Prediction and Study of Air Quality Based on Multiple Linear Regression and Grey Correlation Analysis

The aim of this paper is to construct a model by both multiple linear regression and grey correlation analysis in order to improve the accuracy and depth of understanding of air quality prediction. By collecting and analysing key meteorological factors (e.g., temperature, humidity, wind speed, etc.) and pollution source emission data, this study firstly applies multiple linear regression to establish a quantitative relationship model between air quality indicators (e.g., PM2.5, SO2 concentration) and multiple predictors. Subsequently, grey correlation analysis is introduced to explore in depth the nonlinear dynamic correlations among the factors and their combined effects on air quality. The empirical study shows that the composite model can not only effectively predict the shortterm air quality trends, but also identify the key sensitive factors affecting air quality, which provides a scientific basis for the formulation of environmental protection policies and pollution prevention and control measures.