Air Quality Prediction Based on a New Discrete Variable Weight Multivariable Grey Model
摘要
With the rapid development of industrialization and urbanization, air pollution has become a major environmental problem in developing areas. Existing prediction models have some limitations in dealing with limited data samples, nonlinear trends and regional differences. Therefore, an improved grey prediction framework is constructed and applied to the air quality prediction of Yangquan City and Jincheng City in Shanxi Province. Firstly, grey correlation analysis is used to identify the main influencing factors, including population, urbanization rate, secondary industry added value, etc. Secondly, fractional grey model is constructed to predict the future evolution trend of the above factors. Subsequently, multivariate discrete variable weight grey model is established to fit and predict the concentration of air pollutants. Finally, scenario simulation analysis is carried out under different influencing factors scenarios. The research results show that by 2030, the annual average concentrations of PM2.5, PM10, and O3 in Yangquan City are expected to decrease to 34.01 µg/m3, 67.05 µg/m3 and 130.61 µg/m3, respectively. The corresponding concentrations in Jincheng City are expected to be 30.97 µg/m3, 61.23 µg/m3 and 140.85 µg/m3, respectively. In addition, the air pollution level increases with the growth of population, the number of motor vehicles and the scale of secondary industry, but decreases with the increase of urbanization rate. When the annual growth rate of urban population and vehicles is controlled within 1%, and the annual growth rate of secondary industry added value does not exceed 5%, the adverse impact on air quality is small. Based on the research findings, it is recommended that local governments strengthen environmental protection while promoting industrial development, and further improve air quality through the management of traffic and population.