A novel hybrid decomposition-and-ensemble model based on CEEMD and GWO for short-term PM_2.5 concentration forecasting

To enhance prediction reliability and accuracy, a hybrid model based on the promising principle of "decomposition and ensemble" and a recently proposed meta-heuristic called grey wolf optimizer (GWO) is introduced for daily PM_2.5 concentration forecasting. Compared with existing PM_2.5 forecasting methods, this proposed model has improved the prediction accuracy and hit rates of directional prediction. The proposed model involves three main steps, i.e., decomposing the original PM_2.5 series into several intrinsic mode functions (IMFs) via complementary ensemble empirical mode decomposition (CEEMD) for simplifying the complex data; individually predicting each IMF with support vector regression (SVR) optimized by GWO; integrating all predicted IMFs for the ensemble result as the final prediction by another SVR optimized by GWO. Seven benchmark models, including single artificial intelligence (AI) models, other decomposition-ensemble models with different decomposition methods and models with the same decomposition-ensemble method but optimized by different algorithms, are considered to verify the superiority of the proposed hybrid model. The empirical study indicates that the proposed hybrid decomposition-ensemble model is remarkably superior to all considered benchmark models for its higher prediction accuracy and hit rates of directional prediction.