J/ApJS/276/53 White dwarfs from machine learning (Zhang+, 2025)
A multiple-detection-heads machine learning algorithm for detecting white
dwarfs.
Zhang J., Bu Y., Zhang M., Xie D., Yi Z.
<Astrophys. J. Suppl. Ser., 276, 53 (2025)>
=2025ApJS..276...53Z 2025ApJS..276...53Z
ADC_Keywords: Stars, white dwarf; Surveys; Optical
Keywords: White dwarf stars ; Astronomy data analysis ;
Astronomical object identification ; Astrostatistics
Abstract:
White dwarfs (WDs) are the ultimate stage for approximately 97% of
stars in the Milky Way and are crucial for studying stellar evolution
and galaxy structure. Due to their small size and low luminosity, WDs
are not easily observable. Traditional search methods mostly rely on
analyzing photometric parameters, which need high-quality data. In
recent years, machine learning has played a significant role in
astronomical data mining, due to its speed, real time, and precision.
However, we have identified two common issues. On the one hand, many
studies are based on high-quality spectral data, while a large amount
of image data remain underutilized. On the other hand, existing
astronomical algorithms are essentially classification algorithms,
with sample incompleteness being a critical weakness. In our study, we
propose the WD Network (WDNet) algorithm, which is a new object
detection algorithm that integrates multiple advanced technologies and
can directly locate WDs in images. WDNet overcomes the degradation
issue of WDs and detected 31,065 candidates in 80,448 images. The
candidates exhibit a wide range of types, including DA, DB, DC, DQ,
and DZ, with surface gravity within 7.8dex∼8.4dex, effective
temperatures within 10000K∼56000K, colors within -1<u-g<1 and
-0.8<g-r<0.4, and reduced proper motion within 20∼35mag. In the
future, WDNet will conduct large-scale searches using the Chinese
Space Station Telescope and Sloan Digital Sky Survey V.
Description:
In our experiments, we utilized the white dwarf (WD) catalog provided
by Kong & Luo (2021RNAAS...5..249K 2021RNAAS...5..249K) to crossmatch with SDSS DR17
(Abdurro'uf+ 2022, III/286) within 0.02'. We obtained 2640 images
containing WD targets. See Section 3.
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
table4.dat 117 31065 Candidates catalog
--------------------------------------------------------------------------------
See also:
III/210 : Spectroscopically Identified White Dwarfs (McCook+, 1999)
III/235 : Spectroscopically Identified White Dwarfs (McCook+, 2008)
V/156 : LAMOST DR7 catalogs (Luo+, 2019)
V/154 : Sloan Digital Sky Surveys (SDSS), Release 16 (DR16) (Ahumada+, 2020)
III/286 : APOGEE-2 DR17 final allStar catalog (Abdurro'uf+, 2022)
J/ApJS/156/47 : DA WDs from the Palomar Green Survey (Liebert+, 2005)
J/AJ/137/4377 : List of SEGUE plate pairs (Yanny+, 2009)
J/other/SCPMA/57.176 : Carbon stars & DZ white dwarfs in SDSS sp. (Si+ 2014)
J/MNRAS/472/4173 : Bright white dwarfs for high-speed photometry (Raddi+, 2017)
J/ApJS/234/31 : Carbon stars from LAMOST using machine learning (Li+, 2018)
J/MNRAS/482/4570 : Gaia DR2 white dwarf candidates (Gentile Fusillo+, 2019)
J/MNRAS/485/5573 : Gaia-DR2 100pc white dwarf population (Torres+, 2019)
J/ApJ/883/175 : 1st release of the MaNGA Stellar Library (Yan+, 2019)
J/MNRAS/508/3877 : Catalogue of white dwarfs in Gaia EDR3 (Gentile+, 2021)
J/MNRAS/506/1651 : XGBoost ML classifier of BASS DR3 sources (Li+, 2021)
J/A+A/662/A40 : Hot subdwarf stars studied with Gaia (Culpan+, 2022)
J/MNRAS/509/2674 : White dwarfs in LAMOST DR5 (Guo+, 2022)
J/A+A/679/A127 : 100pc WD spectral classification (Garcia-Zamora+, 2023)
J/A+A/678/A20 : New white dwarf-open cluster associations (Prisegen+, 2023)
J/ApJS/268/28 : LAMOST DR9 white dwarf cand. from deep-learning (Tan+, 2023)
J/ApJS/269/59 : Low-surface-brightness galaxy cand. from SDSS (Xing+, 2023)
J/A+A/682/A5 : Gaia white dwarfs Classification (Vincent+, 2024)
http://www.sdss.org/ : SDSS homepage
http://www.lamost.org/ : LAMOST homepage
http://www.montrealwhitedwarfdatabase.org/ : Montreal WD Database (MWDD) home
Byte-by-byte Description of file: table4.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 5 I5 --- Seq [1/31065] Unique ID of candidates
7- 14 F8.6 --- Conf [0.4/0.98] Probability of being a White Dwarf
16- 28 F13.9 deg RAdeg Right ascension (J2000)
30- 42 F13.9 deg DEdeg [-24.6/84.7] Declination (J2000)
44- 53 A10 --- TypeSDSS Certification labels from SDSS DR17 (1)
55- 56 A2 --- TypeLAMOST Certification labels from LAMOST DR10 (2)
58- 93 A36 --- TypeMWDD Certification labels from MWDD
(Dufour+ 2017ASPC..509....3D 2017ASPC..509....3D)
95- 105 F11.9 [-] logg [7.73/8.52]? Log of surface gravity from
Machine Learning
107- 117 F11.5 K Teff [10926/61383]? Effective temperature from
Machine Learning
--------------------------------------------------------------------------------
Note (1): Labels from SDSS (III/286) as follows:
CalciumWD = 46 occurrences
CarbonWD = 13 occurrences
WD = 3609 occurrences
WDcooler = 113 occurrences
WDhotter = 1257 occurrences
WDmagnetic = 61 occurrences
Note (2): Labels from LAMOST as follows:
DA = 926 occurrences
DB = 88 occurrences
DC = 13 occurrences
DZ = 4 occurrences
--------------------------------------------------------------------------------
History:
From electronic version of the journal
(End) Prepared by [AAS], Emmanuelle Perret [CDS] 30-Oct-2025