Prediction and Analysis of PM2.5 and PM10 Concentration in Hohhot Based on Machine Learning
A machine learning model was established to predict the change of pollutant concentration according to the complexity and nonlinearity of air pollutant concentration change.By analyzing the time variation characteristics of air pollutants at different time scales in Hohhot,the air pollution concentration,meteorological factors,seasonal factors and human factors were determined as the input variables of the prediction model.The air pollutants with high correlation with PM2.5 and PM10 were determined by grey correlation analysis.The main meteorological factors in meteorological factors were extracted by principal component analysis.BP neural network model and support vector machine model were established to predict the concentration of PM2.5 and PM10.The predicted value of BP neural network model is close to the measured value,and the R2 of training set and test set is above 0.8.The mean absolute error(MAE)was less than 19.The root mean square error(RMSE)was less than 25.The R2 of the SVM model for PMu prediction can reach 0.895,but the prediction R2 for PM10 is only 0.668.
Air pollutantsGrey correlation analysisPrincipal component analysisBP neural networkSupport vector machine
万方数据
