Constrained tandem neural network assisted inverse design of metasurfaces for microwave absorption

TL;DR

This paper introduces a constrained tandem neural network approach for the inverse design of multilayered metasurfaces, enabling efficient customization of microwave absorbers with optimized spectra and physical attributes without expert knowledge.

Contribution

The work presents a novel inverse design method using a constrained tandem neural network for metasurfaces, allowing for optimized microwave absorber design considering physical constraints.

Findings

Successfully designed broadband microwave absorbers with near-causality-limit thickness

The neural network efficiently predicts structural parameters for desired spectra

The method reduces design time and computational cost

Abstract

Designing microwave absorbers with customized spectrums is an attractive topic in both scientific and engineering communities. However, due to the massive number of design parameters involved, the design process is typically time-consuming and computationally expensive. To address this challenge, machine learning has emerged as a powerful tool for optimizing design parameters. In this work, we present an analytical model for an absorber composed of a multi-layered metasurface and propose a novel inverse design method based on a constrained tandem neural network. The network can provide structural and material parameters optimized for a given absorption spectrum, without requiring professional knowledge. Furthermore, additional physical attributes, such as absorber thickness, can be optimized when soft constraints are applied. As an illustrative example, we use the neural network to design broadband microwave absorbers with a thickness close to the causality limit imposed by the Kramers-Kronig relation. Our approach provides new insights into the reverse engineering of physical devices.