Cooperative simultaneous inversion of satellite-based real-time PM and ozone levels using an improved deep learning model with attention mechanism.

Ground-level fine particulate matter (PM) and ozone (O) are air pollutants that can pose severe health risks. Surface PM and O concentrations can be monitored from satellites, but most retrieval methods retrieve PM or O separately and disregard the shared information between the two air pollutants, for example due to common emission sources. Using surface observations across China spanning 2014-2021, we found a strong relationship between PM and O with distinct spatiotemporal characteristics. Thus, in this study, we propose a new deep learning model called the Simultaneous Ozone and PM inversion deep neural Network (SOPiNet), which allows for daily real-time monitoring and full coverage of PM and O simultaneously at a spatial resolution of 5 km. SOPiNet employs the multi-head attention mechanism to better capture the temporal variations in PM and O based on previous days' conditions. Applying SOPiNet to MODIS data over China in 2022, using 2019-2021 to construct the network, we found that simultaneous retrievals of PM and O improved the performance compared with retrieving them independently: the temporal R increased from 0.66 to 0.72 for PM, and from 0.79 to 0.82 for O. The results suggest that near-real time satellite-based air quality monitoring can be improved by simultaneous retrieval of different but related pollutants. The codes of SOPiNet and its user guide are freely available online at https://github.com/RegiusQuant/ESIDLM.