Forecasting hourly PM2.5 based on deep temporal convolutional neural network and decomposition method

doi:10.1016/j.asoc.2021.107988

	Forecasting hourly PM2.5 based on deep temporal convolutional neural network and decomposition method
	Jiang, Fuxin 1,2; Zhang, Chengyuan 3; Sun, Shaolong 4; Sun, Jingyun5
	2021-12
发表期刊	Applied Soft Computing
卷号	113
摘要	For hourly PM2.5 concentration prediction, accurately capturing the data patterns of external factors that affect PM2.5 concentration changes, and constructing a forecasting model is one of efficient means to improve forecasting accuracy. In this study, a novel hybrid forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and deep temporal convolutional neural network (DeepTCN) is developed to predict PM2.5 concentration, by modeling the data patterns of historical pollutant concentrations data, meteorological data, and discrete time variables’ data. Taking PM2.5 concentration of Beijing as the sample, experimental results showed that the forecasting accuracy of the proposed CEEMDAN-DeepTCN model is verified to be the highest when compared with the statistics-based models, traditional machine learning models, the popular deep learning models and several existing hybrid models. The new model has improved the capability to model the PM2.5-related factor data patterns, and can be used as a promising tool for forecasting PM2.5 concentrations. © 2021 Elsevier B.V.
关键词	Acoustic noise measurement Convolution Learning systems Neural network models Convolutional neural networks Deep neural networks Forecasting Meteorology Spurious signal noise Adaptive noise Complete ensemble empirical mode decomposition with adaptive noise Convolutional neural network Data patterns Deep learning Empirical Mode Decomposition Forecasting models PM 2.5 PM2.5 concentration forecasting Temporal convolutional
DOI	10.1016/j.asoc.2021.107988
收录类别	EI ; SCIE ; SSCI
ISSN	1568-4946
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications
WOS记录号	WOS:000765558100001
出版者	Elsevier Ltd
EI入藏号	20214511118197
EI主题词	Empirical mode decomposition
EI分类号	461.4 Ergonomics and Human Factors Engineering ; 716.1 Information Theory and Signal Processing ; 723.4 Artificial Intelligence ; 751.4 Acoustic Noise ; 941.2 Acoustic Variables Measurements
原始文献类型	Journal article (JA)
EISSN	1872-9681
引用统计	被引频次：27[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/33414
专题	统计与数据科学学院
作者单位	1.Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing; 100190, China; 2.School of Economics and Management, University of Chinese Academy of Sciences, Beijing; 100190, China; 3.School of Economics and Management, Xidian University, Xi'an; 710126, China; 4.School of Management, Xi'an Jiaotong University, Xi'an; 710049, China; 5.School of Statistics, Lanzhou University of Finance and Economics, Lanzhou; 730020, China
第一作者单位	经济学院
推荐引用方式 GB/T 7714	Jiang, Fuxin,Zhang, Chengyuan,Sun, Shaolong,et al. Forecasting hourly PM2.5 based on deep temporal convolutional neural network and decomposition method[J]. Applied Soft Computing,2021,113.
APA	Jiang, Fuxin,Zhang, Chengyuan,Sun, Shaolong,&Sun, Jingyun.(2021).Forecasting hourly PM2.5 based on deep temporal convolutional neural network and decomposition method.Applied Soft Computing,113.
MLA	Jiang, Fuxin,et al."Forecasting hourly PM2.5 based on deep temporal convolutional neural network and decomposition method".Applied Soft Computing 113(2021).