Identifying Contributors to PM2.5 Simulation Biases of Chemical Transport Model Using Fully Connected Neural Networks

Abstract

Abstract Accurate prediction of ambient PM2.5 concentrations using air quality models can provide governments with information for public health alerts. However, due to large uncertainties of input parameters and over‐simplification of the chemical mechanism, the model simulations tend to have a certain deviation from the observations. To provide an insight into the discrepancy and to explain the contributors to the model bias, we propose here a machine learning based method to identify the contributors to PM2.5 simulation biases. A fully connected deep neural network (noted as FCNN) was designed to correct the PM2.5 biases between the simulations from a common air quality model (i.e., Community Multiscale Air Quality, CMAQ) and observations with meteorological and pollutants variables. The FCNN was applied in two polluted regions in China including Beijing‐Tianjin‐Hebei (BTH) and Yangtze River Delta (YRD) in 2015, exhibiting excellent performance in reducing the root mean square error of annual PM2.5 by 46.6% and 37.2%, respectively. The relative contribution of each input feature for the bias correction was also estimated from the FCNN. Results suggest that the temperature and humidity exhibit the greatest contribution to the PM2.5 simulation bias among all meteorological factors, probably due to their high association with the physical and chemical reaction conditions. NO2 and SO2 concentrations and associated biases were also found to be crucial to CMAQ model accuracy, implying the importance of NO2‐ and SO2‐related reaction for PM2.5 formation. The study also revealed a cumulative effect of pollution and an enhancement effect of atmospheric oxidation on the formation of heavy pollution.

Keywords

• air quality model
• bias correction
• PM2.5
• neural networks
• contribution analysis
• China