A Combined Machine-Learning/Optimization-Based Approach for Inverse Design of Nonuniform Bianisotropic Metasurfaces

Electromagnetic metasurface (EMMS) design based on far-field (FF) constraints without the complete knowledge of the fields on both sides of the metasurface is typically a time-consuming and iterative process, which relies heavily on heuristics and ad hoc methods. This article proposes an end-to-end systematic and efficient approach where the designer inputs high-level FF constraints, such as nulls, sidelobe levels, and main beam level(s), and a three-layer nonuniform passive, lossless, and omega-type bianisotropic EMMS design to satisfy them is returned. The surface parameters to realize the FF criteria are found using the alternating direction method of multipliers on a homogenized model derived from the method of moments (MoM). This model incorporates edge effects of the finite surface and intercell mutual coupling in the inhomogeneous impedance sheet. Optimization through the physical unit cell space integrated with machine-learning-based surrogate models is used to realize the desired surface parameters from physical meta-atom (or unit cell) designs. Two passive lossless examples with different feeding systems and FF constraints are shown to demonstrate the effectiveness of this method.

Automated summary

This article proposes an efficient approach for the design of electromagnetic metasurfaces based on far-field constraints. The approach allows the designer to input high-level constraints and returns a design that satisfies these constraints. The method utilizes optimization and machine-learning techniques to determine the required surface parameters. Two examples are provided to demonstrate the effectiveness of the approach.