Inverse design of topological photonic time crystals via deep learning
Photonic time crystals are a new kind of photonic system in modern optical physics, leading to devices with new properties in time. However, so far, it is still a challenge to design photonic time crystals with specific topological states due to the complex relations between time crystal structures...
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Journal Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/179935 |
_version_ | 1826124766364303360 |
---|---|
author | Long, Yang Zou, Linyang Yu, Letian Hu, Hao Xiong, Jiang Zhang, Baile |
author2 | School of Physical and Mathematical Sciences |
author_facet | School of Physical and Mathematical Sciences Long, Yang Zou, Linyang Yu, Letian Hu, Hao Xiong, Jiang Zhang, Baile |
author_sort | Long, Yang |
collection | NTU |
description | Photonic time crystals are a new kind of photonic system in modern optical physics, leading to devices with new properties in time. However, so far, it is still a challenge to design photonic time crystals with specific topological states due to the complex relations between time crystal structures and topological properties. Here, we propose a deep-learning-based approach to address this challenge. In a photonic time crystal with time inversion symmetry, each band separated by momentum gaps can have a non-zero quantized Berry phase. We show that the neural network can learn the relationship between time crystal structures and Berry phases, and then determine the crystal structures of photonic time crystals based on given Berry phase properties. Our work shows a new way of applying machine learning to the inverse design of time-varying optical systems and has potential extensions to other fields, such as time-varying phononic devices. |
first_indexed | 2024-10-01T06:26:03Z |
format | Journal Article |
id | ntu-10356/179935 |
institution | Nanyang Technological University |
language | English |
last_indexed | 2024-10-01T06:26:03Z |
publishDate | 2024 |
record_format | dspace |
spelling | ntu-10356/1799352024-09-09T15:34:47Z Inverse design of topological photonic time crystals via deep learning Long, Yang Zou, Linyang Yu, Letian Hu, Hao Xiong, Jiang Zhang, Baile School of Physical and Mathematical Sciences School of Electrical and Electronic Engineering Centre for Disruptive Photonic Technologies (CDPT) Physics Crystals Deep learning Photonic time crystals are a new kind of photonic system in modern optical physics, leading to devices with new properties in time. However, so far, it is still a challenge to design photonic time crystals with specific topological states due to the complex relations between time crystal structures and topological properties. Here, we propose a deep-learning-based approach to address this challenge. In a photonic time crystal with time inversion symmetry, each band separated by momentum gaps can have a non-zero quantized Berry phase. We show that the neural network can learn the relationship between time crystal structures and Berry phases, and then determine the crystal structures of photonic time crystals based on given Berry phase properties. Our work shows a new way of applying machine learning to the inverse design of time-varying optical systems and has potential extensions to other fields, such as time-varying phononic devices. Ministry of Education (MOE) National Research Foundation (NRF) Published version National Research Foundation Singapore (Competitive Research Program NRF-CRP23-2019-0007); Ministry of Education - Singapore Academic Research Fund Tier 2 (MOE-T2EP50123-0007); Distinguished Professor Fund of Jiangsu Province (1004-YQR23064); Selected Chinese Government Talent-recruitment Programs of Nanjing (1004-YQR23122); the Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship. 2024-09-04T05:23:05Z 2024-09-04T05:23:05Z 2024 Journal Article Long, Y., Zou, L., Yu, L., Hu, H., Xiong, J. & Zhang, B. (2024). Inverse design of topological photonic time crystals via deep learning. Optical Materials Express, 14(8), 2032-2039. https://dx.doi.org/10.1364/OME.525396 2159-3930 https://hdl.handle.net/10356/179935 10.1364/OME.525396 2-s2.0-85200606598 8 14 2032 2039 en NRF-CRP23-2019-0007 MOE-T2EP50123-0007 Optical Materials Express © 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement. application/pdf |
spellingShingle | Physics Crystals Deep learning Long, Yang Zou, Linyang Yu, Letian Hu, Hao Xiong, Jiang Zhang, Baile Inverse design of topological photonic time crystals via deep learning |
title | Inverse design of topological photonic time crystals via deep learning |
title_full | Inverse design of topological photonic time crystals via deep learning |
title_fullStr | Inverse design of topological photonic time crystals via deep learning |
title_full_unstemmed | Inverse design of topological photonic time crystals via deep learning |
title_short | Inverse design of topological photonic time crystals via deep learning |
title_sort | inverse design of topological photonic time crystals via deep learning |
topic | Physics Crystals Deep learning |
url | https://hdl.handle.net/10356/179935 |
work_keys_str_mv | AT longyang inversedesignoftopologicalphotonictimecrystalsviadeeplearning AT zoulinyang inversedesignoftopologicalphotonictimecrystalsviadeeplearning AT yuletian inversedesignoftopologicalphotonictimecrystalsviadeeplearning AT huhao inversedesignoftopologicalphotonictimecrystalsviadeeplearning AT xiongjiang inversedesignoftopologicalphotonictimecrystalsviadeeplearning AT zhangbaile inversedesignoftopologicalphotonictimecrystalsviadeeplearning |