Abstract
Accurate PM2.5 concentration forecasting is crucial for protecting public health and atmospheric environment. However, the intermittent and unstable nature of PM2.5 concentration series makes its forecasting become a very difficult task. In order to improve the forecast accuracy of PM2.5 concentration, this paper proposes a hybrid model based on wavelet transform (WT), variational mode decomposition (VMD) and back propagation (BP) neural network optimized by differential evolution (DE) algorithm. Firstly, WT is employed to disassemble the PM2.5 concentration series into a number of subsets with different frequencies. Secondly, VMD is applied to decompose each subset into a set of variational modes (VMs). Thirdly, DE-BP model is utilized to forecast all the VMs. Fourthly, the forecast value of each subset is obtained through aggregating the forecast results of all the VMs obtained from VMD decomposition of this subset. Finally, the final forecast series of PM2.5 concentration is obtained by adding up the forecast values of all subsets. Two PM2.5 concentration series collected from Wuhan and Tianjin, respectively, located in China are used to test the effectiveness of the proposed model. The results demonstrate that the proposed model outperforms all the other considered models in this paper.
Highlights
Over the past few decades, with the rapid development of industrialization and urbanization, the occurrence of haze pollution episodes has become more frequent and more severe in China [1,2].According to the statistics of China’s National Development and Reform Commission, since early 2013, many areas including the north China, Huanghuai, Jianghuai, Jianghan, south of the Yangtze River and the north of southern China have suffered severe and continuous haze weather
To verify the superiority of the proposed wavelet transform (WT)-variational mode decomposition (VMD)-differential evolution (DE)-back propagation (BP) model in forecasting capability, forecasting models of BP, DE-BP, WT-DE-BP, VMD-DE-BP and WT-VMD-DE-BP are adopted as the benchmark models
Accurate PM2.5 concentration forecasting is crucial for risk-analysis and decision-making in environmental protection departments
Summary
Over the past few decades, with the rapid development of industrialization and urbanization, the occurrence of haze pollution episodes has become more frequent and more severe in China [1,2].According to the statistics of China’s National Development and Reform Commission, since early 2013, many areas including the north China, Huanghuai, Jianghuai, Jianghan, south of the Yangtze River and the north of southern China have suffered severe and continuous haze weather. Over the past few decades, with the rapid development of industrialization and urbanization, the occurrence of haze pollution episodes has become more frequent and more severe in China [1,2]. Haze pollution brings serious adverse effects on the environment, clime, ecological systems, economy and public health, causes great harm to the human production and life on a global scale [3,4]. Even though the mechanism of haze formation is still not clear [5], the high level concentrations of fine particles with aerodynamic diameter of 2.5 μm or less (PM2.5 ) was inferred as the main reason of haze pollution episodes, and attracted widespread public concerns [6,7]. Public Health 2017, 14, 764; doi:10.3390/ijerph14070764 www.mdpi.com/journal/ijerph
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Environmental Research and Public Health
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
