Aerosol Absorption Over Land Derived From the Ultra-Violet Aerosol Index by Deep Learning

Abstract

Quantitative measurements of aerosol absorptive properties, e.g., the absorbing aerosol optical depth (AAOD) and the single scattering albedo (SSA), are important to reduce uncertainties of aerosol climate radiative forcing assessments. Currently, global retrievals of AAOD and SSA are mainly provided by the ground-based aerosol robotic network (AERONET), whereas it is still challenging to retrieve them from space. However, we found the AERONET AAOD has a relatively strong correlation with the satellite retrieved ultra-violet aerosol index (UVAI). Based on this, a numerical relation is built by a deep neural network (DNN) to predict global AAOD and SSA over land from the long-term UVAI record (2006–2019) provided by the ozone monitoring instrument (OMI) onboard Aura. The DNN predicted aerosol absorption is satisfying for samples with AOD at 550 nm larger than 0.1, and the DNN model performance is better for smaller absorbing aerosols (e.g., smoke) than larger ones (e.g., mineral dust). The comparison of the DNN predictions with AERONET shows a high correlation coefficient of 0.90 and a root mean square of 0.005 for the AAOD, and over 80% of samples are within the expected uncertainty of AERONET SSA ($\pm$0.03).

Keywords

• Absorbing aerosol optical depth (AAOD)
• deep neural network (DDN)
• machine learning
• ozone monitoring instrument (OMI)
• single scattering albedo (SSA)
• ultra-violet aerosol index (UVAI)