Abstract
PM(2.5) (Particulate Matter less than 2.5 micrometers) is the main cause of haze weather, especially high concentrations of PM(2.5) can have a significant impact on normal production and daily life. The developed heavy industry in North China has led to poor air quality, characterized by high concentrations of pollutants and frequent pollution incidents. The research on the prediction of PM(2.5) concentration in North China is of great significance for the prevention and control of air pollution nationwide. In this article, hourly PM(2.5) data from six important cities in North China, namely Beijing, Tianjin, Shijiazhuang, Taiyuan, Jinan, and Zhengzhou, were used as the basic dataset. Empirical Mode Decomposition (EMD), Long Short-Term Memory (LSTM), Support Vector Machine (SVM), and Autoregressive Integrated Moving Average (ARIMA) were mixed to establish a PM(2.5) hourly prediction model (Hybrid-EMD(HL)). The selection of different analysis models based on the time-frequency characteristics of high-frequency and low-frequency subsequences helps to improve the adaptability of data and models, deeply mine data information, and fully express the inherent characteristics of one-dimensional time series, which improves the prediction accuracy. Firstly, nonlinear and non-stationary PM(2.5) time-series data were decomposed into Intrinsic Mode Functions (IMFs) and residuals at different frequencies using EMD technology. Then, based on the frequency characteristics of the subseries, LSTM and ARIMA model were used to predict the high-frequency and low-frequency parts, respectively. Finally, the SVM (Support Vector Machine) model was used to integrate the high and low frequency prediction results to obtain the final result. The simulation experiment was verified by algorithm performance indicators. Compared with the single prediction model, the hybrid prediction model significantly improved the prediction accuracy of PM(2.5) concentration. Specifically, in multiple data experiments, the directional indicator DA of hybrid prediction model is higher than 0.69, showing better direction prediction ability, which is of practical significance for the prevention and control of air pollution in North China.