Presentation
5 October 2023 Experimental demonstration of deep learning enabled ultra-broadband epsilon-near-zero perfect absorbers
Author Affiliations +
Abstract
The design of multilayer ENZ stacks is challenging due to the many parameters involved, including the number of layers, thicknesses, ENZ wavelength, and optical losses. Our machine learning-based approach enables us to efficiently search through the vast design space and experimentally verify the performance of the resulting thin film stack. The resulting 2-layered AZO ENZ thin film stack achieved perfect absorption of light (> 95%) in the near-infrared region from 1500 nm to 2500 nm, highlighting the potential of machine learning techniques in designing ENZ materials for a range of applications.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
David Dang, Sudip J. Gurung, Juan Manuel Raffo Calixto, Xuguo Zhou, Aleksei Anopchenko, and Howard Lee "Experimental demonstration of deep learning enabled ultra-broadband epsilon-near-zero perfect absorbers", Proc. SPIE PC12648, Plasmonics: Design, Materials, Fabrication, Characterization, and Applications XXI, PC1264807 (5 October 2023); https://doi.org/10.1117/12.2678517
Advertisement
Advertisement
KEYWORDS
Deep learning

Design and modelling

Light absorption

Thin films

Film thickness

Multilayers

Optical communications

RELATED CONTENT


Back to Top