Get access

Random forest automated supervised classification of Hipparcos periodic variable stars

Authors

  • P. Dubath,

    Corresponding author
    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • L. Rimoldini,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • M. Süveges,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • J. Blomme,

    1. Instituut voor Sterrenkunde, K. U. Leuven, Celestijnenlaan 200D, 3001 Leuven, Belgium
    Search for more papers by this author
  • M. López,

    1. Centro de Astrobiología (INTA-CSIC), Departamento de Astrofísica, PO Box 78, E-28691 Villanueva de la Cañada, Spain
    Search for more papers by this author
  • L. M. Sarro,

    1. Dpt. de Inteligencia Artificial, UNED, Juan del Rosal, 16, 28040 Madrid, Spain
    Search for more papers by this author
  • J. De Ridder,

    1. Instituut voor Sterrenkunde, K. U. Leuven, Celestijnenlaan 200D, 3001 Leuven, Belgium
    Search for more papers by this author
  • J. Cuypers,

    1. Royal Observatory of Belgium, Ringlaan 3, 1180 Brussels, Belgium
    Search for more papers by this author
  • L. Guy,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • I. Lecoeur,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • K. Nienartowicz,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • A. Jan,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • M. Beck,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • N. Mowlavi,

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author
  • P. De Cat,

    1. Royal Observatory of Belgium, Ringlaan 3, 1180 Brussels, Belgium
    Search for more papers by this author
  • T. Lebzelter,

    1. University of Vienna, Department of Astronomy, Türkenschanzstrasse 17, A1180 Vienna, Austria
    Search for more papers by this author
  • L. Eyer

    1. Observatoire astronomique de l’Université de Genève, ch. des Maillettes 51, 1290 Versoix, Switzerland
    2. ISDC Data Center For Astronphysics, ch. d’Ecogia 16, 1290 Versoix, Switzerland
    Search for more papers by this author

E-mail: pierre.dubath@unige.ch

ABSTRACT

We present an evaluation of the performance of an automated classification of the Hipparcos periodic variable stars into 26 types. The sub-sample with the most reliable variability types available in the literature is used to train supervised algorithms to characterize the type dependencies on a number of attributes. The most useful attributes evaluated with the random forest methodology include, in decreasing order of importance, the period, the amplitude, the VI colour index, the absolute magnitude, the residual around the folded light-curve model, the magnitude distribution skewness and the amplitude of the second harmonic of the Fourier series model relative to that of the fundamental frequency. Random forests and a multi-stage scheme involving Bayesian network and Gaussian mixture methods lead to statistically equivalent results. In standard 10-fold cross-validation (CV) experiments, the rate of correct classification is between 90 and 100 per cent, depending on the variability type. The main mis-classification cases, up to a rate of about 10 per cent, arise due to confusion between SPB and ACV blue variables and between eclipsing binaries, ellipsoidal variables and other variability types. Our training set and the predicted types for the other Hipparcos periodic stars are available online.

Ancillary