Deep learning for the design and characterization of high efficiency self-focusing grating
Deep learning for the design and characterization of high efficiency self-focusing grating
We demonstrate that the deep learning algorithm can considerably simplify the design and characterization of high efficient self-focusing varied line-spaced gratings. Our neural network is implemented with a recovery rate of up to 94% for the transmission function parameters. With numerical simulations, and optical experiments, we show that the self-focusing varied line-spaced gratings designed in such a way are endowed with enhanced functionalities, such as the intensity of first-order diffraction peak being enhanced with around a factor of 30 compared with the incident intensity, and a high ratio (about 60) between the peak intensity of the first order and the intensity of the zero-order. Our results allow the rapid design and characterization of self-focusing varied line-spaced gratings as well as optimal microstructures for targeted far-field diffraction patterns, which are playing key roles in spectroscopy and monochromatization applications.
Diffraction grating, Neural network, Optical structures design, Self-focusing
Pu, Tanchao
89eb5a37-31bf-469a-ae29-c871d5d25c65
Cao, Fulin
f7d7ac99-73df-4d91-8da2-9fe1099cd373
Liu, Ziwei
3cbbfc31-2982-40e7-b3f5-0ded2d281e20
Xie, Changqing
e46346b9-56b3-44cb-9533-0a67428a9e4a
1 May 2022
Pu, Tanchao
89eb5a37-31bf-469a-ae29-c871d5d25c65
Cao, Fulin
f7d7ac99-73df-4d91-8da2-9fe1099cd373
Liu, Ziwei
3cbbfc31-2982-40e7-b3f5-0ded2d281e20
Xie, Changqing
e46346b9-56b3-44cb-9533-0a67428a9e4a
Pu, Tanchao, Cao, Fulin, Liu, Ziwei and Xie, Changqing
(2022)
Deep learning for the design and characterization of high efficiency self-focusing grating.
Optics Communications, 510, [127951].
(doi:10.1016/j.optcom.2022.127951).
Abstract
We demonstrate that the deep learning algorithm can considerably simplify the design and characterization of high efficient self-focusing varied line-spaced gratings. Our neural network is implemented with a recovery rate of up to 94% for the transmission function parameters. With numerical simulations, and optical experiments, we show that the self-focusing varied line-spaced gratings designed in such a way are endowed with enhanced functionalities, such as the intensity of first-order diffraction peak being enhanced with around a factor of 30 compared with the incident intensity, and a high ratio (about 60) between the peak intensity of the first order and the intensity of the zero-order. Our results allow the rapid design and characterization of self-focusing varied line-spaced gratings as well as optimal microstructures for targeted far-field diffraction patterns, which are playing key roles in spectroscopy and monochromatization applications.
Text
accept version
- Accepted Manuscript
More information
Accepted/In Press date: 10 January 2022
Published date: 1 May 2022
Additional Information:
Funding Information:
T. Pu thanks the valuable discussion with Dr. N. Papasimakis from University of Southampton, UK and acknowledges the financial support from Chinese Scholarship Council (CSC No. 201804910540 ).
Funding Information:
This work was supported by the National Key Research and Development Program of China (Grant No. 2017YFA0206002 ); National Natural Science Foundation of China (Grant Nos. U1832217 , 61804169 , and 61821091 ).
Publisher Copyright:
© 2022 Elsevier B.V.
Keywords:
Diffraction grating, Neural network, Optical structures design, Self-focusing
Identifiers
Local EPrints ID: 455427
URI: http://eprints.soton.ac.uk/id/eprint/455427
ISSN: 0030-4018
PURE UUID: 9236f581-56fe-4609-a916-9b1eeb578c09
Catalogue record
Date deposited: 21 Mar 2022 17:53
Last modified: 27 Jul 2024 04:02
Export record
Altmetrics
Contributors
Author:
Fulin Cao
Author:
Ziwei Liu
Author:
Changqing Xie
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
