An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10

Blue horizontal-branch (BHB) stars are ideal tracers for studying the kinematics and structural properties of the Milky Way. With massive spectral data provided by the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), we aim to identify more potential BHB stars using machine learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhang Zhang, Yude Bu, Jiangchuan Zhang, Ke Wang, Huili Wu, Mengmeng Zhang, Shanshan Li, Jingzhen Sun, Xiaoming Kong, Zhenping Yi, Meng Liu
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:The Astronomical Journal
Subjects:
Online Access:https://doi.org/10.3847/1538-3881/adea95
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849391367678066688
author Yuhang Zhang
Yude Bu
Jiangchuan Zhang
Ke Wang
Huili Wu
Mengmeng Zhang
Shanshan Li
Jingzhen Sun
Xiaoming Kong
Zhenping Yi
Meng Liu
author_facet Yuhang Zhang
Yude Bu
Jiangchuan Zhang
Ke Wang
Huili Wu
Mengmeng Zhang
Shanshan Li
Jingzhen Sun
Xiaoming Kong
Zhenping Yi
Meng Liu
author_sort Yuhang Zhang
collection DOAJ
description Blue horizontal-branch (BHB) stars are ideal tracers for studying the kinematics and structural properties of the Milky Way. With massive spectral data provided by the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), we aim to identify more potential BHB stars using machine learning methods. In this study, we propose BHBNet, an advanced two-stage deep learning model integrating multiple techniques. By implementing Bayesian inference, it not only provides classification results but also quantifies uncertainty. In stage 1, a six-class classification model was constructed to initially identify BHB candidates, achieving a precision of 95.43% on the test set. In stage 2, a binary classification model constructed through the transfer learning method was employed to further refine the candidates, achieving a precision of 98.36% on the test set. Subsequently, by performing a two-stage search in LAMOST low-resolution survey DR10, we identified 6792 candidates. Nevertheless, since the completeness of this search result has not been assessed, these samples may not be adequate for statistical studies of the BHB population. We analyzed candidate properties including color, absolute magnitude, and spatial distribution, while estimating their atmospheric parameters. Eventually, by fitting Balmer line profiles, we identified 1605 new BHB stars compared to the previous studies by X.-X. Xue et al. and J. J. Vickers et al. Our study emphasizes the potential and effectiveness of using machine learning methods in identifying and analyzing BHB stars.
format Article
id doaj-art-390b422359b34cfc81dbded1e66d28e0
institution Kabale University
issn 1538-3881
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series The Astronomical Journal
spelling doaj-art-390b422359b34cfc81dbded1e66d28e02025-08-20T03:41:05ZengIOP PublishingThe Astronomical Journal1538-38812025-01-01170315810.3847/1538-3881/adea95An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10Yuhang Zhang0https://orcid.org/0009-0009-7973-4077Yude Bu1https://orcid.org/0000-0002-9474-4734Jiangchuan Zhang2https://orcid.org/0009-0006-5523-3997Ke Wang3Huili Wu4Mengmeng Zhang5Shanshan Li6Jingzhen Sun7https://orcid.org/0009-0000-8724-497XXiaoming Kong8https://orcid.org/0000-0002-4764-4749Zhenping Yi9https://orcid.org/0000-0001-8590-4110Meng Liu10https://orcid.org/0000-0003-2442-2841School of Mathematics and Statistics, Shandong University , Weihai, 264209, Shandong, People’s Republic of China ; buyude@sdu.edu.cnSchool of Mathematics and Statistics, Shandong University , Weihai, 264209, Shandong, People’s Republic of China ; buyude@sdu.edu.cnSchool of Space Science and Technology, Shandong University , Weihai, 264209, Shandong, People’s Republic of ChinaSchool of Mathematics and Statistics, Shandong University , Weihai, 264209, Shandong, People’s Republic of China ; buyude@sdu.edu.cnSchool of Mathematics and Statistics, Shandong University , Weihai, 264209, Shandong, People’s Republic of China ; buyude@sdu.edu.cnSchool of Mathematics and Statistics, Shandong University , Weihai, 264209, Shandong, People’s Republic of China ; buyude@sdu.edu.cnSchool of Mathematics and Statistics, Shandong University , Weihai, 264209, Shandong, People’s Republic of China ; buyude@sdu.edu.cnSchool of Mathematics and Statistics, Shandong University , Weihai, 264209, Shandong, People’s Republic of China ; buyude@sdu.edu.cnSchool of Mechanical, Electrical and Information Engineering, Shandong University , Weihai, 264209, Shandong, People’s Republic of China; Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application, Shandong University , Weihai, 264209, Shandong, People’s Republic of ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University , Weihai, 264209, Shandong, People’s Republic of China; Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application, Shandong University , Weihai, 264209, Shandong, People’s Republic of ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University , Weihai, 264209, Shandong, People’s Republic of China; Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application, Shandong University , Weihai, 264209, Shandong, People’s Republic of ChinaBlue horizontal-branch (BHB) stars are ideal tracers for studying the kinematics and structural properties of the Milky Way. With massive spectral data provided by the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), we aim to identify more potential BHB stars using machine learning methods. In this study, we propose BHBNet, an advanced two-stage deep learning model integrating multiple techniques. By implementing Bayesian inference, it not only provides classification results but also quantifies uncertainty. In stage 1, a six-class classification model was constructed to initially identify BHB candidates, achieving a precision of 95.43% on the test set. In stage 2, a binary classification model constructed through the transfer learning method was employed to further refine the candidates, achieving a precision of 98.36% on the test set. Subsequently, by performing a two-stage search in LAMOST low-resolution survey DR10, we identified 6792 candidates. Nevertheless, since the completeness of this search result has not been assessed, these samples may not be adequate for statistical studies of the BHB population. We analyzed candidate properties including color, absolute magnitude, and spatial distribution, while estimating their atmospheric parameters. Eventually, by fitting Balmer line profiles, we identified 1605 new BHB stars compared to the previous studies by X.-X. Xue et al. and J. J. Vickers et al. Our study emphasizes the potential and effectiveness of using machine learning methods in identifying and analyzing BHB stars.https://doi.org/10.3847/1538-3881/adea95AstrostatisticsAstronomy data analysisHorizontal branch starsConvolutional neural networks
spellingShingle Yuhang Zhang
Yude Bu
Jiangchuan Zhang
Ke Wang
Huili Wu
Mengmeng Zhang
Shanshan Li
Jingzhen Sun
Xiaoming Kong
Zhenping Yi
Meng Liu
An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10
The Astronomical Journal
Astrostatistics
Astronomy data analysis
Horizontal branch stars
Convolutional neural networks
title An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10
title_full An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10
title_fullStr An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10
title_full_unstemmed An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10
title_short An Advanced Deep Learning Model for Identifying Blue Horizontal-branch Stars from LAMOST DR10
title_sort advanced deep learning model for identifying blue horizontal branch stars from lamost dr10
topic Astrostatistics
Astronomy data analysis
Horizontal branch stars
Convolutional neural networks
url https://doi.org/10.3847/1538-3881/adea95
work_keys_str_mv AT yuhangzhang anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT yudebu anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT jiangchuanzhang anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT kewang anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT huiliwu anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT mengmengzhang anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT shanshanli anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT jingzhensun anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT xiaomingkong anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT zhenpingyi anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT mengliu anadvanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT yuhangzhang advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT yudebu advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT jiangchuanzhang advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT kewang advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT huiliwu advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT mengmengzhang advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT shanshanli advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT jingzhensun advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT xiaomingkong advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT zhenpingyi advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10
AT mengliu advanceddeeplearningmodelforidentifyingbluehorizontalbranchstarsfromlamostdr10