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.
14 May 2022 in Environmental Science and Pollution Research
Air pollution seriously affects human health. The traffic and production restriction is widely used for controlling heavy air pollution. However, the effectiveness of these two policies has not been scientifically verified through a city-level study. COVID-19 pandemic caused lockdowns in many cities, which makes it possible to verify the effectiveness of these two policies. Taken Wuhan as the study area, this study firstly verifies the existence of lockdown effect on air pollution and analyzes the evolution rule of six air pollutants (PM2.5, PM10, NO2, SO2, CO and O3) using statistical methods. Then the structural break points in six air pollutants are detected with the regression discontinuity design model. Because Spring Festival overlapping COVID-19 may also affect the air pollution, in order to avoid the disturbance of Spring Festival on the results, the Spring Festival effect is also validated. The results illustrate that the effects of traffic and production restriction on six air pollutants are obviously different, in which the concentrations of PM2.5, PM10 and NO2 decrease significantly, while traffic and production restriction has no apparent effects on SO2, CO and O3. Moreover, the structural break points are verified in the four air pollutants (PM2.5, PM10, NO2 and CO), and the structural break points are caused by lockdown instead of Spring Festival. This study revealed how the traffic and production restriction affected the air pollution at a city level, and provided strong implementation basis to the air pollution control policy.