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

TY - JOUR

T1 - Hybrid equivalent circuit-deep neural network design of optically transparent metasurface with microwave RCS reduction

AU - Si, Liming

AU - Ma, Tianyu

AU - Dong, Lin

AU - Niu, Rong

AU - Dang, Chenyang

AU - Bao, Xiue

AU - Zhu, Kaiqiang

AU - Sun, Houjun

AU - Zhu, Weiren

N1 - Publisher Copyright: © 2026 The Author(s)

PY - 2026/4/17

Y1 - 2026/4/17

N2 - 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.

AB - 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.

KW - applied sciences

KW - devices

KW - physics

UR - https://www.scopus.com/pages/publications/105033274419

U2 - 10.1016/j.isci.2026.115212

DO - 10.1016/j.isci.2026.115212

M3 - Article

AN - SCOPUS:105033274419

SN - 2589-0042

VL - 29

JO - iScience

JF - iScience

IS - 4

M1 - 115212

ER -