High Spatial Resolution Nighttime PM2.5 Datasets in the Beijing–Tianjin–Hebei Region from 2015 to 2021 Using VIIRS/DNB and Deep Learning Model

Abstract

The concentration of particulate matter (PM2.5) can be estimated using satellite data collected during the daytime. However, there are currently no long-term evening PM2.5 datasets, and the application of low-light satellite data to analyze nighttime PM2.5 concentrations is limited. The Visible Infrared Imaging Radiometer Suite Day/Night Band (VIIRS/DNB), meteorology, Digital Elevation Model, moon phase angle, and Normalized Digital Vegetation Index were used in this study to develop a Deep Neural Network model (DNN) for estimating the nighttime concentrations of PM2.5 in the Beijing–Tianjin–Hebei (BTH) region from 2015 to 2021. To evaluate the model’s performance from 2015 to 2021, a ten-fold cross-validation coefficient of determination was utilized (CV − R2 = 0.51 − 0.68). Using a high spatial resolution of 500 m, we successfully generated a PM2.5 concentration map for the BTH region. This finer resolution enabled a detailed representation of the PM2.5 distribution over the area. Interannual and seasonal trends in nighttime PM2.5 concentrations were analyzed. Winter had the highest seasonal spatial PM2.5, followed by spring and autumn, whereas summer had the lowest. The annual concentration of PM2.5 at night steadily decreased. Finally, the estimation of nighttime PM2.5 was applied in scenarios such as continuous day–night changes, rapid short-term changes, and single-point monitoring. A deeper understanding of PM2.5, enabled by nightly PM2.5, will serve as an invaluable resource for future research.