Above Cloud Aerosol Detection and Retrieval from Multi-Angular Polarimetric Satellite Measurements in a Neural Network Ensemble Approach

Abstract. This paper describes an algorithm for above-cloud aerosol (ACA) retrievals from PARASOL (Polarisation and Anisotropy of Reflectances for Atmospheric Science coupled with Observations from a Lidar) Multi-Angle Polarimetric measurements. The algorithm, based on neural networks (NNs), has been trained on synthetic measurements and has been applied to the processing of one-year PARASOL data. The algorithm makes use of three subsequent NNs: 1) for the detection of liquid clouds, 2) for the retrieval of aerosol properties for ACA cases, and 3) an NN forward model to evaluate the goodness-of-fit of the retrieval. The NN's theoretical capability of retrieval is investigated by several synthetic data studies. It is shown that the NN is able to retrieve ACAOT (above cloud aerosol optical depth), AE (Angstrom exponent), and SSA (single scattering albedo) yielding an RMSE (root mean squared error) of ~0.1 on ACAOT, ~0.4 on AE and ~0.04 on SSA in synthetic experiments. Finally, comparison between the NN retrievals and adjacent PARASOL-RemoTAP clear sky retrieval in 2008 shows good agreement within the range that is expected from the synthetic study.