基于改进机器学习的PM2.5浓度预测模型研究OA北大核心CSTPCD

In response to the problem of performance decrease of existing machine learning model for predicting PM2.5 concentration because that the model is too complex,and does not consider spatio-temporal information and effective missing values imputation is not accurate,random forest is used instead of statistical methods to fill in missing values,and spatio-temporal factors are incorporated to improve model accuracy.Combining remote sensing data,meteorological and collaborative pollutant data,a model(K-means-RF-XGBoost model)suitable for PM2.5 concentration prediction in coastal cities is established,with a prediction time of only 4％of that of BP neural networks.The prediction of PM2.5 concentration of the model is trained and tested using real-time monitoring data from Dalian in 2019.The results show that the established K-means-RF-XGBoost model has high accuracy in predicting PM2.5 concentration,and compared to the same model without considering spatio-temporal information,the root mean square error(erms)decreases by about 48％,and coefficient of determination(R2)increases by about 10％.It effectively predicts high PM2.5 concentrations and is suitable for large fluctuation ranges,such as an R of 0.935 is achieved in the testing set for the spring model.At the same time,it performs well in daily prediction,with an R2 of 0.819.This study provides a new idea for predicting PM2.5 concentration in coastal cities.