An enhanced hybrid ensemble deep learning approach for forecasting daily PM2.5

PM2.5 forecasting technology can provide a scientific and effective way to assist environmental governance and protect public health. To forecast PM2.5, an enhanced hybrid ensemble deep learning model is proposed in this research. The whole framework of the proposed model can be generalized as follows: the original PM2.5 series is decomposed into 8 sub-series with different frequency characteristics by variational mode decomposition (VMD); the long short-term memory (LSTM) network, echo state network (ESN), and temporal convolutional network (TCN) are applied for parallel forecasting for 8 different frequency PM2.5 sub-series; the gradient boosting decision tree (GBDT) is applied to assemble and reconstruct the forecasting results of LSTM, ESN and TCN. By comparing the forecasting data of the models over 3 PM2.5 series collected from Shenyang, Changsha and Shenzhen, the conclusions can be drawn that GBDT is a more effective method to integrate the forecasting result than traditional heuristic algorithms; MAE values of the proposed model on 3 PM2.5 series are 1.587, 1.718 and 1.327 mu g/m(3), respectively and the proposed model achieves more accurate results for all experiments than sixteen alternative forecasting models which contain three state-of-the-art models.