An intelligent hybrid model for air pollutant concentrations forecasting: Case of Beijing in China

• Published in: Sustainable cities and society Vol. 47; p. 101471
• Main Authors: Liu, Hui, Wu, Haiping, Lv, Xinwei, Ren, Zhiren, Liu, Min, Li, Yanfei, Shi, Huipeng
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.05.2019
• Subjects: Air pollutant concentrations forecasting; Empirical wavelet transform; Multi-agent evolutionary genetic algorithm; Nonlinear auto regressive models with exogenous inputs; Time series; ANN; VARMA; NARX network; WRF; Air pollutant concentrations forecasting; SVM; Nonlinear auto regressive models with exogenous inputs; SVR; BP; MAEGA; MLP; Multi-agent evolutionary genetic algorithm; GA; ARMA; ANFIS; EMD; ADMM; TDL; EWT; IMF; ACF; NBFS; Time series; AERMOD; MAPE; RMSE; VMD; MAE; PACF; Empirical wavelet transform; ARIMA
• ISSN: 2210-6707; 2210-6715
• DOI: 10.1016/j.scs.2019.101471

[Display omitted] •A novel hybrid model is put forward for air pollutant concentrations advanced multi-step forecasting.•The EWT decomposition algorithm is employed to decompose the raw air pollutant series.•The MAEGA model is used to determine the value of two input delays in the NARX neural network.•The NARX neural networks are built for each decomposed sub-series.•The proposed novel model is compared with five other models to investigate its prediction performance. The forecasting of air pollutant concentrations is of great significance to protect the environment and guarantee the health of people. In the study, a novel hybrid model, namely EWT-MAEGA-NARX combining the EWT, MAEGA and NARX neural networks, is put forward for multi-step air pollutant concentrations forecasting. Four types of air pollutant containing PM2.5, SO2, NO2, and CO in Beijing, China are selected to verify the accuracy of the proposed model. To inspect the forecasting performance of the proposed model, some other models are chosen as the comparison models, which comprise of the VMD-MAEGA-NARX model, EWT-MAEGA-SVM model, MAEGA-NARX model, EWT-NARX model and EWT-ARIMA-NARX model. The experimental results show that: (1) The EWT-MAEGA-NARX model can achieve satisfactory predictions in air pollutant concentrations forecasting, whose MAE in 1-step forecasting of PM2.5, SO2, NO2, CO series are 0.1314 μ g/ m3, 0.0213 μ g/ m3, 0.0722 μ g/ m3, 0.0033 mg/ m3, respectively. (2) In the EWT-MAEGA-NARX model, the EWT is a good feature extractor and the parameter optimization process of MAEGA for the NARX neural network can obviously enhance the prediction performance of the model.