Collaborative Neural Networks significantly Improve Global Aerosol Retrievals From Multi-Angle Polarimeters

Abstract

We present the RemoTAP-Hybrid algorithm for global aerosol products retrieved from Multi-Angle Polarimeters (MAP), and apply it to one-year aerosol retrievals from the SPEXone MAP instrument. For the first time, Multiple Collaborated Neural Networks (MCNN) are used to perform global aerosol MAP retrievals over land and ocean. The combined use of MCNN with a full physics inversion in RemoTAP-Hybrid, significantly improves accuracy and computational speed of SPEXone aerosol retrievals. We validate the retrieved Aerosol Optical Depth (AOD), Angstrom Exponent (AE), Single Scattering Albedo (SSA), Absorption AOD (AAOD), Fine mode AOD (FAOD), Coarse mode AOD (CAOD), and fine mode effective radius (reff_fine) with AERONET data. The validation suggests that aerosol retrievals can be further improved when extending the aerosol description to include a fine non-spherical mode. For AOD, the Root-Mean-Square Error (RMSE) is 0.051 (0.037) over land (ocean), while 78.3% (80.8%) of the retrievals are within the requirement formulated by the Global Climate Observing System (GCOS). The RMSE is 0.186 (0.207) for AE, 0.038 (0.044) for SSA, 0.023 (0.014) for AAOD, 0.047 (0.031) for FAOD, 0.043 (0.027) for CAOD, and 0.021 (0.026) for reff_fine over land (ocean). Compared to the current RemoTAP algorithm, RemoTAP-Hybrid shows improved agreement with AERONET for AOD, AE, and FAOD over land and ocean while the number of valid retrievals is increased by 4% (3%) over land (ocean) and the computational time is reduced by 43% (32%). Finally, we present the first global seasonal maps of aerosol optical and microphysical properties and chemical composition from SPEXone.