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

doi:10.1016/j.asoc.2021.107988

CSpace

	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, Jingyun 5
	2021-12-01
发表期刊	APPLIED SOFT COMPUTING
ISSN	1568-4946
卷号	113 页码:15
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. (C) 2021 Elsevier B.V. All rights reserved.
关键词	PM2.5 concentration forecasting Complete ensemble empirical mode decomposition with adaptive noise Temporal convolutional Data patterns Deep learning
DOI	10.1016/j.asoc.2021.107988
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[72101197] ; National Natural Science Foundation of China[71988101] ; Fundamental Research Funds for the Central Universities, China[SK2021007] ; Innovation Ability Improvement Project in Colleges and Universities of Gansu Province of China[2019A-060]
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
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/60158
专题	中国科学院数学与系统科学研究院
通讯作者	Zhang, Chengyuan; Sun, Shaolong
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Econ & Management, Beijing 100190, Peoples R China 3.Xidian Univ, Sch Econ & Management, Xian 710126, Peoples R China 4.Xi An Jiao Tong Univ, Sch Management, Xian 710049, Peoples R China 5.Lanzhou Univ Finance & Econ, Sch Stat, Lanzhou 730020, Peoples R China
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,2021,113:15.
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,113,15.
MLA	Jiang, Fuxin,et al."Forecasting hourly PM2.5 based on deep temporal convolutional neural network and decomposition method".APPLIED SOFT COMPUTING 113(2021):15.