Predicting concentrations of atmospheric particle matters in Guangzhou by time series models

Particulate matter is one of the major air pollutants closely related to human health. In order predict atmospheric particulate concentrations effectively and accurately, this paper utilized ARIMA model, Holt-Winters STL-Holt model STL-ARIMA carry out prediction experiments based on hourly PM2.5 PM10 concentration historical data in Guangzhou city. The results showed that four models were effective predicting concentrations. RMSE, MAE, MAPE, R2 metrics used evaluate accuracy models. It was found performed best among This study may provide guides for environmental authorities forecasting