Assembling Reconfigurable Intelligent Metasurfaces With a Synthetic Neural Network
- 7 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 72 (6) , 5252-5260
Abstract
Reconfigurable metasurfaces have provided us with extraordinary ways to manipulate electromagnetic waves at sub-wavelength scale and taught us how to implement various tasks in a wide range. As its next generation, intelligent metasurfaces have recently attracted much attention as they are endowed with intelligence to self-adapt to ever-changing environment. So far, although there are a number of works about the creation of deep learning algorithms to drive intelligent metasurfaces, they are mostly about fixed objects and thus constrained by specific applications. In this work, we propose a synthetic neural network to break the limit that conventional inverse design algorithms only work for certain metasurface configuration. The dynamic assembly of reconfigurable metasurfaces in physical space is directly mapped to the network recombination in algorithm space. This is particularly useful because it can greatly save training data and avoid repeated training of network. We apply it in the inverse design of metasurfaces with the relative error less than 13%, and experimentally demonstrate reconfigurable microwave metasurfaces with flexible deployment. Our work opens up a promising avenue for overcoming the application-bound limitations of conventional inverse designs, particularly in the dynamic and adaptive context of intelligent metasurfaces.Keywords
Funding Information
- National Natural Science Foundation of China (11961141010, 61625502, 61975176, 62027805, 62071423, 62071424, 62101485)
- Top-Notch Young Talents Program of China
- Fundamental Research Funds for the Central Universities
This publication has 46 references indexed in Scilit:
- Arbitrary Polarization Readout with Dual‐Channel Neuro‐MetasurfacesAdvanced Science, 2022
- Heterogeneous Transfer‐Learning‐Enabled Diverse Metasurface DesignAdvanced Optical Materials, 2022
- Programmable Controlling of Multiple Spatial Harmonics via a Nonlinearly Phased Grating MetasurfaceAdvanced Functional Materials, 2022
- Pushing the Limits of Functionality‐Multiplexing Capability in Metasurface Design Based on Statistical Machine LearningAdvanced Materials, 2022
- Independent Manipulation of Reflection Amplitude and Phase by a Single‐Layer Reconfigurable MetasurfaceAdvanced Optical Materials, 2021
- Demonstration of Spider‐Eyes‐Like Intelligent Antennas for Dynamically Perceiving Incoming WavesAdvanced Intelligent Systems, 2021
- Deep Learning the Electromagnetic Properties of Metamaterials—A Comprehensive ReviewAdvanced Functional Materials, 2021
- Tackling Photonic Inverse Design with Machine LearningAdvanced Science, 2021
- Multistate Switching of Photonic Angular Momentum Coupling in Phase‐Change MetadevicesAdvanced Materials, 2020
- Deep Learning: A Rapid and Efficient Route to Automatic Metasurface DesignAdvanced Science, 2019