# Hybrid equivalent circuit-deep neural network design of optically transparent metasurface with microwave RCS reduction

## TL;DR

A new design method combines physics and AI to create transparent, flexible metasurfaces that reduce radar visibility while allowing light to pass through.

## Contribution

A physics-guided intelligent design approach integrating circuit analog optimization with deep neural networks for metasurface design.

## Key findings

- The metasurface achieves wideband RCS reduction from 8.9 to 37.2 GHz with 123% fractional bandwidth.
- The fabricated metasurface has approximately 75% visible transmittance and excellent angular stability.
- The design method enables flexible and optically transparent metasurfaces suitable for stealth and solar-powered applications.

## Abstract

Metasurface-based ultra-wideband radar cross-section (RCS) reduction techniques that offer flexibility and optical transparency are strategically important for electromagnetic protection. Although many methods, including machine learning techniques, have been developed to design complex metasurfaces, they typically require prior knowledge and extensive computational resources. Herein, we propose a physics-guided intelligent design approach to develop flexible optically transparent metasurfaces, which integrates the circuit analog optimization method (CAOM) with a deep neural network (DNN). As a proof-of-concept, a flexible, optically transparent metasurface for ultra-wideband RCS reduction was designed, fabricated, and experimentally characterized. The experimental results align closely with the simulations, demonstrating excellent flexibility and wide-angle RCS reduction from 8.9 to 37.2 GHz (123% fractional bandwidth). The metasurfaces exhibit excellent optical transparency with a visible transmittance of approximately 75%. The proposed metasurface shows great potential for integration into the window glass of stealth aircraft and warships, as well as solar-powered vehicles.

•Physics-guided intelligent design combining circuit-analog optimization with DNN proposed•Flexible and optically transparent metasurface developed for ultra-wideband RCS reduction•Achieves ≤−10 dB mono/bistatic RCS reduction across 8.9–37.2 GHz (123% bandwidth)Fabricated sample exhibits ∼75% visible transmittance and excellent angular stability

Physics-guided intelligent design combining circuit-analog optimization with DNN proposed

Flexible and optically transparent metasurface developed for ultra-wideband RCS reduction

Achieves ≤−10 dB mono/bistatic RCS reduction across 8.9–37.2 GHz (123% bandwidth)

Fabricated sample exhibits ∼75% visible transmittance and excellent angular stability

Physics; Applied sciences; Devices