Neural Network AEROsol Retrieval for Geostationary Satellite (NNAeroG) Based on Temporal, Spatial and Spectral Measurements.

Geostationary satellites observe the earth surface and atmosphere with a short repeat
time, thus, providing aerosol parameters with high temporal resolution, which contributes to the air
quality monitoring. Due to the limited information content in satellite data, and the coupling between
the signals received from the surface and the atmosphere, the accurate retrieval of multiple aerosol
parameters over land is difficult. With the strategy of taking full advantage of satellite measurement
information, here we propose a neural network AEROsol retrieval framework for geostationary
satellite (NNAeroG), which can potentially be applied to different instruments to obtain various
aerosol parameters. NNAeroG was applied to the Advanced Himawari Imager on Himawari-8 and
the results were evaluated versus independent ground-based sun photometer reference data. The
aerosol optical depth, Ångström exponent and fine mode fraction produced by the NNAeroG method
are significantly better than the official JAXA aerosol products. With spectral bands selection, the use
of thermal infrared bands is meaningful for aerosol retrieval.