong Social Sciences Planning Research Program ; Shandong Province Higher Educational Humanities and Social Science Program ; State Key Laboratory of Loess and Quaternary Geology Foundation
内容类型	期刊论文
源URL	[http://ir.ieecas.cn/handle/361006/14853]
专题	地球环境研究所_古环境研究室
通讯作者	Guo, Qingehun; He, Zhenfang
作者单位	1.Chinese Acad Sci, Res Ctr Ecoenvironm Sci, State Key Lab Urban & Reg Ecol, Beijing 100085, Peoples R China 2.Liaocheng Univ, Sch Environm & Planning, Liaocheng 252000, Shandong, Peoples R China 3.Chinese Acad Sci, Inst Earth Environm, State Key Lab Loess & Quaternary Geol, Xian 710061, Peoples R China 4.CAS Ctr Excellence Tibetan Plateau Earth Sci, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Guo, Qingehun,He, Zhenfang,Li, Shanshan,et al. Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions[J]. AEROSOL AND AIR QUALITY RESEARCH,2020,20(6):1429-1439.
APA	Guo, Qingehun.,He, Zhenfang.,Li, Shanshan.,Li, Xinzhou.,Meng, Jingjing.,...&Chen, Yongjin.(2020).Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions.AEROSOL AND AIR QUALITY RESEARCH,20(6),1429-1439.
MLA	Guo, Qingehun,et al."Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions".AEROSOL AND AIR QUALITY RESEARCH 20.6(2020):1429-1439.