Deep-learning-assisted intelligent design of terahertz hybrid-functional metasurfaces with freeform patterns

Xia, H; Chen, SL; Wang, Y; Zhao, Y; Jia, H; Yang, R; Jay Guo, Y

Deep-learning-assisted intelligent design of terahertz hybrid-functional metasurfaces with freeform patterns

Xia, H Chen, SL Wang, Y Zhao, Y Jia, H Yang, R Jay Guo, Y

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Optics and Laser Technology, 2025, 181
Issue Date:: 2025-02-01

Embargoed

	Filename	Description	Size
	Deep-learning-assisted intelligent design of terahertz hybrid-functional metasurfaces with freeform patterns.pdf	Accepted version	1.33 MB		View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 31 Oct 2026

Full metadata record

Field	Value	Language
dc.contributor.author	Xia, H
dc.contributor.author	Chen, SL
dc.contributor.author	Wang, Y
dc.contributor.author	Zhao, Y
dc.contributor.author	Jia, H
dc.contributor.author	Yang, R
dc.contributor.author	Jay Guo, Y
dc.date.accessioned	2025-01-27T13:04:20Z
dc.date.available	2025-01-27T13:04:20Z
dc.date.issued	2025-02-01
dc.identifier.citation	Optics and Laser Technology, 2025, 181
dc.identifier.issn	0030-3992
dc.identifier.issn	1879-2545
dc.identifier.uri	http://hdl.handle.net/10453/184229
dc.description.abstract	Metasurfaces (MSs) possess powerful abilities to precisely manipulate electromagnetic (EM) waves. However, traditional metasurface design relies on time-consuming trial-and-error methods, and the design process becomes increasingly complex and challenging, particularly with the growing demand to integrate multiple functions into a single MS. To overcome these challenges, this work develops an innovative deep Unet++ conditional generative adversarial network (GAN), named Deep UCGAN++, for designing and characterizing hybrid-functional MSs with freeform patterns. The developed deep learning (DL) network model achieves not only accurate forward prediction of the EM response for given MSs, but also enables the inverse design of candidate MSs based on the target of user-defined functionalities. By constructing and training a hybrid-mode database of freeform MS, we effectively overcome the challenges of the limited design freedom and the deficiency of model generalization ability in DL-assisted MSs. This work offers a robust, high-accuracy yet time-efficient method for the generation of hybrid-functional MSs, paving the way for the further development of reconfigurable multifunctional MSs.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Optics and Laser Technology
dc.relation.isbasedon	10.1016/j.optlastec.2024.112041
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	0205 Optical Physics
dc.subject.classification	Optoelectronics & Photonics
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	Deep-learning-assisted intelligent design of terahertz hybrid-functional metasurfaces with freeform patterns
dc.type	Journal Article
utslib.citation.volume	181
utslib.for	0205 Optical Physics
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Global Big Data Technologies Centre (GBDTC)
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2026-10-31T00:00:00+1000Z
dc.date.updated	2025-01-27T13:04:18Z
pubs.publication-status	Accepted
pubs.volume	181

Abstract:

Metasurfaces (MSs) possess powerful abilities to precisely manipulate electromagnetic (EM) waves. However, traditional metasurface design relies on time-consuming trial-and-error methods, and the design process becomes increasingly complex and challenging, particularly with the growing demand to integrate multiple functions into a single MS. To overcome these challenges, this work develops an innovative deep Unet++ conditional generative adversarial network (GAN), named Deep UCGAN++, for designing and characterizing hybrid-functional MSs with freeform patterns. The developed deep learning (DL) network model achieves not only accurate forward prediction of the EM response for given MSs, but also enables the inverse design of candidate MSs based on the target of user-defined functionalities. By constructing and training a hybrid-mode database of freeform MS, we effectively overcome the challenges of the limited design freedom and the deficiency of model generalization ability in DL-assisted MSs. This work offers a robust, high-accuracy yet time-efficient method for the generation of hybrid-functional MSs, paving the way for the further development of reconfigurable multifunctional MSs.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/184229