Abstract: Artificially structured materials are created artificially and offer customizable properties. They are being used in various fields. A system and method for designing artificially structured materials have been provided. The system and method is based on neural networks for approximating the electromagnetic (EM) responses of the artificially structured materials. By treating the EM spectral data as time-varying sequences and the inverse problem as a single-input, multi-output model, the architecture is forced to learn the geometry of the designs from the training data as opposed to abstract features thereby addressing both the forward and the inverse design problems.

Abstract: Conventionally, design methodologies employed deep learning model based on physics which considers only real (permittivity) term and ignores the imaginary (conductivity) term in complex loss function which fail to help in design of complex structures and limit their applications to scenarios such as array of metamaterial structures. Present application provides systems and method implement apply a Physics-Informed Neural Network (PINN) for inversely calculating the effective material parameters of a multi-dimensional metamaterial from its scattered field(s). By employing a loss function based on the Helmholtz wave equation, performance of a metamaterial is modeled by the system the dependance of resonant behavior on the homogenized electric permittivity distribution profile generated by the PINN is demonstrated.

Abstract: Artificially structured materials are created artificially and offer customizable properties. They are being used in various fields. A system and method for designing artificially structured materials have been provided. The system and method is based on neural networks for approximating the electromagnetic (EM) responses of the artificially structured materials. By treating the EM spectral data as time-varying sequences and the inverse problem as a single-input, multi-output model, the architecture is forced to learn the geometry of the designs from the training data as opposed to abstract features thereby addressing both the forward and the inverse design problems.