Combined prediction of air quality based on IOWA operator
The purpose of this paper is to forecast AQI to reflect the trend and the fluctuation of data.So we propose a Prophet-EEMD-XGBoost model based on the induced ordered weighted average operator(IOWA).Firstly,Prophet algorithm was used to decompose the data into trend item,season item,holiday item and error item.Then,ensemble empirical mode decomposition EEMD was used to divide the original data into 9 IMF and residual component.Finally,XGBoost model was used to predict each component.MAE,MAPE,RMSE and RMSPE were used to evaluate the predicted results.The results show that compared with some single prediction models and other combined prediction models,the Prophet-EEMD-XGBoost model based on IOWA operator has better prediction effect.
Prophet algorithmextreme gradient boostinginduced ordered weighted average operator
NETL
NSTL
万方数据
