Designing thermal radiation metamaterials via a hybrid adversarial autoencoder and Bayesian optimization

Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objectives. In this Letter, we develop a hybrid materials informatics approach which combines the adversarial autoencoder and Bayesian optimization to design narrowband thermal e...

Full description

Saved in:
Bibliographic Details
Published in:Optics letters Vol. 47; no. 14; p. 3395
Main Authors: Zhu, Dezhao, Guo, Jiang, Yu, Gang, Zhao, C Y, Wang, Hong, Ju, Shenghong
Format: Journal Article
Language:English
Published: 15.07.2022
ISSN:1539-4794, 1539-4794
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objectives. In this Letter, we develop a hybrid materials informatics approach which combines the adversarial autoencoder and Bayesian optimization to design narrowband thermal emitters at different target wavelengths. With only several hundreds of training data sets, new structures with optimal properties can be quickly determined in a compressed two-dimensional latent space. This enables the optimal design by calculating far less than 0.001% of the total candidate structures, which greatly decreases the design period and cost. The proposed design framework can be easily extended to other thermal radiation metamaterials design with higher dimensional features.Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objectives. In this Letter, we develop a hybrid materials informatics approach which combines the adversarial autoencoder and Bayesian optimization to design narrowband thermal emitters at different target wavelengths. With only several hundreds of training data sets, new structures with optimal properties can be quickly determined in a compressed two-dimensional latent space. This enables the optimal design by calculating far less than 0.001% of the total candidate structures, which greatly decreases the design period and cost. The proposed design framework can be easily extended to other thermal radiation metamaterials design with higher dimensional features.
AbstractList Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objectives. In this Letter, we develop a hybrid materials informatics approach which combines the adversarial autoencoder and Bayesian optimization to design narrowband thermal emitters at different target wavelengths. With only several hundreds of training data sets, new structures with optimal properties can be quickly determined in a compressed two-dimensional latent space. This enables the optimal design by calculating far less than 0.001% of the total candidate structures, which greatly decreases the design period and cost. The proposed design framework can be easily extended to other thermal radiation metamaterials design with higher dimensional features.Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objectives. In this Letter, we develop a hybrid materials informatics approach which combines the adversarial autoencoder and Bayesian optimization to design narrowband thermal emitters at different target wavelengths. With only several hundreds of training data sets, new structures with optimal properties can be quickly determined in a compressed two-dimensional latent space. This enables the optimal design by calculating far less than 0.001% of the total candidate structures, which greatly decreases the design period and cost. The proposed design framework can be easily extended to other thermal radiation metamaterials design with higher dimensional features.
Author Zhu, Dezhao
Yu, Gang
Ju, Shenghong
Wang, Hong
Guo, Jiang
Zhao, C Y
Author_xml – sequence: 1
  givenname: Dezhao
  surname: Zhu
  fullname: Zhu, Dezhao
– sequence: 2
  givenname: Jiang
  surname: Guo
  fullname: Guo, Jiang
– sequence: 3
  givenname: Gang
  surname: Yu
  fullname: Yu, Gang
– sequence: 4
  givenname: C Y
  surname: Zhao
  fullname: Zhao, C Y
– sequence: 5
  givenname: Hong
  surname: Wang
  fullname: Wang, Hong
– sequence: 6
  givenname: Shenghong
  surname: Ju
  fullname: Ju, Shenghong
BookMark eNpN0EtLAzEUBeAgFWyrC_9Blm6mTh5NZpZarQqFbnRd7iR32shMUpO0UH-942Ph6h448MG5EzLywSMh16ycMaHk7Xo1k3MhJT8jYzYXdSF1LUf_8gWZpPRelqXSQozJ7gGT23rntzTvMPbQ0QjWQXbB0x4z9JAxOugSPTqgQHenJjpLwR4xJvhuKBxyQG-CxUjBW3oPpwEFT8M-u959_mCX5LwdFLz6u1Pytnx8XTwXq_XTy-JuVRhel7nQuoKKzRsAI9BoaSyyVtlhk2qrpqkbJqTmglvBTKVUJVqpW9EaUAimsjWfkptfdx_DxwFT3vQuGew68BgOacNVzUqphwfwL1ZeXi0
CitedBy_id crossref_primary_10_1016_j_ijheatmasstransfer_2023_124831
crossref_primary_10_1016_j_solmat_2024_112822
crossref_primary_10_1016_j_optcom_2024_130569
crossref_primary_10_1002_advs_202401951
crossref_primary_10_1016_j_ijheatmasstransfer_2022_123332
crossref_primary_10_1016_j_ijmecsci_2025_110335
crossref_primary_10_1016_j_nxener_2023_100078
crossref_primary_10_1063_5_0250763
crossref_primary_10_1515_nanoph_2025_0159
crossref_primary_10_1364_AO_465157
crossref_primary_10_34133_icomputing_0135
ContentType Journal Article
DBID 7X8
DOI 10.1364/OL.453442
DatabaseName MEDLINE - Academic
DatabaseTitle MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Database_xml – sequence: 1
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Physics
EISSN 1539-4794
GroupedDBID ---
-~X
.DC
123
29N
4.4
53G
7X8
8SL
AAWJZ
ACBEA
ACGFO
AEDJG
AENEX
AGQFO
AKGWG
ALMA_UNASSIGNED_HOLDINGS
ATHME
AYPRP
AZSQR
AZYMN
CS3
DSZJF
DU5
EBS
F5P
ODPQJ
OFLFD
OPJBK
OPLUZ
P2P
RNS
ROL
ROS
SJN
TAE
TN5
TR6
WH7
Y7S
YNT
ID FETCH-LOGICAL-c290t-778a815baac3ec74cde1f6d4536f8bb9b1347232d31c86683f47f3fca6eac8d92
IEDL.DBID 7X8
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000826474100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1539-4794
IngestDate Thu Oct 02 06:56:29 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 14
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c290t-778a815baac3ec74cde1f6d4536f8bb9b1347232d31c86683f47f3fca6eac8d92
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 2691047000
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2691047000
PublicationCentury 2000
PublicationDate 20220715
PublicationDateYYYYMMDD 2022-07-15
PublicationDate_xml – month: 07
  year: 2022
  text: 20220715
  day: 15
PublicationDecade 2020
PublicationTitle Optics letters
PublicationYear 2022
SSID ssj0006733
Score 2.4805596
Snippet Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objectives. In this Letter, we...
SourceID proquest
SourceType Aggregation Database
StartPage 3395
Title Designing thermal radiation metamaterials via a hybrid adversarial autoencoder and Bayesian optimization
URI https://www.proquest.com/docview/2691047000
Volume 47
WOSCitedRecordID wos000826474100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1JSwMxFA5qFby4izsRvI7tJJksJ3ErHqR6UOitZKU9dEY700L_vXnTKQVPgufJYXhbPl7e-z6Ebqg3KgjCEkVSn8SgSBNDLUmCCR3hg2OZCbXYhOj1ZL-v3puGW9mMVS5rYl2oXWGhR94mXAGrQMzgu6_vBFSj4HW1kdBYRy0aoQwkpuiv2MK5qKXkY1Ir6CCxhlmIctZ-e71lGWWg0P6rBtcXS3f3v7-0h3YaSInvFzGwj9Z8foC26tFOWx6i4VM9pBGvKAxgbxyPToCQADyCx77SEbMuwhDPRhprPJzDFhfWINVcaviC9bQqgPHS-QnWucMPeu5h-xIXseKMm1XOI_TZff54fEkafYXEEtWpIrCWWqaZ0dpSbwWzzqeBR_dQHqQxysCaaURcjqZWci5pYCLQYDWP1Vo6RY7RRl7k_gRhyVNrlCNKG8ICJ8oE2ZG-40gwXnB3iq6XJhzE-IVHCZ37YloOVkY8-8OZc7RNYP8AmC2zC9QK0Tj-Em3aWTUqJ1e1-38AD269fA
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Designing+thermal+radiation+metamaterials+via+a+hybrid+adversarial+autoencoder+and+Bayesian+optimization&rft.jtitle=Optics+letters&rft.au=Zhu%2C+Dezhao&rft.au=Guo%2C+Jiang&rft.au=Yu%2C+Gang&rft.au=Zhao%2C+C+Y&rft.date=2022-07-15&rft.issn=1539-4794&rft.eissn=1539-4794&rft.volume=47&rft.issue=14&rft.spage=3395&rft_id=info:doi/10.1364%2FOL.453442&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1539-4794&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1539-4794&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1539-4794&client=summon