Prediction of PM2.5 Concentration in Ningxia Hui Autonomous Region Based on PCA-Attention-LSTM

Abstract

The problem of air pollution has attracted more and more attention. PM2.5 is a key factor affecting air quality. In order to improve the prediction accuracy of PM2.5 concentration and make people effectively control the generation and propagation of atmospheric pollutants, in this paper, a long short-term memory neural network (LSTM) model based on principal component analysis (PCA) and attention mechanism (attention) is constructed, which first uses PCA to reduce the dimension of data, eliminate the correlation effect between indicators, and reduce model complexity, and then uses the extracted principal components to establish a PCA-attention-LSTM model. Simulation experiments were conducted on the air pollutant data, meteorological element data, and working day data of five cities in Ningxia from 2018 to 2020 to predict the PM2.5 concentration. The PCA-attention-LSTM model is compared with the support vector regression model (SVR), AdaBoost model, random forest model (RF), BP neural network model (BPNN), and long short-term memory neural network (LSTM). The results show that the PCA-attention-LSTM model is optimal; the correlation coefficients of the PCA-attention-LSTM model in Wuzhong, Yinchuan, Zhongwei, Shizuishan, and Guyuan are 0.91, 0.93, 0.91, 0.91, and 0.90, respectively, and the SVR model is the worst. The addition of variables such as a week, precipitation, and temperature can better predict PM2.5 concentration. The concentration of PM2.5 was significantly correlated with the geographical location of the municipal area, and the overall air quality of the southern mountainous area was better than that in the northern Yellow River irrigation area. PM2.5 concentration shows a clear seasonal change trend, with the lowest in summer and the highest in winter, which is closely related to the climate environment of Ningxia.