VEXAS: VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Standard

VEXAS : VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere. / Khramtsov, V.; Spiniello, C.; Agnello, A.; Sergeyev, A.

I: Astronomy & Astrophysics, Bind 651, A69, 16.07.2021.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Harvard

Khramtsov, V, Spiniello, C, Agnello, A & Sergeyev, A 2021, 'VEXAS: VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere', Astronomy & Astrophysics, bind 651, A69. https://doi.org/10.1051/0004-6361/202040131

APA

Khramtsov, V., Spiniello, C., Agnello, A., & Sergeyev, A. (2021). VEXAS: VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere. Astronomy & Astrophysics, 651, [A69]. https://doi.org/10.1051/0004-6361/202040131

Vancouver

Khramtsov V, Spiniello C, Agnello A, Sergeyev A. VEXAS: VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere. Astronomy & Astrophysics. 2021 jul. 16;651. A69. https://doi.org/10.1051/0004-6361/202040131

Author

Khramtsov, V. ; Spiniello, C. ; Agnello, A. ; Sergeyev, A. / VEXAS : VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere. I: Astronomy & Astrophysics. 2021 ; Bind 651.

Bibtex

@article{1116aa5a5db2413dadc2b0fb8e35ccb9,
title = "VEXAS: VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere",
abstract = "Context. We present the second public data release of the VISTA EXtension to Auxiliary Surveys (VEXAS), where we classify objects into stars, galaxies, and quasars based on an ensemble of machine learning algorithms.Aims. The aim of VEXAS is to build the widest multi-wavelength catalogue, providing reference magnitudes, colours, and morphological information for a large number of scientific uses.Methods. We applied an ensemble of thirty-two different machine learning models, based on three different algorithms and on different magnitude sets, training samples, and classification problems (two or three classes) on the three VEXAS Data Release 1 (DR1) optical and infrared (IR) tables. The tables were created in DR1 cross-matching VISTA near-infrared data with Wide-field Infrared Survey Explorer far-infrared data and with optical magnitudes from the Dark Energy Survey (VEXAS-DESW), the Sky Mapper Survey (VEXAS-SMW), and the Panoramic Survey Telescope and Rapid Response System Survey (VEXAS-PSW). We assembled a large table of spectroscopically confirmed objects (VEXAS-SPEC-GOOD, 415 628 unique objects), based on the combination of six different spectroscopic surveys that we used for training. We developed feature imputation to also classify objects for which magnitudes in one or more bands are missing.Results. We classify in total approximate to 90x10(6) objects in the Southern Hemisphere. Among these, approximate to 62.9x10(6) (approximate to 52.6x10(6)) are classified as 'high confidence' ('secure') stars, approximate to 920 000 (approximate to 750 000) as 'high confidence' ('secure') quasars, and approximate to 34.8 (approximate to 34.1) million as 'high confidence' ('secure') galaxies, with p(class)>= 0.7 (p(class)>= 0.9). The DR2 tables update the DR1 with the addition of imputed magnitudes and membership probabilities to each of the three classes.Conclusions. The density of high-confidence extragalactic objects varies strongly with the survey depth: at p(class)>0.7, there are 11 deg(-2) quasars in the VEXAS-DESW footprint and 103 deg(-2) in the VEXAS-PSW footprint, while only 10.7 deg(-2) in the VEXAS-SM footprint. Improved depth in the mid-infrared and coverage in the optical and near-infrared are needed for the SM footprint that is not already covered by DESW and PSW.",
keywords = "astronomical databases: miscellaneous, catalogs, surveys, methods: data analysis, virtual observatory tools, DARK ENERGY SURVEY, GRAVITATIONALLY LENSED QUASARS, OSCILLATION SPECTROSCOPIC SURVEY, PHOTOMETRIC SYSTEM CALIBRATION, RADIO IMAGING SURVEY, QSO REDSHIFT SURVEY, KILO-DEGREE SURVEY, SURVEY DESIGN, GALAXY-EVOLUTION, NUMBER COUNTS",
author = "V. Khramtsov and C. Spiniello and A. Agnello and A. Sergeyev",
year = "2021",
month = jul,
day = "16",
doi = "10.1051/0004-6361/202040131",
language = "English",
volume = "651",
journal = "Astronomy & Astrophysics",
issn = "0004-6361",
publisher = "E D P Sciences",

}

RIS

TY - JOUR

T1 - VEXAS

T2 - VISTA EXtension to Auxiliary Surveys: Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere

AU - Khramtsov, V.

AU - Spiniello, C.

AU - Agnello, A.

AU - Sergeyev, A.

PY - 2021/7/16

Y1 - 2021/7/16

N2 - Context. We present the second public data release of the VISTA EXtension to Auxiliary Surveys (VEXAS), where we classify objects into stars, galaxies, and quasars based on an ensemble of machine learning algorithms.Aims. The aim of VEXAS is to build the widest multi-wavelength catalogue, providing reference magnitudes, colours, and morphological information for a large number of scientific uses.Methods. We applied an ensemble of thirty-two different machine learning models, based on three different algorithms and on different magnitude sets, training samples, and classification problems (two or three classes) on the three VEXAS Data Release 1 (DR1) optical and infrared (IR) tables. The tables were created in DR1 cross-matching VISTA near-infrared data with Wide-field Infrared Survey Explorer far-infrared data and with optical magnitudes from the Dark Energy Survey (VEXAS-DESW), the Sky Mapper Survey (VEXAS-SMW), and the Panoramic Survey Telescope and Rapid Response System Survey (VEXAS-PSW). We assembled a large table of spectroscopically confirmed objects (VEXAS-SPEC-GOOD, 415 628 unique objects), based on the combination of six different spectroscopic surveys that we used for training. We developed feature imputation to also classify objects for which magnitudes in one or more bands are missing.Results. We classify in total approximate to 90x10(6) objects in the Southern Hemisphere. Among these, approximate to 62.9x10(6) (approximate to 52.6x10(6)) are classified as 'high confidence' ('secure') stars, approximate to 920 000 (approximate to 750 000) as 'high confidence' ('secure') quasars, and approximate to 34.8 (approximate to 34.1) million as 'high confidence' ('secure') galaxies, with p(class)>= 0.7 (p(class)>= 0.9). The DR2 tables update the DR1 with the addition of imputed magnitudes and membership probabilities to each of the three classes.Conclusions. The density of high-confidence extragalactic objects varies strongly with the survey depth: at p(class)>0.7, there are 11 deg(-2) quasars in the VEXAS-DESW footprint and 103 deg(-2) in the VEXAS-PSW footprint, while only 10.7 deg(-2) in the VEXAS-SM footprint. Improved depth in the mid-infrared and coverage in the optical and near-infrared are needed for the SM footprint that is not already covered by DESW and PSW.

AB - Context. We present the second public data release of the VISTA EXtension to Auxiliary Surveys (VEXAS), where we classify objects into stars, galaxies, and quasars based on an ensemble of machine learning algorithms.Aims. The aim of VEXAS is to build the widest multi-wavelength catalogue, providing reference magnitudes, colours, and morphological information for a large number of scientific uses.Methods. We applied an ensemble of thirty-two different machine learning models, based on three different algorithms and on different magnitude sets, training samples, and classification problems (two or three classes) on the three VEXAS Data Release 1 (DR1) optical and infrared (IR) tables. The tables were created in DR1 cross-matching VISTA near-infrared data with Wide-field Infrared Survey Explorer far-infrared data and with optical magnitudes from the Dark Energy Survey (VEXAS-DESW), the Sky Mapper Survey (VEXAS-SMW), and the Panoramic Survey Telescope and Rapid Response System Survey (VEXAS-PSW). We assembled a large table of spectroscopically confirmed objects (VEXAS-SPEC-GOOD, 415 628 unique objects), based on the combination of six different spectroscopic surveys that we used for training. We developed feature imputation to also classify objects for which magnitudes in one or more bands are missing.Results. We classify in total approximate to 90x10(6) objects in the Southern Hemisphere. Among these, approximate to 62.9x10(6) (approximate to 52.6x10(6)) are classified as 'high confidence' ('secure') stars, approximate to 920 000 (approximate to 750 000) as 'high confidence' ('secure') quasars, and approximate to 34.8 (approximate to 34.1) million as 'high confidence' ('secure') galaxies, with p(class)>= 0.7 (p(class)>= 0.9). The DR2 tables update the DR1 with the addition of imputed magnitudes and membership probabilities to each of the three classes.Conclusions. The density of high-confidence extragalactic objects varies strongly with the survey depth: at p(class)>0.7, there are 11 deg(-2) quasars in the VEXAS-DESW footprint and 103 deg(-2) in the VEXAS-PSW footprint, while only 10.7 deg(-2) in the VEXAS-SM footprint. Improved depth in the mid-infrared and coverage in the optical and near-infrared are needed for the SM footprint that is not already covered by DESW and PSW.

KW - astronomical databases: miscellaneous

KW - catalogs

KW - surveys

KW - methods: data analysis

KW - virtual observatory tools

KW - DARK ENERGY SURVEY

KW - GRAVITATIONALLY LENSED QUASARS

KW - OSCILLATION SPECTROSCOPIC SURVEY

KW - PHOTOMETRIC SYSTEM CALIBRATION

KW - RADIO IMAGING SURVEY

KW - QSO REDSHIFT SURVEY

KW - KILO-DEGREE SURVEY

KW - SURVEY DESIGN

KW - GALAXY-EVOLUTION

KW - NUMBER COUNTS

U2 - 10.1051/0004-6361/202040131

DO - 10.1051/0004-6361/202040131

M3 - Journal article

VL - 651

JO - Astronomy & Astrophysics

JF - Astronomy & Astrophysics

SN - 0004-6361

M1 - A69

ER -

ID: 279127967