Please use this identifier to cite or link to this item: https://doi.org/10.1038/s41467-021-23087-y
DC FieldValue
dc.titlePhase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning
dc.contributor.authorZhu, Ruichao
dc.contributor.authorQiu, Tianshuo
dc.contributor.authorWang, Jiafu
dc.contributor.authorSui, Sai
dc.contributor.authorHao, Chenglong
dc.contributor.authorLiu, Tonghao
dc.contributor.authorLi, Yongfeng
dc.contributor.authorFeng, Mingde
dc.contributor.authorZhang, Anxue
dc.contributor.authorQiu, Cheng-Wei
dc.contributor.authorQu, Shaobo
dc.date.accessioned2022-10-12T07:56:52Z
dc.date.available2022-10-12T07:56:52Z
dc.date.issued2021-05-20
dc.identifier.citationZhu, Ruichao, Qiu, Tianshuo, Wang, Jiafu, Sui, Sai, Hao, Chenglong, Liu, Tonghao, Li, Yongfeng, Feng, Mingde, Zhang, Anxue, Qiu, Cheng-Wei, Qu, Shaobo (2021-05-20). Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning. Nature Communications 12 (1) : 2974. ScholarBank@NUS Repository. https://doi.org/10.1038/s41467-021-23087-y
dc.identifier.issn2041-1723
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/232329
dc.description.abstractMetasurfaces have provided unprecedented freedom for manipulating electromagnetic waves. In metasurface design, massive meta-atoms have to be optimized to produce the desired phase profiles, which is time-consuming and sometimes prohibitive. In this paper, we propose a fast accurate inverse method of designing functional metasurfaces based on transfer learning, which can generate metasurface patterns monolithically from input phase profiles for specific functions. A transfer learning network based on GoogLeNet-Inception-V3 can predict the phases of 28×8 meta-atoms with an accuracy of around 90%. This method is validated via functional metasurface design using the trained network. Metasurface patterns are generated monolithically for achieving two typical functionals, 2D focusing and abnormal reflection. Both simulation and experiment verify the high design accuracy. This method provides an inverse design paradigm for fast functional metasurface design, and can be readily used to establish a meta-atom library with full phase span. © 2021, The Author(s).
dc.publisherNature Research
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourceScopus OA2021
dc.typeArticle
dc.contributor.departmentDEPT OF ELECTRICAL & COMPUTER ENGG
dc.contributor.departmentCOLLEGE OF DESIGN AND ENGINEERING
dc.description.doi10.1038/s41467-021-23087-y
dc.description.sourcetitleNature Communications
dc.description.volume12
dc.description.issue1
dc.description.page2974
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1038_s41467-021-23087-y.pdf3.56 MBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

46
checked on Jan 30, 2023

Page view(s)

15
checked on Jan 26, 2023

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons