Machine-learning Regression of Stellar Effective Temperatures in the Second Gaia Data Release

被引:55
作者
Bai, Yu [1 ]
Lu, JiFeng [1 ,2 ]
Bai, ZhongRui [1 ]
Wang, Song [1 ]
Fan, DongWei [3 ]
机构
[1] Chinese Acad Sci, Natl Astron Observ, Key Lab Opt Astron, 20A Datun Rd, Beijing 100012, Peoples R China
[2] Univ Chinese Acad Sci, Coll Astron & Space Sci, Beijing 100049, Peoples R China
[3] Chinese Acad Sci, Natl Astron Observ, 20A Datun Rd, Beijing 100012, Peoples R China
基金
美国安德鲁·梅隆基金会; 中国国家自然科学基金;
关键词
methods: data analysis; stars: fundamental parameters; techniques: spectroscopic; SEGUE; DISTANCE; STARS; III;
D O I
10.3847/1538-3881/ab3048
中图分类号
P1 [天文学];
学科分类号
0704 ;
摘要
This paper reports on the application of the supervised machine-learning algorithm to the stellar effective temperature regression for the second Gaia data release, based on the combination of the stars in four spectroscopic surveys: the Large Sky Area Multi-Object Fiber Spectroscopic Telescope, Sloan Extension for Galactic Understanding and Exploration, the Apache Point Observatory Galactic Evolution Experiment, and the Radial Velocity Extension. This combination, of about four million stars, enables us to construct one of the largest training samples for the regression and further predict reliable stellar temperatures with a rms error of 191 K. This result is more precise than that given by the Gaia second data release that is based on about sixty thousands stars. After a series of data cleaning processes, the input features that feed the regressor are carefully selected from the Gaia parameters, including the colors, the 3D position, and the proper motion. These Gaia parameters are used to predict effective temperatures for 132,739,323 valid stars in the second Gaia data release. We also present a new method for blind tests and a test for external regression without additional data. The machine-learning algorithm fed with the parameters only in one catalog provides us with an effective approach to maximize the sample size for prediction, and this methodology has a wide application prospect in future studies of astrophysics.
引用
收藏
页数:6
相关论文
共 38 条
[1]   First stellar parameters from Apsis [J].
Andrae, Rene ;
Fouesneau, Morgan ;
Creevey, Orlagh ;
Ordenovic, Christophe ;
Mary, Nicolas ;
Burlacu, Alexandru ;
Chaoul, Laurence ;
Jean-Antoine-Piccolo, Anne ;
Kordopatis, Georges ;
Korn, Andreas ;
Lebreton, Yveline ;
Panem, Chantal ;
Pichon, Bernard ;
Thevenin, Frederic ;
Walmsley, Gavin ;
Bailer-Jones, Coryn A. L. .
ASTRONOMY & ASTROPHYSICS, 2018, 616
[2]   Machine Learning Applied to Star-Galaxy-QSO Classification and Stellar Effective Temperature Regression [J].
Bai, Yu ;
Liu, JiFeng ;
Wang, Song ;
Yang, Fan .
ASTRONOMICAL JOURNAL, 2019, 157 (01)
[3]   Machine learning classification of Gaia Data Release 2 [J].
Bai, Yu ;
Liu, Ji-Feng ;
Wang, Song .
RESEARCH IN ASTRONOMY AND ASTROPHYSICS, 2018, 18 (10)
[4]   Estimating Distances from Parallaxes. V. Geometric and Photogeometric Distances to 1.47 Billion Stars in Gaia Early Data Release 3 [J].
Bailer-Jones, C. A. L. ;
Rybizki, J. ;
Fouesneau, M. ;
Demleitner, M. ;
Andrae, R. .
ASTRONOMICAL JOURNAL, 2021, 161 (03)
[5]   The Gaia astrophysical parameters inference system (Apsis) Pre-launch description [J].
Bailer-Jones, C. A. L. ;
Andrae, R. ;
Arcay, B. ;
Astraatmadja, T. ;
Bellas-Velidis, I. ;
Berihuete, A. ;
Bijaoui, A. ;
Carrion, C. ;
Dafonte, C. ;
Damerdji, Y. ;
Dapergolas, A. ;
de Laverny, P. ;
Delchambre, L. ;
Drazinos, P. ;
Drimmel, R. ;
Fremat, Y. ;
Fustes, D. ;
Garcia-Torres, M. ;
Guede, C. ;
Heiter, U. ;
Janotto, A. -M. ;
Karampelas, A. ;
Kim, D. -W. ;
Knude, J. ;
Kolka, I. ;
Kontizas, E. ;
Kontizas, M. ;
Korn, A. J. ;
Lanzafame, A. C. ;
Lebreton, Y. ;
Lindstrom, H. ;
Liu, C. ;
Livanou, E. ;
Lobel, A. ;
Manteiga, M. ;
Martayan, C. ;
Ordenovic, Ch. ;
Pichon, B. ;
Recio-Blanco, A. ;
Rocca-Volmerange, B. ;
Sarro, L. M. ;
Smith, K. ;
Sordo, R. ;
Soubiran, C. ;
Surdej, J. ;
Thevenin, F. ;
Tsalmantza, P. ;
Vallenari, A. ;
Zorec, J. .
ASTRONOMY & ASTROPHYSICS, 2013, 559
[6]   Scaling to very very large corpora for natural language disambiguation [J].
Banko, M ;
Brill, E .
39TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 2001, :26-33
[7]   Parameter estimation from a model grid application to the Gaia RVS spectra [J].
Bijaoui, A. ;
Recio-Blanco, A. ;
de Laverny, P. ;
Ordenovic, C. .
STATISTICAL METHODOLOGY, 2012, 9 (1-2) :55-62
[8]   Comparison of Different Interpolation Algorithm in Feature-based Template Matching for Stellar Parameters Analysis [J].
BingDu ;
Luo, ALi ;
Zhang, JianNan ;
YueWu ;
Wang, FengFei .
SOFTWARE AND CYBERINFRASTRUCTURE FOR ASTRONOMY II, 2012, 8451
[9]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[10]  
Brown A.G.A., 2018, A&A, V616, pA1, DOI [10.1051/0004-6361/201833051, DOI 10.1051/0004-6361/201833051]