Author Affiliations
Abstract
1 State Key Laboratory of Millimeter Waves, Southeast University, Nanjing, China
2 Institute of Electromagnetic Space, Southeast University, Nanjing, China
3 State Key Laboratory of Advanced Optical Communication Systems and Networks, Department of Electronics, Peking University, Beijing, China
Metamaterials and metasurfaces have inspired worldwide interest in the recent two decades due to their extraordinary performance in controlling material parameters and electromagnetic properties. However, most studies on metamaterials and metasurfaces are focused on manipulations of electromagnetic fields and waves, because of their analog natures. The concepts of digital coding and programmable metasurfaces proposed in 2014 have opened a new perspective to characterize and design metasurfaces in a digital way, and made it possible to control electromagnetic fields/waves and process digital information simultaneously, yielding the birth of a new direction of information metasurfaces. On the other hand, artificial intelligence (AI) has become more important in automatic designs of metasurfaces. In this review paper, we first show the intrinsic natures and advantages of information metasurfaces, including information operations, programmable and real-time control capabilities, and space–time-coding strategies. Then we introduce the recent advances in designing metasurfaces using AI technologies, and particularly discuss the close combinations of information metasurfaces and AI to generate intelligent metasurfaces. We present self-adaptively smart metasurfaces, AI-based intelligent imagers, microwave cameras, and programmable AI machines based on optical neural networks. Finally, we indicate the challenges, applications, and future directions of information and intelligent metasurfaces.
information metasurface artificial intelligence intelligent metasurface Photonics Insights
2022, 1(1): R01
Author Affiliations
Abstract
1 Shaanxi Key Laboratory of Artificially-Structured Functional Materials and Devices, Air Force Engineering University, Xi’an 710051, China
2 Institute of Electromagnetic Space, Southeast University, Nanjing 210096, China
3 State Key Laboratory of Millimeter Wave, Southeast University, Nanjing 210096, China
4 e-mail: wangjiafu1981@126.com
5 e-mail: 88jiangjinming@163.com
6 e-mail: tjcui@seu.edu.cn
7 e-mail: qushaobo@mail.xjtu.edu.cn
For camouflage applications, the performance requirements for metamaterials in different electromagnetic spectra are usually contradictory, which makes it difficult to develop satisfactory design schemes with multispectral compatibility. Fortunately, empowered by machine learning, metamaterial design is no longer limited to directly solving Maxwell’s equations. The design schemes and experiences of metamaterials can be analyzed, summarized, and learned by computers, which will significantly improve the design efficiency for the sake of practical engineering applications. Here, we resort to the machine learning to solve the multispectral compatibility problem of metamaterials and demonstrate the design of a new metafilm with multiple mechanisms that can realize small microwave scattering, low infrared emissivity, and visible transparency simultaneously using a multilayer backpropagation neural network. The rapid evolution of structural design is realized by establishing a mapping between spectral curves and structural parameters. By training the network with different materials, the designed network is more adaptable. Through simulations and experimental verifications, the designed architecture has good accuracy and robustness. This paper provides a facile method for fast designs of multispectral metafilms that can find wide applications in satellite solar panels, aircraft windows, and others.
Photonics Research
2022, 10(5): 05001146
1 东南大学电磁空间科学与技术研究院, 江苏 南京 210096
2 东南大学毫米波国家重点实验室, 江苏 南京 210096
3 北京大学先进光通信系统与网络国家重点实验室, 北京 100871
人工智能的发展已经给人类社会的发展带来了极大变革,各种基于人工智能的新应用层出不穷。电磁和光学超材料对电磁波有强大的调控能力,且具有灵活的设计特性,尤其是可编程超材料的实时数字化调控能力,有利于基于人工智能技术的电磁超材料的设计和智能化应用。对超材料的智能化设计、智能化结构和智能化系统进行了阐述,对于人工智能技术与电磁和光学超材料的结合,总结介绍了结构优化、架构设计和系统应用的主要进展和成果,并展望了智能超材料的未来发展方向。
光学仪器 人工智能 电磁超材料 光学超材料 信息超材料