A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-Resonators

Miniaturized spectrometers employing photonic crystal cavity arrays in conjunction with computational reconstruction have gained attention as effective tools for spectral analysis. Nevertheless, achieving an optimal balance among spectral resolution, detection range, and device compactness remains c...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinyi Zhou, Cheng Zhang, Zhenyu Zheng, Hongbin Li, Chao Peng
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Photonics
Subjects:
Online Access:https://www.mdpi.com/2304-6732/12/5/449
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849326929696522240
author Xinyi Zhou
Cheng Zhang
Zhenyu Zheng
Hongbin Li
Chao Peng
author_facet Xinyi Zhou
Cheng Zhang
Zhenyu Zheng
Hongbin Li
Chao Peng
author_sort Xinyi Zhou
collection DOAJ
description Miniaturized spectrometers employing photonic crystal cavity arrays in conjunction with computational reconstruction have gained attention as effective tools for spectral analysis. Nevertheless, achieving an optimal balance among spectral resolution, detection range, and device compactness remains challenging, particularly when complex nonlinear mappings, inter-pattern correlations, and noise interference are involved. In this work, we present ESTspecNet, a deep learning framework that integrates EfficientNet, the Swin Transformer, and spatial-channel attention mechanisms to improve spectral reconstruction accuracy. We reconstructed near-infrared spectra over an 80 nm range using a 144-unit photonic crystal cavity array, and achieved a single-peak resolution of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.47</mn></mrow></semantics></math></inline-formula> nm and a double-peak resolution of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.7</mn></mrow></semantics></math></inline-formula> nm. Compared to conventional methods, the proposed model demonstrates superior performance in both wide-range spectral reconstruction and fine-resolution tasks, thus highlighting its ability to effectively capture intricate spectral features and long-range dependencies, thereby advancing the reconstruction capabilities of miniaturized spectrometers.
format Article
id doaj-art-464b8bfb4fa54a4e825a811584000c52
institution Kabale University
issn 2304-6732
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Photonics
spelling doaj-art-464b8bfb4fa54a4e825a811584000c522025-08-20T03:48:02ZengMDPI AGPhotonics2304-67322025-05-0112544910.3390/photonics12050449A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-ResonatorsXinyi Zhou0Cheng Zhang1Zhenyu Zheng2Hongbin Li3Chao Peng4State Key Laboratory of Photonics and Communications, School of Electronics, Peking University, Beijing 100871, ChinaState Key Laboratory of Photonics and Communications, School of Electronics, Peking University, Beijing 100871, ChinaState Key Laboratory of Photonics and Communications, School of Electronics, Peking University, Beijing 100871, ChinaState Key Laboratory of Photonics and Communications, School of Electronics, Peking University, Beijing 100871, ChinaState Key Laboratory of Photonics and Communications, School of Electronics, Peking University, Beijing 100871, ChinaMiniaturized spectrometers employing photonic crystal cavity arrays in conjunction with computational reconstruction have gained attention as effective tools for spectral analysis. Nevertheless, achieving an optimal balance among spectral resolution, detection range, and device compactness remains challenging, particularly when complex nonlinear mappings, inter-pattern correlations, and noise interference are involved. In this work, we present ESTspecNet, a deep learning framework that integrates EfficientNet, the Swin Transformer, and spatial-channel attention mechanisms to improve spectral reconstruction accuracy. We reconstructed near-infrared spectra over an 80 nm range using a 144-unit photonic crystal cavity array, and achieved a single-peak resolution of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.47</mn></mrow></semantics></math></inline-formula> nm and a double-peak resolution of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.7</mn></mrow></semantics></math></inline-formula> nm. Compared to conventional methods, the proposed model demonstrates superior performance in both wide-range spectral reconstruction and fine-resolution tasks, thus highlighting its ability to effectively capture intricate spectral features and long-range dependencies, thereby advancing the reconstruction capabilities of miniaturized spectrometers.https://www.mdpi.com/2304-6732/12/5/449miniaturized spectrometerresonant arraydeep learningspectral reconstruction
spellingShingle Xinyi Zhou
Cheng Zhang
Zhenyu Zheng
Hongbin Li
Chao Peng
A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-Resonators
Photonics
miniaturized spectrometer
resonant array
deep learning
spectral reconstruction
title A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-Resonators
title_full A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-Resonators
title_fullStr A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-Resonators
title_full_unstemmed A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-Resonators
title_short A Deep Learning Model for Spectral Reconstruction of Arrayed Micro-Resonators
title_sort deep learning model for spectral reconstruction of arrayed micro resonators
topic miniaturized spectrometer
resonant array
deep learning
spectral reconstruction
url https://www.mdpi.com/2304-6732/12/5/449
work_keys_str_mv AT xinyizhou adeeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT chengzhang adeeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT zhenyuzheng adeeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT hongbinli adeeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT chaopeng adeeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT xinyizhou deeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT chengzhang deeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT zhenyuzheng deeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT hongbinli deeplearningmodelforspectralreconstructionofarrayedmicroresonators
AT chaopeng deeplearningmodelforspectralreconstructionofarrayedmicroresonators