Deep-Learning-Equipped Iterative Solution of Electromagnetic Scattering From Dielectric Objects

Deep-learning (DL)-equipped iterators are developed to accelerate the iterative solution of electromagnetic scattering problems. In proposed iterators, DL blocks consisting of U-nets are employed to replace the nonlinear process of the traditional iterators, i.e., the conjugate gradient (CG) method and the generalized minimal residual (GMRES) method. New implementations of the complex-valued batch normalization in the U-net are proposed and investigated in terms of the DL-equipped iterators. Numerical results show that the DL-equipped iterators outperform their traditional counterparts in terms of computational time under comparable accuracy since the phase information of the currents, fields, and permittivity is properly handled.

Automated summary

DL-equipped iterators are developed to accelerate the iterative solution of electromagnetic scattering problems. DL blocks consisting of U-nets are employed to replace the nonlinear process of traditional iterators. The proposed complex-valued batch normalization in the U-net improves the computational time and accuracy of the DL-equipped iterators by properly handling phase information.