… paper, a seasonal stacked autoencoder model combining seasonal analysis … deep feature
learning is proposed for forecasting the hourly PM 2.5 concentration, named DL-SSAE model. …

… deep learning model based on an auto-encoder and bidirectional long short-term memory
(Bi-LSTM) to forecast PM 2.5 concentrations … The model comprises several aspects, including …

… At the same time, we present the stacked autoencoder to encode the meteorological information
of … Zhang, “Hourly PM2.5 concentration forecast using stacked autoencoder model with …

… We will present the prediction accuracy using different predictors and we … forecasting skills
of the proposed stacked autoencoder-based method with existing monsoon prediction models…

… models to predict fine PM concentrations using long short-term memory (LSTM) and deep
autoencoder (DAE) methods, and compared the model … We applied the models to hourly air …

… deep recurrent neural networks solving the MTS forecasting problem. In this paper, we
introduce our previous model … the PM2.5 mass concentrations forecasting problem 44 . In this …

… In this paper, the FFNN, a typical and common-used forecasting model, is selected as the
regression model. The w l is utilized to initialize the weights w of the FFNN. It is noted that the …

… pollution-concentration spatial correlation prediction model based on a fusion deep neural
… As noted previously, the conventional stacked autoencoders discussed above are not used …

… Finally, an ELM algorithm establishes the relationship between the NOx emission concentration
and deep features. The experimental results on practical data indicate that the proposed …

… On another aspect, to validate the generalization performance of the prediction method
and the new forecasting model proposed in this study in other cities, three ground sites from …