Convolutional neural networks for mode on-demand high finesse optical resonator design
Abstract We demonstrate the use of machine learning through convolutional neural networks to solve inverse design problems of optical resonator engineering. The neural network finds a harmonic modulation of a spherical mirror to generate a resonator mode with a given target topology (“mode on-demand...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-09-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-42223-w |
_version_ | 1797559946802364416 |
---|---|
author | Denis V. Karpov Sergei Kurdiumov Peter Horak |
author_facet | Denis V. Karpov Sergei Kurdiumov Peter Horak |
author_sort | Denis V. Karpov |
collection | DOAJ |
description | Abstract We demonstrate the use of machine learning through convolutional neural networks to solve inverse design problems of optical resonator engineering. The neural network finds a harmonic modulation of a spherical mirror to generate a resonator mode with a given target topology (“mode on-demand”). The procedure allows us to optimize the shape of mirrors to achieve a significantly enhanced coupling strength and cooperativity between a resonator photon and a quantum emitter located at the center of the resonator. In a second example, a double-peak mode is designed which would enhance the interaction between two quantum emitters, e.g., for quantum information processing. |
first_indexed | 2024-03-10T17:52:26Z |
format | Article |
id | doaj.art-06c6147a6ae94b58a89ad47876f4530f |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-10T17:52:26Z |
publishDate | 2023-09-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-06c6147a6ae94b58a89ad47876f4530f2023-11-20T09:17:13ZengNature PortfolioScientific Reports2045-23222023-09-0113111010.1038/s41598-023-42223-wConvolutional neural networks for mode on-demand high finesse optical resonator designDenis V. Karpov0Sergei Kurdiumov1Peter Horak2Optoelectronics Research Centre, University of SouthamptonOptoelectronics Research Centre, University of SouthamptonOptoelectronics Research Centre, University of SouthamptonAbstract We demonstrate the use of machine learning through convolutional neural networks to solve inverse design problems of optical resonator engineering. The neural network finds a harmonic modulation of a spherical mirror to generate a resonator mode with a given target topology (“mode on-demand”). The procedure allows us to optimize the shape of mirrors to achieve a significantly enhanced coupling strength and cooperativity between a resonator photon and a quantum emitter located at the center of the resonator. In a second example, a double-peak mode is designed which would enhance the interaction between two quantum emitters, e.g., for quantum information processing.https://doi.org/10.1038/s41598-023-42223-w |
spellingShingle | Denis V. Karpov Sergei Kurdiumov Peter Horak Convolutional neural networks for mode on-demand high finesse optical resonator design Scientific Reports |
title | Convolutional neural networks for mode on-demand high finesse optical resonator design |
title_full | Convolutional neural networks for mode on-demand high finesse optical resonator design |
title_fullStr | Convolutional neural networks for mode on-demand high finesse optical resonator design |
title_full_unstemmed | Convolutional neural networks for mode on-demand high finesse optical resonator design |
title_short | Convolutional neural networks for mode on-demand high finesse optical resonator design |
title_sort | convolutional neural networks for mode on demand high finesse optical resonator design |
url | https://doi.org/10.1038/s41598-023-42223-w |
work_keys_str_mv | AT denisvkarpov convolutionalneuralnetworksformodeondemandhighfinesseopticalresonatordesign AT sergeikurdiumov convolutionalneuralnetworksformodeondemandhighfinesseopticalresonatordesign AT peterhorak convolutionalneuralnetworksformodeondemandhighfinesseopticalresonatordesign |