AUTOMATED CLASSIFICATION OF PERIODIC VARIABLE STARS DETECTED BY THE WIDE-FIELD INFRARED SURVEY EXPLORER

We describe a methodology to classify periodic variable stars identified using photometric time-series measurements constructed from the Wide-field Infrared Survey Explorer (WISE) full-mission single-exposure Source Databases. This will assist in the future construction of a WISE Variable Source Database that assigns variables to specific science classes as constrained by the WISE observing cadence with statistically meaningful classification probabilities. We have analyzed the WISE light curves of 8273 variable stars identified in previous optical variability surveys (MACHO, GCVS, and ASAS) and show that Fourier decomposition techniques can be extended into the mid-IR to assist with their classification. Combined with other periodic light-curve features, this sample is then used to train a machine-learned classifier based on the random forest (RF) method. Consistent with previous classification studies of variable stars in general, the RF machine-learned classifier is superior to other methods in terms of accuracy, robustness against outliers, and relative immunity to features that carry little or redundant class information. For the three most common classes identified by WISE: Algols, RR Lyrae, and W Ursae Majoris type variables, we obtain classification efficiencies of 80.7%, 82.7%, and 84.5% respectively using cross-validation analyses, with 95% confidence intervals of approximately ±2%. These accuracies are achieved at purity (or reliability) levels of 88.5%, 96.2%, and 87.8% respectively, similar to that achieved in previous automated classification studies of periodic variable stars.

[1]  Nathaniel R. Butler,et al.  Mid-infrared period–luminosity relations of RR Lyrae stars derived from the AllWISE Data Release , 2014, 1402.4449.

[2]  A. Dambis,et al.  Mid-infrared period-luminosity relations for globular cluster RR Lyrae , 2014, 1401.5523.

[3]  Dominic J. Benford,et al.  Explanatory Supplement to the AllWISE Data Release Products , 2013, WISE 2013.

[4]  Wendy L. Freedman,et al.  A PRELIMINARY CALIBRATION OF THE RR LYRAE PERIOD–LUMINOSITY RELATION AT MID-INFRARED WAVELENGTHS: WISE DATA , 2013, 1308.3160.

[5]  M. Park,et al.  Classification of Variable Stars Using Thick-Pen Transform Method , 2013 .

[6]  M. Wainwright,et al.  Using machine learning for discovery in synoptic survey imaging data , 2012, 1209.3775.

[7]  VARIABILITY FLAGGING IN THE WIDE-FIELD INFRARED SURVEY EXPLORER PRELIMINARY DATA RELEASE , 2012 .

[8]  Dominic J. Benford,et al.  Explanatory Supplement to the WISE All-Sky Data Release Products , 2012, WISE 2012.

[9]  Noureddine El Karoui,et al.  Optimizing Automated Classification of Variable Stars in New Synoptic Surveys , 2012, 1201.4863.

[10]  Tamara Broderick,et al.  RAPID, MACHINE-LEARNED RESOURCE ALLOCATION: APPLICATION TO HIGH-REDSHIFT GAMMA-RAY BURST FOLLOW-UP , 2011, 1112.3654.

[11]  E. O. Ofek,et al.  Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era , 2011, 1106.5491.

[12]  Pavlos Protopapas,et al.  QUASI-STELLAR OBJECT SELECTION ALGORITHM USING TIME VARIABILITY AND MACHINE LEARNING: SELECTION OF 1620 QUASI-STELLAR OBJECT CANDIDATES FROM MACHO LARGE MAGELLANIC CLOUD DATABASE , 2011 .

[13]  Adam A. Miller,et al.  ACTIVE LEARNING TO OVERCOME SAMPLE SELECTION BIAS: APPLICATION TO PHOTOMETRIC VARIABLE STAR CLASSIFICATION , 2011, 1106.2832.

[14]  Nathaniel R. Butler,et al.  MID-INFRARED PERIOD–LUMINOSITY RELATIONS OF RR LYRAE STARS DERIVED FROM THE WISE PRELIMINARY DATA RELEASE , 2011, 1105.0055.

[15]  E. L. Wright,et al.  PRELIMINARY RESULTS FROM NEOWISE: AN ENHANCEMENT TO THE WIDE-FIELD INFRARED SURVEY EXPLORER FOR SOLAR SYSTEM SCIENCE , 2011, 1102.1996.

[16]  Pavlos Protopapas,et al.  QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database , 2011, 1101.3316.

[17]  P. Dubath,et al.  Random forest automated supervised classification of Hipparcos periodic variable stars , 2011, 1101.2406.

[18]  J. Richards,et al.  ON MACHINE-LEARNED CLASSIFICATION OF VARIABLE STARS WITH SPARSE AND NOISY TIME-SERIES DATA , 2011, 1101.1959.

[19]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[20]  Martin G. Cohen,et al.  THE WIDE-FIELD INFRARED SURVEY EXPLORER (WISE): MISSION DESCRIPTION AND INITIAL ON-ORBIT PERFORMANCE , 2010, 1008.0031.

[21]  J. De Ridder,et al.  AUTOMATED CLASSIFICATION OF VARIABLE STARS IN THE ASTEROSEISMOLOGY PROGRAM OF THE KEPLER SPACE MISSION , 2010, 1001.0507.

[22]  K. Freeman,et al.  Galaxies and their Masks , 2010 .

[23]  Canada.,et al.  Data Mining and Machine Learning in Astronomy , 2009, 0906.2173.

[24]  Sukanta Deb,et al.  Light curve analysis of Variable stars using Fourier decomposition and Principal component analysis , 2009, 0903.3500.

[25]  P. Dubath,et al.  Variability type classification of multi-epoch surveys , 2009, 0901.2835.

[26]  M. Zechmeister,et al.  The generalised Lomb-Scargle periodogram. A new formalism for the floating-mean and Keplerian periodograms , 2009, 0901.2573.

[27]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[28]  NEW β LYRAE AND ALGOL CANDIDATES FROM THE NORTHERN SKY VARIABILITY SURVEY , 2008 .

[29]  Observatories of the Carnegie Institution of Washington,et al.  The expansion field: the value of H0 , 2008, 0806.3018.

[30]  L. M. Sarro,et al.  Automated supervised classification of variable stars - I. Methodology , 2007, 0711.0703.

[31]  John R. Percy.  Understanding Variable Stars , 2007 .

[32]  J. Torra,et al.  A procedure for the classification of eclipsing binaries , 2007 .

[33]  University of Michigan,et al.  Analysis of RR Lyrae Stars in the Northern Sky Variability Survey , 2006, astro-ph/0606092.

[34]  W. T. Vestrand,et al.  Identifying Red Variables in the Northern Sky Variability Survey , 2004 .

[35]  R. West,et al.  The automated classification of astronomical light curves using Kohonen self-organizing maps , 2004, astro-ph/0408118.

[36]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[37]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[38]  L. Eyer,et al.  Automated classification of variable stars for All-Sky Automated Survey 1–2 data , 2005 .

[39]  Shinichi Morishita,et al.  On Classification and Regression , 1998, Discovery Science.

[40]  Peter B. Stetson,et al.  ON THE AUTOMATIC DETERMINATION OF LIGHT-CURVE PARAMETERS FOR CEPHEID VARIABLES , 1996 .

[41]  S. Rucinski.  A SIMPLE DESCRIPTION OF LIGHT CURVES OF W UMA SYSTEMS , 1993 .

[42]  J. Scargle.  Studies in astronomical time series analysis. II - Statistical aspects of spectral analysis of unevenly spaced data , 1982 .

[43]  R. Stellingwerf.  Period determination using phase dispersion minimization , 1978 .

[44]  L. B. Lucy,et al.  THE LIGHT CURVES OF W URSAE MAJORIS STARS. , 1968 .

[45]  T. D. Kinman,et al.  An RR Lyrae Star Survey with Ihe Lick 20-INCH Astrograph II. The Calculation of RR Lyrae Periods by Electronic Computer. , 1965 .