Deep Sequence Learning for Prediction of Daily NO2 Concentration in Coastal Cities of Northern China

Nitrogen dioxide (NO2) is an important precursor of atmospheric aerosol. Forecasting urban NO2 concentration is vital for effective control of air pollution. This paper proposes a hybrid deep learning model for predicting daily average NO2 concentrations on the next day, based on atmospheric pollutants, meteorological data, and historical data during 2014 to 2020 in five coastal cities of Shandong peninsula, northern China. A random Forest (RF) algorithm was used to select input variables to reduce data dimensionality trained by the sequence to sequence (Seq2Seq) the model and describe how the Seq2Seq model understands each predictor variable. The hybrid model combining an RF with Seq2Seq network (RF-S2S) was evaluated and achieved a Pearson's correlation coefficient of 0.93, a Nash-Sutcliffe coefficient (NS) of 0.79, a Root Mean Square Error (RMSE) of 5.85 mu g/m(3), a Mean Absolute Error (MAE) of 4.50 mu g/m(3), and a Mean Absolute Percentage Error (MAPE) of 20.86%. Feature selection by an RF model improves the performance of the Seq2Seq model, reducing errors by 19.7% (RMSE), 20.3% (MAE), and 29.3% (MAPE), respectively. Carbon monoxide (CO) and PM10 are two common, important features influencing the prediction of NO2 concentrations in coastal areas of northern China. The results of RF-S2S models can capture general trends and disruptions more accurately than can long-short term memory (LSTM) models with and without feature selection. The decreasing tendency of NO2 from 2014 to 2020 illustrated by the empirical mode decomposition (EMD) method is one important obstacle to improving the RF-S2S prediction accuracy. An EMD-based RF-S2S model could help to perform the short-term forecast of NO2 concentrations efficiently.