Characterization of temporal PM2.5, nitrate, and sulfate using deep learning techniques

Abstract Water-soluble inorganic salts (WIS) contribute a large fraction of PM2.5, which are responsible for the adverse effects on human health and environment. It is important to investigate the long-term variation trend of PM2.5 and WIS for exposure assessment and effective abatement strategies development. In this study, a multi-step ahead artificial neural network (MSA-ANN) and a long short-term memory fully connected (LSTM-FC) model for PM2.5, nitrate (NO3−), and sulfate (SO42−) prediction were developed to provide high temporal resolution datasets. Results show that the kinetic formation rate of HNO3 and HSO3− used as input variables can improve the accuracy of the present model for PM2.5, NO3−, and SO42− prediction. The MSA-ANN is able to predict 80–83%, 93%, and 91% of PM2.5, NO3−, and SO42−, respectively, with t+1 prediction horizon. With increasing prediction horizon to t+4 and t+8, the present model still can track the temporal variation of PM2.5, NO3−, and SO42− very well and capture the peak values during a severe pollution event. The proposed method is applicable to predict regional temporal variation trend of PM2.5, NO3−, and SO42− and fill the data gap in area with limited WIS measurement.