Oct 2026· Advanced Optical Materials· 0 citations· 41 references
TL;DR
A novel and highly precise design paradigm based on reversible deep learning (RDL), which employs a single, bidirectionally trainable neural network for rapid and accurate design of meta‐absorbers tailored to specific absorption spectra, facilitating the intelligent development of advanced optical metamaterials and metadevices.
Abstract
Optical meta‐absorbers are artificially engineered materials capable of trapping light in a highly controllable manner, rendering them attractive for a wide range of applications. Artificial intelligence provides powerful tools for the efficient design of such complex structures. Among current methods, tandem neural networks (TNNs) have emerged as a mainstream solution for forward‐inverse modeling. However, TNNs require two separate networks, leading to high computational costs and limited accuracy—particularly in inverse design. In this work, we propose a novel and highly precise design paradigm based on reversible deep learning (RDL), which employs a single, bidirectionally trainable neural network. The RDL framework performs simultaneous training of the inverse and forward models within a unified architecture—addressing structural generation and spectral prediction, and significantly reducing computational costs. As a proof of concept, we demonstrate the design of near‐infrared meta‐absorbers using RDL, achieving an order‐of‐magnitude improvement in inverse prediction accuracy compared to TNNs, while using only 66.35% of the training parameters and requiring minimal memory and storage. This study introduces a flexible and efficient platform for the rapid and accurate design of meta‐absorbers tailored to specific absorption spectra, facilitating the intelligent development of advanced optical metamaterials and metadevices.
Terahertz (THz) metasurface absorbers have attracted significant interest for wideband energy harvesting, electromagnetic stealth, and sensing applications. However, the design of ultra-wideband THz absorbers still relies heavily on empirical optimization and time-consuming full-wave simulations, particularly when high...
Pin Wen, Jin-Yu Liu, Kun Zhan et al.· IEEE Journal of Selected Top...· 0 citations
Metasurfaces are ultrathin optical elements that control light through carefully engineered structures smaller than the wavelength of light, enabling compact devices with functionalities that are difficult to achieve with conventional optics. However, exploiting their full design freedom over large areas has been prohi...
Deep learning has emerged as a potent methodology for the inverse design of metasurfaces; however, its deployment in complex optical systems is often hindered by substantial computational demands and the scarcity of comprehensive data sets, particularly when addressing diverse design requirements. To address these ch...
ABSTRACT Artificial intelligence is reshaping the discovery and engineering of photonic materials. Here, we introduce a data‐driven framework that employs a generative deep neural network to create ultrathin, multilayer epsilon‐near‐zero absorbers with record‐breaking broadband performance. Within this framework, the n...
David Dang, Meena Salib, Quynh Dang et al.· Advancement of science· 0 citations
Developing reliable inverse design networks for complex nanophotonic structures remains challenging due to limited training data, inherent spectral bias and “one-to-many degeneracy” problem. In this work, we propose a data-efficient tandem neural network (TNN) framework that integrates Fourier-feature encoding (FFE) wi...
J. Lee, Yong Soo Kim, Jincheol Kim et al.· IEEE Journal of Selected Top...· 0 citations
The inverse design of multilayer metamaterials —artificial structures with engineered electromagnetic, acoustic, thermal, or mechanical properties— represents a high-dimensional optimisation challenge that has driven the integration of deep learning into computational photonics and materials science. This paper present...
Federico Rodas, Laura Malache, Osmani Mujica Pérez· Revista Tecnológica - ESPOL· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.