Aerosol Fine-Mode-Fraction Retrieval from GEO-KOMPSAT-2A/AMI using a Deep Neural Network and Spectral Deconvolution Algorithm

Aerosol size information is important to the understanding of aerosol dynamics, which change rapidly over Asia, with size retrieval from geostationary satellite observations being vital. In this study, a deep neural network model was trained using Advanced Meteorological Imager (AMI) level 1b observations, AMI aerosol products, and observation geometries to retrieve the aerosol optical depth (AOD), Ångström exponent (AE), and spectral derivatives of AE (AE′). The fine-mode fraction (FMF) was calculated with a spectral deconvolution algorithm using retrieved AE and AE′ when AOD > 0.2. The retrieved aerosol products were validated using AERONET (AOD at 550 nm: R = 0.829, RMSE = 0.241, MBE = –0.053; AE: R = 0.723; RMSE = 0.235; MBE = 0.005; FMF: R = 0.814; RMSE = 0.083; MBE = 0.011). Case studies of dust-transport and wildfire events in Asia revealed that the retrieved aerosol size products may be used for analysis of sudden pollution events. Monthly average FMF values in Asia were consistent with previous studies, confirming that the retrieved FMF is useful for seasonal aerosol property analysis. Results of this study indicate the potential for comprehensive analysis of aerosol properties in Asia using continuous aerosol size data from geostationary Earth orbit satellite observations.