A NEW ALGORITHM FOR THE AOD INVERSION FROM NOAA/AVHRR DATA

This study developed a space-time Light Gradient Boosting Machine (STLG) model to derive the high-temporal-resolution (1 h) and high-quality PM_2.5 dataset in China (i.e., ChinaHighPM_2.5) at a 5 km spatial resolution from the Himawari-8 Advanced Himawari Imager aerosol products. Our model outperforms most previous related studies with a much lower computation burden in terms of speed and memory, making it most suitable for real-time air pollution monitoring in China.

This study introduced an enhanced space–time extremely randomized trees (STET) approach to improve the 1 km resolution ground-level PM_2.5 estimates across China using the remote sensing technology. The STET model shows high accuracy and strong predictive power and appears to outperform most models reported by previous studies. Thus, it is of great importance for future air pollution studies at medium- or small-scale areas and will be applied to generate the historical PM_2.5 dataset across China.

This study evaluates the suitability of 11 satellite-derived aerosol products in describing the spatio-temporal variations over the world. Our results show similar global patterns among these products but noticeable spatial heterogeneity and numerical differences over land regions. In general, MODIS products perform best at reflecting the spatial distributions and capturing the temporal trends of aerosol. This study help readers select a suitable aerosol dataset for their studies.