• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

通过正向和逆向设计探索超表面结构中的人工智能。

Exploring AI in metasurface structures with forward and inverse design.

作者信息

Yang Guantai, Xiao Qingxiong, Zhang Zhilin, Yu Zhe, Wang Xiaoxu, Lu Qianbo

机构信息

Frontiers Science Center for Flexible Electronics (FSCFE) Institute of Flexible Electronics (IFE), Northwestern Polytechnical University, Xi'an 710072, China.

School of Automation, Northwestern Polytechnical University, 127 West Youyi Road, Beilin District, Xi'an 710072, China.

出版信息

iScience. 2025 Feb 15;28(3):111995. doi: 10.1016/j.isci.2025.111995. eCollection 2025 Mar 21.

DOI:10.1016/j.isci.2025.111995
PMID:40104054
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11914293/
Abstract

As an artificially manufactured planar device, a metasurface structure can produce unusual electromagnetic responses by harnessing four basic characteristics of the light wave. Traditional design processes rely on numerical algorithms combined with parameter optimization. However, such methods are often time-consuming and struggle to match actual responses. This paper aims to give a unique perspective to classify the artificial intelligence(AI)-enabled design, dividing it into forward and inverse designs according to the mapping relationship between variables and performance. Forward designs are driven by intelligent algorithms; neural networks are one of the principal ways to realize reverse design. This paper reviews recent progress in AI-enabled metasurface design, examining the principles, advantages, and potential applications. A rich content and detailed comparison can help build a holistic understanding of metasurface design. Moreover, the authors believe that this systematic and detailed review will pave the way for future research and the selection of practical applications.

摘要

作为一种人工制造的平面器件，超表面结构可以通过利用光波的四个基本特性产生异常的电磁响应。传统的设计过程依赖于结合参数优化的数值算法。然而，这些方法往往耗时且难以匹配实际响应。本文旨在从独特的视角对基于人工智能（AI）的设计进行分类，根据变量与性能之间的映射关系将其分为正向设计和逆向设计。正向设计由智能算法驱动；神经网络是实现逆向设计的主要方法之一。本文回顾了基于AI的超表面设计的最新进展，研究了其原理、优势和潜在应用。丰富的内容和详细的比较有助于建立对超表面设计的全面理解。此外，作者认为这种系统而详细的综述将为未来的研究和实际应用的选择铺平道路。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/a8ca108dcd2c/gr17.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/7bd6cf606ab2/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/bc9344bf29e7/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/403f61c6967d/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/52d5b23e6bc8/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/8920df02f5c9/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/3a1df820e20a/gr5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/50a54d189178/gr6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/24491691483d/gr7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/11bf9c4631d5/gr8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/b0476a1b22ae/gr9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/d8a0286ebce6/gr10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/d7da9dfd9ed3/gr11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/6ed91eaa9428/gr12.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/f153d8656567/gr13.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/143a6a7afe45/gr14.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/8d98711fd98c/gr15.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/8e717bb813be/gr16.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/a8ca108dcd2c/gr17.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/7bd6cf606ab2/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/bc9344bf29e7/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/403f61c6967d/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/52d5b23e6bc8/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/8920df02f5c9/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/3a1df820e20a/gr5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/50a54d189178/gr6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/24491691483d/gr7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/11bf9c4631d5/gr8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/b0476a1b22ae/gr9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/d8a0286ebce6/gr10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/d7da9dfd9ed3/gr11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/6ed91eaa9428/gr12.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/f153d8656567/gr13.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/143a6a7afe45/gr14.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/8d98711fd98c/gr15.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/8e717bb813be/gr16.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b9c9/11914293/a8ca108dcd2c/gr17.jpg

相似文献

1
Exploring AI in metasurface structures with forward and inverse design.通过正向和逆向设计探索超表面结构中的人工智能。
iScience. 2025 Feb 15;28(3):111995. doi: 10.1016/j.isci.2025.111995. eCollection 2025 Mar 21.
2
Recent advances in metasurface design and quantum optics applications with machine learning, physics-informed neural networks, and topology optimization methods.超表面设计以及机器学习、物理信息神经网络和拓扑优化方法在量子光学应用方面的最新进展。
Light Sci Appl. 2023 Jul 7;12(1):169. doi: 10.1038/s41377-023-01218-y.
3
On-Demand Design of Metasurfaces through Multineural Network Fusion.通过多神经网络融合实现超表面的按需设计
ACS Appl Mater Interfaces. 2024 Sep 18;16(37):49673-49686. doi: 10.1021/acsami.4c11972. Epub 2024 Sep 4.
4
A cyclical deep learning based framework for simultaneous inverse and forward design of nanophotonic metasurfaces.一种基于循环深度学习的框架，用于纳米光子超表面的同时逆向和正向设计。
Sci Rep. 2020 Nov 10;10(1):19427. doi: 10.1038/s41598-020-76400-y.
5
A knowledge-inherited learning for intelligent metasurface design and assembly.用于智能超表面设计与组装的知识继承学习
Light Sci Appl. 2023 Mar 30;12(1):82. doi: 10.1038/s41377-023-01131-4.
6
Maximizing Triboelectric Nanogenerators by Physics-Informed AI Inverse Design.通过物理信息人工智能逆向设计实现摩擦纳米发电机的最大化
Adv Mater. 2024 Feb;36(5):e2308505. doi: 10.1002/adma.202308505. Epub 2023 Dec 7.
7
Protein Science Meets Artificial Intelligence: A Systematic Review and a Biochemical Meta-Analysis of an Inter-Field.蛋白质科学与人工智能相遇：跨领域的系统评价与生化荟萃分析
Front Bioeng Biotechnol. 2022 Jul 7;10:788300. doi: 10.3389/fbioe.2022.788300. eCollection 2022.
8
Unleashing the potential: AI empowered advanced metasurface research.释放潜力：人工智能助力先进超表面研究。
Nanophotonics. 2024 Feb 27;13(8):1239-1278. doi: 10.1515/nanoph-2023-0759. eCollection 2024 Apr.
9
Exploring the Potential of Artificial Intelligence as a Facilitating Tool for Formulation Development in Fluidized Bed Processor: a Comprehensive Review.探索人工智能作为流化床处理器制剂开发辅助工具的潜力：全面综述。
AAPS PharmSciTech. 2024 May 13;25(5):111. doi: 10.1208/s12249-024-02816-8.
10
A surrogate-assisted extended generative adversarial network for parameter optimization in free-form metasurface design.一种基于代理的扩展生成对抗网络，用于自由曲面超表面设计中的参数优化。
Neural Netw. 2024 Dec;180:106654. doi: 10.1016/j.neunet.2024.106654. Epub 2024 Aug 22.

引用本文的文献

1
Nanophotonic Materials and Devices: Recent Advances and Emerging Applications.纳米光子材料与器件：最新进展及新兴应用
Micromachines (Basel). 2025 Aug 13;16(8):933. doi: 10.3390/mi16080933.
2
A Systems Biology Approach to Memory Health: Integrating Network Pharmacology, Gut Microbiota, and Multi-Omics for Health Functional Foods.一种针对记忆健康的系统生物学方法：整合网络药理学、肠道微生物群和多组学用于健康功能食品。
Int J Mol Sci. 2025 Jul 12;26(14):6698. doi: 10.3390/ijms26146698.

本文引用的文献

1
Experimental demonstration of inverse-designed silicon integrated photonic power splitters.逆设计硅基集成光子功率分配器的实验演示
Nanophotonics. 2022 Sep 9;11(20):4581-4590. doi: 10.1515/nanoph-2022-0443. eCollection 2022 Sep.
2
Deep neural network enabled active metasurface embedded design.基于深度神经网络的有源超表面嵌入式设计。
Nanophotonics. 2022 Jun 10;11(17):4149-4158. doi: 10.1515/nanoph-2022-0152. eCollection 2022 Sep.
3
Implementing of infrared camouflage with thermal management based on inverse design and hierarchical metamaterial.
基于逆向设计和分层超材料的具有热管理功能的红外伪装实现
Nanophotonics. 2023 Apr 13;12(10):1891-1902. doi: 10.1515/nanoph-2023-0067. eCollection 2023 May.
4
Free-form optimization of nanophotonic devices: from classical methods to deep learning.纳米光子器件的自由形式优化：从经典方法到深度学习。
Nanophotonics. 2022 Jan 12;11(9):1809-1845. doi: 10.1515/nanoph-2021-0713. eCollection 2022 Apr.
5
Genetic algorithm-enabled on-demand co-design of optically transparent metamaterial for multispectral stealth applications.用于多光谱隐身应用的基于遗传算法的光学透明超材料按需协同设计。
Opt Express. 2024 Aug 26;32(18):30969-30981. doi: 10.1364/OE.529553.
6
Energy-efficient dynamic 3D metasurfaces via spatiotemporal jamming interleaved assemblies for tactile interfaces.通过用于触觉接口的时空干扰交错组件实现的节能动态3D超表面。
Nat Commun. 2024 Aug 26;15(1):7340. doi: 10.1038/s41467-024-51865-x.
7
Harnessing the Missing Spectral Correlation for Metasurface Inverse Design.利用缺失的光谱相关性进行超表面逆设计。
Adv Sci (Weinh). 2024 Sep;11(33):e2308807. doi: 10.1002/advs.202308807. Epub 2024 Jul 1.
8
Inverse-designed ultra-compact multi-channel and multi-mode waveguide crossings.逆设计的超紧凑多通道多模波导交叉结构。
Opt Express. 2023 Aug 28;31(18):29235-29244. doi: 10.1364/OE.500327.
9
Correlating metasurface spectra with a generation-elimination framework.将超表面光谱与生成-消除框架相关联。
Nat Commun. 2023 Aug 12;14(1):4872. doi: 10.1038/s41467-023-40619-w.
10
Intelligent indoor metasurface robotics.智能室内超表面机器人技术
Natl Sci Rev. 2022 Nov 24;10(8):nwac266. doi: 10.1093/nsr/nwac266. eCollection 2023 Aug.