DOI: 10.1016/j.atmosenv.2018.04.004
Scopus记录号: 2-s2.0-85045378706
论文题名: PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors
作者: Zhu S ; , Lian X ; , Wei L ; , Che J ; , Shen X ; , Yang L ; , Qiu X ; , Liu X ; , Gao W ; , Ren X ; , Li J
刊名: Atmospheric Environment
ISSN: 0168-2563
EISSN: 1573-515X
出版年: 2018
卷: 183 起始页码: 20
结束页码: 32
语种: 英语
英文关键词: Gravitational search algorithm
; Grey correlation analysis
; Particle swarm optimization
; PM2.5 concentrations
; Support vector regression
Scopus关键词: Air quality
; Climate models
; Correlation methods
; Learning algorithms
; Neural networks
; Particle swarm optimization (PSO)
; Particles (particulate matter)
; Regression analysis
; Respiratory system
; Air quality forecasting
; Complementary ensemble empirical mode decompositions
; Generalized Regression Neural Network(GRNN)
; Gravitational search algorithms
; Grey correlation analysis
; Meteorological factors
; PM2.5 concentration
; Support vector regression (SVR)
; Weather forecasting
; air quality
; algorithm
; atmospheric pollution
; concentration (composition)
; correlation
; experimental study
; forecasting method
; meteorology
; model
; optimization
; particle size
; particulate matter
; regression analysis
; air pollution
; air quality
; Article
; China
; correlation analysis
; forecasting
; learning algorithm
; meteorological phenomena
; multiple regression
; particulate matter
; priority journal
; statistical model
; support vector machine
; time series analysis
; China
; Chongqing
; Harbin
; Heilongjiang
; Jinan [Shandong]
; Shandong
Scopus学科分类: Environmental Science: Water Science and Technology
; Earth and Planetary Sciences: Earth-Surface Processes
; Environmental Science: Environmental Chemistry
英文摘要: The PM2.5 is the culprit of air pollution, and it leads to respiratory system disease when the fine particles are inhaled. Therefore, it is increasingly significant to develop an effective model for PM2.5 forecasting and warnings that informs people to foresee the air quality. People can reduce outdoor activities and take preventive measures if they know the air quality is bad ahead of time. In addition, reliable forecasting results can remind the relevant departments to control and reduce pollutants discharge. According to our knowledge, the current hybrid forecasting techniques of PM2.5 do not take the meteorological factors into consideration. Actually, meteorological factors affect the concentrations of air pollution, but it is unclear whether meteorological factors are helpful for improving the PM2.5 forecasting results or not. This paper proposes a hybrid model called CEEMD-PSOGSA-SVR-GRNN, based on complementary ensemble empirical mode decomposition (CEEMD), particle swarm optimization and gravitational search algorithm (PSOGSA), support vector regression (SVR), generalized regression neural network (GRNN) and grey correlation analysis (GCA), for the daily PM2.5 concentrations forecasting. The main steps of proposed model are described as follows: the original PM2.5 data decomposition with CEEMD, optimal SVR selection with PSOGCA, meteorological factors selection with GCA, residual revision by GRNN and forecasting results analysis. Three cities (Chongqing, Harbin and Jinan) in China with different characteristics of climate, terrain and pollution sources are selected to verify the effectiveness of proposed model, and CEEMD-PSOGSA-SVR*, EEMD-PSOGSA-SVR, PSOGSA-SVR, CEEMD-PSO-SVR, CEEMD-GSA-SVR, CEEMD-GWO-SVR are considered to be compared models. The experimental results show that the hybrid CEEMD-PSOGSA-SVR-GRNN model outperforms other six compared models. Therefore, the proposed CEEMD-PSOGSA-SVR-GRNN model can be used to develop air quality forecasting and warnings. © 2018 Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/82866
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: School of Public Health, Lanzhou University, Lanzhou, Gansu, China; School of Mathematics & Statistics, Lanzhou University, Tianshuinanlu 222, Lanzhou, China; School of Science, Nanchang Institute of Technology, Nanchang, JiangXi, China
Recommended Citation:
Zhu S,, Lian X,, Wei L,et al. PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors[J]. Atmospheric Environment,2018-01-01,183