The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database â

Dae Won Kim, Pavlos Protopapas, Coryn A.L. Bailer-Jones, Yong Ik Byun, Seo Won Chang, Jean Baptiste Marquette, Min Su Shin

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

The EPOCH (EROS-2 periodic variable star classification using machine learning) project aims to detect periodic variable stars in the EROS-2 light curve database. In this paper, we present the first result of the classification of periodic variable stars in the EROS-2 LMC database. To classify these variables, we first built a training set by compiling known variables in the Large Magellanic Cloud area from the OGLE and MACHO surveys. We crossmatched these variables with the EROS-2 sources and extracted 22 variability features from 28âE 392 light curves of the corresponding EROS-2 sources. We then used the random forest method to classify the EROS-2 sources in the training set. We designed the model to separate not only δ Scuti stars, RR Lyraes, Cepheids, eclipsing binaries, and long-period variables, the superclasses, but also their subclasses, such as RRab, RRc, RRd, and RRe for RR Lyraes, and similarly for the other variable types. The model trained using only the superclasses shows 99% recall and precision, while the model trained on all subclasses shows 87% recall and precision. We applied the trained model to the entire EROS-2 LMC database, which contains about 29 million sources, and found 117234 periodic variable candidates. Out of these 117234 periodic variables, 55 285 have not been discovered by either OGLE or MACHO variability studies. This set comprises 1906 δ Scuti stars, 6607 RR Lyraes, 638 Cepheids, 178 Type II Cepheids, 34562 eclipsing binaries, and 11394 long-period variables.

Original languageEnglish
Article number47
JournalAstronomy and Astrophysics
Volume566
DOIs
Publication statusPublished - 2014 Jun

Fingerprint

EROS (satellites)
variable stars
massive compact halo objects
Mira variables
light curve
education
stars
machine learning
Magellanic clouds
project

All Science Journal Classification (ASJC) codes

  • Astronomy and Astrophysics
  • Space and Planetary Science

Cite this

Kim, D. W., Protopapas, P., Bailer-Jones, C. A. L., Byun, Y. I., Chang, S. W., Marquette, J. B., & Shin, M. S. (2014). The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database â. Astronomy and Astrophysics, 566, [47]. https://doi.org/10.1051/0004-6361/201323252
Kim, Dae Won ; Protopapas, Pavlos ; Bailer-Jones, Coryn A.L. ; Byun, Yong Ik ; Chang, Seo Won ; Marquette, Jean Baptiste ; Shin, Min Su. / The EPOCH Project : I. Periodic variable stars in the EROS-2 LMC database â. In: Astronomy and Astrophysics. 2014 ; Vol. 566.
@article{6cb0aa3bcb8f432199335eb493505b5f,
title = "The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database {\^a}",
abstract = "The EPOCH (EROS-2 periodic variable star classification using machine learning) project aims to detect periodic variable stars in the EROS-2 light curve database. In this paper, we present the first result of the classification of periodic variable stars in the EROS-2 LMC database. To classify these variables, we first built a training set by compiling known variables in the Large Magellanic Cloud area from the OGLE and MACHO surveys. We crossmatched these variables with the EROS-2 sources and extracted 22 variability features from 28{\^a}E 392 light curves of the corresponding EROS-2 sources. We then used the random forest method to classify the EROS-2 sources in the training set. We designed the model to separate not only δ Scuti stars, RR Lyraes, Cepheids, eclipsing binaries, and long-period variables, the superclasses, but also their subclasses, such as RRab, RRc, RRd, and RRe for RR Lyraes, and similarly for the other variable types. The model trained using only the superclasses shows 99{\%} recall and precision, while the model trained on all subclasses shows 87{\%} recall and precision. We applied the trained model to the entire EROS-2 LMC database, which contains about 29 million sources, and found 117234 periodic variable candidates. Out of these 117234 periodic variables, 55 285 have not been discovered by either OGLE or MACHO variability studies. This set comprises 1906 δ Scuti stars, 6607 RR Lyraes, 638 Cepheids, 178 Type II Cepheids, 34562 eclipsing binaries, and 11394 long-period variables.",
author = "Kim, {Dae Won} and Pavlos Protopapas and Bailer-Jones, {Coryn A.L.} and Byun, {Yong Ik} and Chang, {Seo Won} and Marquette, {Jean Baptiste} and Shin, {Min Su}",
year = "2014",
month = "6",
doi = "10.1051/0004-6361/201323252",
language = "English",
volume = "566",
journal = "Astronomy and Astrophysics",
issn = "0004-6361",
publisher = "EDP Sciences",

}

Kim, DW, Protopapas, P, Bailer-Jones, CAL, Byun, YI, Chang, SW, Marquette, JB & Shin, MS 2014, 'The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database â', Astronomy and Astrophysics, vol. 566, 47. https://doi.org/10.1051/0004-6361/201323252

The EPOCH Project : I. Periodic variable stars in the EROS-2 LMC database â. / Kim, Dae Won; Protopapas, Pavlos; Bailer-Jones, Coryn A.L.; Byun, Yong Ik; Chang, Seo Won; Marquette, Jean Baptiste; Shin, Min Su.

In: Astronomy and Astrophysics, Vol. 566, 47, 06.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The EPOCH Project

T2 - I. Periodic variable stars in the EROS-2 LMC database â

AU - Kim, Dae Won

AU - Protopapas, Pavlos

AU - Bailer-Jones, Coryn A.L.

AU - Byun, Yong Ik

AU - Chang, Seo Won

AU - Marquette, Jean Baptiste

AU - Shin, Min Su

PY - 2014/6

Y1 - 2014/6

N2 - The EPOCH (EROS-2 periodic variable star classification using machine learning) project aims to detect periodic variable stars in the EROS-2 light curve database. In this paper, we present the first result of the classification of periodic variable stars in the EROS-2 LMC database. To classify these variables, we first built a training set by compiling known variables in the Large Magellanic Cloud area from the OGLE and MACHO surveys. We crossmatched these variables with the EROS-2 sources and extracted 22 variability features from 28âE 392 light curves of the corresponding EROS-2 sources. We then used the random forest method to classify the EROS-2 sources in the training set. We designed the model to separate not only δ Scuti stars, RR Lyraes, Cepheids, eclipsing binaries, and long-period variables, the superclasses, but also their subclasses, such as RRab, RRc, RRd, and RRe for RR Lyraes, and similarly for the other variable types. The model trained using only the superclasses shows 99% recall and precision, while the model trained on all subclasses shows 87% recall and precision. We applied the trained model to the entire EROS-2 LMC database, which contains about 29 million sources, and found 117234 periodic variable candidates. Out of these 117234 periodic variables, 55 285 have not been discovered by either OGLE or MACHO variability studies. This set comprises 1906 δ Scuti stars, 6607 RR Lyraes, 638 Cepheids, 178 Type II Cepheids, 34562 eclipsing binaries, and 11394 long-period variables.

AB - The EPOCH (EROS-2 periodic variable star classification using machine learning) project aims to detect periodic variable stars in the EROS-2 light curve database. In this paper, we present the first result of the classification of periodic variable stars in the EROS-2 LMC database. To classify these variables, we first built a training set by compiling known variables in the Large Magellanic Cloud area from the OGLE and MACHO surveys. We crossmatched these variables with the EROS-2 sources and extracted 22 variability features from 28âE 392 light curves of the corresponding EROS-2 sources. We then used the random forest method to classify the EROS-2 sources in the training set. We designed the model to separate not only δ Scuti stars, RR Lyraes, Cepheids, eclipsing binaries, and long-period variables, the superclasses, but also their subclasses, such as RRab, RRc, RRd, and RRe for RR Lyraes, and similarly for the other variable types. The model trained using only the superclasses shows 99% recall and precision, while the model trained on all subclasses shows 87% recall and precision. We applied the trained model to the entire EROS-2 LMC database, which contains about 29 million sources, and found 117234 periodic variable candidates. Out of these 117234 periodic variables, 55 285 have not been discovered by either OGLE or MACHO variability studies. This set comprises 1906 δ Scuti stars, 6607 RR Lyraes, 638 Cepheids, 178 Type II Cepheids, 34562 eclipsing binaries, and 11394 long-period variables.

UR - http://www.scopus.com/inward/record.url?scp=84902076715&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902076715&partnerID=8YFLogxK

U2 - 10.1051/0004-6361/201323252

DO - 10.1051/0004-6361/201323252

M3 - Article

AN - SCOPUS:84902076715

VL - 566

JO - Astronomy and Astrophysics

JF - Astronomy and Astrophysics

SN - 0004-6361

M1 - 47

ER -