Spatial-temporal characterization of air pollutants using a hybrid deep learning/Kriging model incorporated with a weather normalization technique

A scarce distribution of the PM 2.5 chemical compositions monitors reduces the applicability of scientific information for policymakers to assess the effectiveness of air pollution control strategies. There is an urgent need for a spatial-temporal prediction model for characterizing PM 2.5 chemical compositions to assess exposure risks and develop effective air pollutants reduction strategies. In this study, the spatial-temporal variations of NO 3 − and SO 4 2− were characterized using a hybrid multi-step ahead neural network (MSA-NN)/Kriging model in the urban areas with limited PM 2.5 constituents monitoring stations. A meteorological normalization technique was further applied to develop a de-weather model to investigate temporal variations of air pollutants during the level 3 COVID-19 alert in central Taiwan. The MSA-NN algorithm could predict 94% and 91% of NO 3 − and SO 4 2− , respectively, at the t+1-time horizon predictions. Based on the predicted results using the present de-weather model, the reduction in primary emissions attributed to the impact of COVID-19 during the level 3 alert was found to dominate the temporal air pollutant concentrations in central Taiwan. The present model could provide applicable and accurate high resolution of spatial-temporal NO 3 − and SO 4 2− datasets in an area with limited PM 2.5 chemical composition measurement. The present model could also be potentially applied to facilitate hotspot identification and human exposure assessment. The present Artificial Neural Network-based de-weather model is applicable to predict meteorological normalized time series air pollutant concentrations, which could be used to verify the effects of the meteorological parameters and primary emissions on the variations in air quality during the implementation of a specific air quality control strategy or changes in anthropogenic activities. • The hybrid MSA-NN/Kriging model is applicable to characterize spatial-temporal NO 3 − and SO 4 2− . • The present model can accurately track the NO 3 − and SO 4 2− concentrations over next 8 h. • The ANN-based de-weather model predicts the impact of the primary emissions on air pollutant concentrations. • The primary emissions dominated the variations of air pollutant concentrations in central Taiwan during the pandemic of COVID-19. • A reduction in NO 3 − concentration during the COVID-19 pandemic was attributed to a reduction of traffic volume.