The acceleration of industrialization not only brings rapid economic development,but also increa-ses the concentration of pollutants mainly PM2.5,which brings adverse effects on human health and envi-ronmental governance.Reasonable and effective prediction of PM2.5 concentration is of great significance to human health and environmental governance.In this paper,a prediction model of PM2.5 concentration based on multiple regression model is designed to predict the PM2.5 concentration of Yan'an city in spring,summer,autumn and winter respectively,and compared with the prediction results of limit tree re-gression,Catboost regression and K proximity regression.The results show that the error of multiple regres-sion model is the smallest and the fitting precision is the highest,which provides a reliable scientific basis for air pollution control in Yan'an city.
关键词
多元回归/PM2.5预测/极限树回归/随机森林
Key words
Kev words:multiple regression/PM2.5 prediction/extra tree regression/random forest
维普
万方数据