High-Resolution Daily Spatiotemporal Distribution and Evaluation of Ground-Level Nitrogen Dioxide Concentration in the Beijing–Tianjin–Hebei Region Based on TROPOMI Data

This study utilized TROPOMI remote sensing data, MODIS ground observation and other ancillary data to construct a high-resolution spatiotemporal distribution evaluation of ground-level NO2 concentrations in the Beijing–Tianjin–Hebei (BTH) region using Geographic Temporal Neural Network Weighted Regression (GTNNWR) model. Through this model, we obtained daily nitrogen dioxide (NO2) at resolution 500 m for period 2019–2022. The research results exhibited higher accuracy more detailed features compared models, enabling accurate reflection spatial temporal variations region, while retaining details trends excluding influence noisy data. Furthermore, conducted an analysis considering important events such as public health incidents Winter Olympics. demonstrated that GTNNWR model outperformed Random Forest (RF), Convolutional (CNN), (GNNWR) models performance metrics R2, RMSE, MAE, MAPE, showcasing greater reliability when heterogeneity non-stationarity. provides crucial support reference atmospheric environmental management pollution prevention control region.