Abstract. Three-dimensional (3D) radiative transfer effects are a major source of retrieval errors in satellite-based optical re- mote sensing of clouds. In this study, we present two retrieval methods based on deep learning. We use deep neural networks (DNNs) to retrieve multipixel estimates of cloud optical thickness and column-mean cloud droplet effective radius simultane- ously from multispectral, multipixel radiances. Cloud field data are obtained from large-eddy simulations, and a 3D radiative transfer model is employed to simulate upward radiances from clouds. The cloud and radiance data are used to train and test the DNNs. The proposed DNN-based retrieval is shown to be more accurate than the existing look-up table approach that assumes plane-parallel, homogeneous clouds. By using convolutional layers, the DNN method estimates cloud properties robustly, even for optically thick clouds, and can correct the 3D radiative transfer effects that would otherwise affect the radiance values.
Three-dimensional non-LTE radiative transfer effects in Fe i lines