Engineering of multiple bound states in the continuum by latent representation of freeform structures

Ronghui Lin; Zahrah Alnakhli; Xiaohang Li

doi:10.1364/PRJ.415655

Engineering of multiple bound states in the continuum by latent representation of freeform structures

Ronghui Lin, Zahrah Alnakhli, Xiaohang Li

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

Abstract

We demonstrate a neural network capable of designing on-demand multiple symmetry-protected bound states in the continuum (BICs) in freeform structures with predefined symmetry. The latent representation of the freeform structures allows the tuning of the geometry in a differentiable, continuous way. We show the rich band inversion and accidental degeneracy in these freeform structures by interacting with the latent representation directly. Moreover, a high design accuracy is demonstrated for arbitrary control of multiple BIC frequencies by using a photonic property readout network to interpret the latent representation.

Original language	English (US)
Pages (from-to)	96-103
Number of pages	8
Journal	Photonics Research
Volume	9
Issue number	4
DOIs	https://doi.org/10.1364/PRJ.415655
State	Published - Mar 22 2021

Bibliographical note

KAUST Repository Item: Exported on 2021-04-14
Acknowledged KAUST grant number(s): BAS/1/1664-01-01, URF/1/3437-01-01, URF/1/3771-01-01
Acknowledgements: King Abdullah University of Science and Technology Baseline Fund (BAS/1/1664-01-01); Competitive Research Grants (URF/1/3437-01-01, URF/1/3771-01-01).

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics

Access to Document

10.1364/PRJ.415655

https://repository.kaust.edu.sa/bitstream/10754/668714/1/20210117_BICNN_PR_unmarked.pdf

Cite this

@article{6465a7272a8e442f931653fda042a61a,

title = "Engineering of multiple bound states in the continuum by latent representation of freeform structures",

abstract = "We demonstrate a neural network capable of designing on-demand multiple symmetry-protected bound states in the continuum (BICs) in freeform structures with predefined symmetry. The latent representation of the freeform structures allows the tuning of the geometry in a differentiable, continuous way. We show the rich band inversion and accidental degeneracy in these freeform structures by interacting with the latent representation directly. Moreover, a high design accuracy is demonstrated for arbitrary control of multiple BIC frequencies by using a photonic property readout network to interpret the latent representation.",

author = "Ronghui Lin and Zahrah Alnakhli and Xiaohang Li",

note = "KAUST Repository Item: Exported on 2021-04-14 Acknowledged KAUST grant number(s): BAS/1/1664-01-01, URF/1/3437-01-01, URF/1/3771-01-01 Acknowledgements: King Abdullah University of Science and Technology Baseline Fund (BAS/1/1664-01-01); Competitive Research Grants (URF/1/3437-01-01, URF/1/3771-01-01).",

year = "2021",

month = mar,

day = "22",

doi = "10.1364/PRJ.415655",

language = "English (US)",

volume = "9",

pages = "96--103",

journal = "Photonics Research",

issn = "2327-9125",

publisher = "OSA Publishing",

number = "4",

}

TY - JOUR

T1 - Engineering of multiple bound states in the continuum by latent representation of freeform structures

AU - Lin, Ronghui

AU - Alnakhli, Zahrah

AU - Li, Xiaohang

N1 - KAUST Repository Item: Exported on 2021-04-14 Acknowledged KAUST grant number(s): BAS/1/1664-01-01, URF/1/3437-01-01, URF/1/3771-01-01 Acknowledgements: King Abdullah University of Science and Technology Baseline Fund (BAS/1/1664-01-01); Competitive Research Grants (URF/1/3437-01-01, URF/1/3771-01-01).

PY - 2021/3/22

Y1 - 2021/3/22

N2 - We demonstrate a neural network capable of designing on-demand multiple symmetry-protected bound states in the continuum (BICs) in freeform structures with predefined symmetry. The latent representation of the freeform structures allows the tuning of the geometry in a differentiable, continuous way. We show the rich band inversion and accidental degeneracy in these freeform structures by interacting with the latent representation directly. Moreover, a high design accuracy is demonstrated for arbitrary control of multiple BIC frequencies by using a photonic property readout network to interpret the latent representation.

AB - We demonstrate a neural network capable of designing on-demand multiple symmetry-protected bound states in the continuum (BICs) in freeform structures with predefined symmetry. The latent representation of the freeform structures allows the tuning of the geometry in a differentiable, continuous way. We show the rich band inversion and accidental degeneracy in these freeform structures by interacting with the latent representation directly. Moreover, a high design accuracy is demonstrated for arbitrary control of multiple BIC frequencies by using a photonic property readout network to interpret the latent representation.

UR - http://hdl.handle.net/10754/668714

UR - https://www.osapublishing.org/abstract.cfm?URI=prj-9-4-B96

UR - http://www.scopus.com/inward/record.url?scp=85103641603&partnerID=8YFLogxK

U2 - 10.1364/PRJ.415655

DO - 10.1364/PRJ.415655

M3 - Article

SN - 2327-9125

VL - 9

SP - 96

EP - 103

JO - Photonics Research

JF - Photonics Research

IS - 4

ER -

Engineering of multiple bound states in the continuum by latent representation of freeform structures

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this