TY - JOUR

T1 - J-PLUS

T2 - Support vector machine applied to STAR-GALAXY-QSO classification

AU - Wang, C.

AU - Bai, Y.

AU - López-Sanjuan, C.

AU - Yuan, H.

AU - Wang, S.

AU - Liu, J.

AU - Sobral, D.

AU - Baqui, P.O.

AU - Martín, E.L.

AU - Andres Galarza, C.

AU - Alcaniz, J.

AU - Angulo, R.E.

AU - Cenarro, A.J.

AU - Cristóbal-Hornillos, D.

AU - Dupke, R.A.

AU - Ederoclite, A.

AU - Hernández-Monteagudo, C.

AU - Marín-Franch, A.

AU - Moles, M.

AU - Sodré, L.

AU - Vázquez Ramió, H.

AU - Varela, J.

PY - 2022/3/31

Y1 - 2022/3/31

N2 - Context. In modern astronomy, machine learning has proved to be efficient and effective in mining big data from the newest telescopes. Aims. In this study, we construct a supervised machine-learning algorithm to classify the objects in the Javalambre Photometric Local Universe Survey first data release (J-PLUS DR1). Methods. The sample set is featured with 12-waveband photometry and labeled with spectrum-based catalogs, including Sloan Digital Sky Survey spectroscopic data, the Large Sky Area Multi-Object Fiber Spectroscopic Telescope, and VERONCAT a the Veron Catalog of Quasars AGN. The performance of the classifier is presented with the applications of blind test validations based on RAdial Velocity Extension, the Kepler Input Catalog, the Two Micron All Sky Survey Redshift Survey, and the UV-bright Quasar Survey. A new algorithm was applied to constrain the potential extrapolation that could decrease the performance of the machine-learning classifier. Results. The accuracies of the classifier are 96.5% in the blind test and 97.0% in training cross-validation. The F1-scores for each class are presented to show the balance between the precision and the recall of the classifier. We also discuss different methods to constrain the potential extrapolation.

AB - Context. In modern astronomy, machine learning has proved to be efficient and effective in mining big data from the newest telescopes. Aims. In this study, we construct a supervised machine-learning algorithm to classify the objects in the Javalambre Photometric Local Universe Survey first data release (J-PLUS DR1). Methods. The sample set is featured with 12-waveband photometry and labeled with spectrum-based catalogs, including Sloan Digital Sky Survey spectroscopic data, the Large Sky Area Multi-Object Fiber Spectroscopic Telescope, and VERONCAT a the Veron Catalog of Quasars AGN. The performance of the classifier is presented with the applications of blind test validations based on RAdial Velocity Extension, the Kepler Input Catalog, the Two Micron All Sky Survey Redshift Survey, and the UV-bright Quasar Survey. A new algorithm was applied to constrain the potential extrapolation that could decrease the performance of the machine-learning classifier. Results. The accuracies of the classifier are 96.5% in the blind test and 97.0% in training cross-validation. The F1-scores for each class are presented to show the balance between the precision and the recall of the classifier. We also discuss different methods to constrain the potential extrapolation.

KW - Astronomical databases: miscellaneous

KW - Methods: data analysis

KW - Techniques: spectroscopic

U2 - 10.1051/0004-6361/202142254

DO - 10.1051/0004-6361/202142254

M3 - Journal article

VL - 659

JO - Astronomy and Astrophysics

JF - Astronomy and Astrophysics

SN - 1432-0746

M1 - A144

ER -