Spatiotemporal neural network for estimating surface NO concentrations over north China and their human health impact.

Atmospheric nitrogen dioxide (NO) is an important reactive gas pollutant harmful to human health. The spatiotemporal coverage provided by traditional NO monitoring methods is insufficient, especially in the suburban and rural areas of north China, which have a high population density and experience severe air pollution. In this study, we implemented a spatiotemporal neural network (STNN) model to estimate surface NO from multiple sources of information, which included satellite and in situ measurements as well as meteorological and geographical data. The STNN predicted NO with high accuracy, with a coefficient of determination (R) of 0.89 and a root mean squared error of 5.8 μg/m for sample-based 10-fold cross-validation. Based on the surface NO concentration determined by the STNN, we analyzed the spatial distribution and temporal trends of NO pollution in north China. We found substantial drops in surface NO concentrations ranging between 9.1% and 33.2% for large cities during the 2020 COVID-19 lockdown when compared to those in 2019. Moreover, we estimated the all-cause deaths attributed to NO exposure at a high spatial resolution of about 1 km, with totals of 6082, 4200, and 18,210 for Beijing, Tianjin, and Hebei Provinces in 2020, respectively. We observed remarkable regional differences in the health impacts due to NO among urban, suburban, and rural areas. Generally, the STNN model could incorporate spatiotemporal neighboring information and infer surface NO concentration with full coverage and high accuracy. Compared with machine learning regression techniques, STNN can effectively avoid model overfitting and simultaneously consider both spatial and temporal correlations of input variables using deep convolutional networks with residual blocks. The use of the proposed STNN model, as well as the surface NO dataset, can benefit air quality monitoring, forecasting, and health burden assessments.