Retrieval of dust aerosol optical and microphysical properties from ground-based Sun-sky radiometer measurements in approximation of randomly oriented spheroids

Deserts currently covering more than one tenth of the land surface gradually spread out over more and more areas due to desertification. Mineral dust as one of the most widespread aerosol types plays increasingly important role in atmospheric processes. An accurate accounting for physical and chemical characteristics of desert dust, particles shape in particular, in methods for aerosol retrievals from remote sensing data, is needed. The neglect of dust particle non-sphericity may lead to errors in quantifying the aerosol radiative and regional climatic effects. Earlier we developed a software package Sun-Sky Measurements for Aerosol ReTrieval (SSMART) to retrieve aerosol optical and microphysical characteristics from spectral ground-based Sun and sky radiance measurements. The single scattering albedo and scattering phase function were retrieved in two ways: (i) directly from the almucantar measurement data without any assumptions about the shape of aerosol particles and (ii) through the calculation on the basis of the Mie theory using the retrieved particle size distribution function and complex refractive index. However, there is experimental evidence that in modeling the optical properties of desert dust, the effects of particle non-sphericity should be taken into consideration. In this paper, we propose an improved version of the SSMART algorithm, in which the inverse light scattering problem is solved using the model of a mixture of randomly oriented polydisperse spheroids. On the basis of closed numerical experiments, the accuracy of aerosol retrievals is investigated in error-free conditions and in the presence of measurement errors. The results of the algorithm applying to almucantar scans obtained at Dakar AERONET site during desert dust events in 2012 are discussed. The retrieved aerosol optical and microphysical characteristics are compared with those obtained by the AERONET inversion algorithm. (C) 2014 Elsevier Ltd. All rights reserved.