Seamless hourly PM2.5 mapping across China with a graph spatiotemporal deep neural network

Key Points

• Accurate mapping of PM2.5 levels allows for timely air quality information, enhancing public awareness.
• The analysis achieved notable performance in predicting air pollution levels across various regions in China.
• Using a deep neural network model—specifically for spatiotemporal mapping—improves resolution compared to traditional methods.
• Highlighting the potential for real-time air quality monitoring, this approach can inform environmental policies.