Short-term prediction of urban PM 2.5 based on a hybrid modified variational mode decomposition and support vector regre
- PDF / 4,967,836 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 54 Downloads / 127 Views
REVIEW ARTICLE
Short-term prediction of urban PM2.5 based on a hybrid modified variational mode decomposition and support vector regression model Junwen Chu 1 & Yingchao Dong 1 & Xiaoxia Han 1 & Jun Xie 2 & Xinying Xu 1 & Gang Xie 1,3 Received: 18 August 2020 / Accepted: 30 September 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract PM2.5 (particulate matter with a size/diameter ≤ 2.5 μm) is an important air pollutant that affects human health, especially in urban environments. However, as time-series data of PM2.5 are non-linear and non-stationary, it is difficult to predict future PM2.5 distribution and behavior. Therefore, in this paper, we propose a hybrid short-term urban PM2.5 prediction model based on variational mode decomposition modified by the correntropy criterion, the state transition simulated annealing (STASA) algorithm, and a support vector regression model to overcome the disadvantages of traditional forecasting techniques which consider different environmental factors. Two experiments were performed with the model to assess its effectiveness and predictive ability: in experiment I, we verified the performance of STASA on benchmark functions, while in experiment II, we used PM2.5 data from different epochs and regions of Beijing to verify its forecasting performance. The experimental results showed that the proposed model is robust and can achieve satisfactory prediction results under different conditions compared with current forecasting techniques. Keywords Air pollution forecasting . Modified variational mode decomposition . State transition simulated annealing algorithm . Support vector regression . PM2.5 prediction . Hybrid models
Introduction With the development of China’s industry and the subsequent emission of massive amounts of chemical substances, the problem of air pollution has gradually become one of the most important problems to solve, especially in large cities in northern China. PM2.5, i.e., particulate matter smaller than 2.5 μm, is one of the main constituents of smog, where higher PM2.5 Responsible Editor: Marcus Schulz * Xiaoxia Han [email protected] 1
Department of Automation, College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China
2
College of Information and Computer, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China
3
School of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, Shanxi, China
concentrations result in more serious air pollution. In recent years, many studies have shown that high concentrations of PM2.5 can increase the occurrence of lung cancer (Burnett et al. 2014; Wu et al. 2014; Zheng et al. 2017). Thus, the establishment of a reasonable and accurate early-warning system for short-term PM2.5 levels is not only helpful for planning effective preventative measures, but it also has practical significance for government departments in terms of regulating social activities, which can avoid some of the haza
Data Loading...
