J/ApJS/259/5 Hot subdwarf candidates from LAMOST DR7 (Tan+, 2022)
A robust identification method for hot subdwarfs based on deep learning.
Tan L., Mei Y., Liu Z., Luo Y., Deng H., Wang F., Deng L., Liu C.
<Astrophys. J. Suppl. Ser., 259, 5-5 (2022)>
=2022ApJS..259....5T 2022ApJS..259....5T (SIMBAD/NED BibCode)
ADC_Keywords: Stars, subdwarf; Spectra, optical
Keywords: Convolutional neural networks; Subdwarf stars; Stellar classification
Stellar types
Abstract:
Hot subdwarf stars are a particular type of star that is crucial for
studying binary evolution and atmospheric diffusion processes. In
recent years, identifying hot subdwarfs by machine-learning methods
has become a hot topic, but there are still limitations in automation
and accuracy. In this paper, we proposed a robust identification
method based on a convolutional neural network. We first constructed
the data set using the spectral data of LAMOST DR7-V1. We then
constructed a hybrid recognition model including an eight-class
classification model and a binary classification model. The model
achieved an accuracy of 96.17% on the testing set. To further validate
the accuracy of the model, we selected 835 hot subdwarfs that were not
involved in the training process from the identified LAMOST catalog
(2428, including repeated observations) as the validation set. An
accuracy of 96.05% was achieved. On this basis, we used the model to
filter and classify all 10,640,255 spectra of LAMOST DR7-V1, and
obtained a catalog of 2393 hot subdwarf candidates, of which 2067 have
been confirmed. We found 25 new hot subdwarfs among the remaining
candidates by manual validation. The overall accuracy of the model is
87.42%. Overall, the model presented in this study can effectively
identify specific spectra with robust results and high accuracy, and
can be further applied to the classification of large-scale spectra
and the search for specific targets.
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
table4.dat 94 2393 Manual verification results of the 2393
hot subdwarf candidates
--------------------------------------------------------------------------------
See also:
V/146 : LAMOST DR1 catalogs (Luo+, 2015)
V/156 : LAMOST DR7 catalogs (Luo+, 2019)
J/MNRAS/380/1098 : UV-upturn of elliptical galaxies model (Han+, 2007)
J/A+A/549/A110 : Metal abundances of sdB stars (Geier, 2013)
J/ApJ/764/25 : FUSE spectra analysis of hot subdwarf stars (Jenkins, 2013)
J/ApJ/818/202 : Hot subdwarf stars in LAMOST DR1 (Luo+, 2016)
J/A+A/600/A50 : Catalog of hot subdwarf stars (Geier+, 2017)
J/ApJ/868/70 : Hot subdwarf stars from Gaia DR2 and LAMOST DR5 (Lei+, 2018)
J/ApJ/881/135 : Hot subdwarf stars from GaiaDR2 & LAMOST DR5. II. (Lei+, 2019)
J/A+A/621/A38 : Gaia catalogue of hot subluminous stars (Geier+, 2019)
J/ApJ/898/64 : Hot subdwarf stars from Gaia & LAMOST. II. RVs (Luo+, 2020)
J/ApJ/889/117 : Hot subdwarf stars from GaiaDR2 & LAMOSTDR6+7. I. (Lei+, 2020)
J/ApJS/256/28 : Hot subdwarf stars with GaiaDR2 & LAMOST DR7 data (Luo+, 2021)
Byte-by-byte Description of file: table4.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 20 A20 --- LAMOST LAMOST designation (JHHMMSS.ss+DDMMSS.s)
22- 30 I9 --- ObsID [106081/746810176] Unique number ID of
this spectrum
32- 41 F10.6 deg RAdeg Right Ascension in decimal degrees (J2000)
43- 51 F9.6 deg DEdeg [-7.14/82] Declination decimal degrees (J2000)
53- 58 F6.2 --- SNRg [2.18/629.1] Signal-to-Noise in g band
60- 65 F6.2 --- SNRu [0/436] Signal-to-Noise in u band
67- 74 F8.2 --- SNRz [0/411.3]?=-9999 Signal-to-Noise in z band
76- 83 F8.2 --- SNRr [0/579]?=-9999 Signal-to-Noise in r band
85- 92 F8.2 --- SNRi [0/608]?=-9999 Signal-to-Noise in i band
94 I1 --- Type [1/4] Type description code (1)
--------------------------------------------------------------------------------
Note (1): Type as follows:
1 = Hot subdwarfs that have been identified by previous work
(2067 occurrences).
2 = Newly discovered Hot subdwarfs (25 occurrences).
3 = Identified as other classes by manual validation (183 occurrences).
4 = Cannot determine the class due to low SNR (118 occurrences).
--------------------------------------------------------------------------------
History:
From electronic version of the journal
(End) Prepared by [AAS], Emmanuelle Perret [CDS] 03-Aug-2022