Radiative transfer simulations and remote sensing studies fundamentally require accurate and efficient computation of the optical properties of non-spherical particles. This paper proposes a deep learning (DL) scheme in conjunction with an optical property database to achieve this goal. Deep neural network (DNN) architectures were obtained from a dataset of the optical properties of super-spheroids with extensive shape parameters, size parameters, and refractive indices. The dataset was computed through the invariant imbedding T-matrix method. Four separate DNN architectures were created to compute the extinction efficiency factor, single-scattering albedo, asymmetry factor, and phase matrix. The criterion for designing these neural networks was the achievement of the highest prediction accuracy with minimal DNN parameters. The numerical results demonstrate that the determination coefficients are greater than 0.999 between the prediction values from the neural networks and the truth values from the database, which indicates that the DNN can reproduce the optical properties in the dataset with high accuracy. In addition, the DNN model can robustly predict the optical properties of particles with high accuracy for shape parameters or refractive indices that are unavailable in the database. Importantly, the ratio of the database size (∼127 GB) to that of the DNN parameters (∼20 MB) is approximately 6810, implying that the DNN model can be treated as a highly compressed database that can be used as an alternative to the original database for real-time computing of the optical properties of non-spherical particles in radiative transfer and atmospheric models.
In atmospheric aerosol remote sensing and data assimilation studies, the Jacobians of the optical properties of non-spherical aerosol particles are required. Specifically, the partial derivatives of the extinction efficiency factor, single-scattering albedo, asymmetry factor, and scattering matrix should be obtained with respect to microphysical parameters, such as complex refractive indices, shape parameters and size parameters. When a look-up table (LUT) of optical properties of particles is available, the Jacobians traditionally can be calculated using the finite difference method (FDM), but the accuracy of the process depends on the resolution of microphysical parameters. In this paper, a deep learning scheme was proposed for computing Jacobians of the optical properties of super-spheroids, which is a flexible model of non-spherical atmospheric particles. Using the neural networks (NN), the error of the Jacobians in the FDM can be reduced by more than 60%, and the error reduction rate of the Jacobians of the scattering matrix elements can be more than 90%. We also tested the efficiency of the NN for computing the Jacobians. The computation takes 30 seconds for one million samples on a host with an NVIDIA GeForce RTX 3070 GPU. The accuracy and efficiency of the present NN scheme proves it is promising for applications in remote sensing and data assimilation studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.