Supervised Ensemble Classification of Kepler Variable Stars

Abstract

Variable star analysis and classification is an important task in the understanding of stellar features and processes. While historically classifications have been done manually by highly skilled experts, the recent and rapid expansion in the quantity and quality of data has demanded new techniques, most notably automatic classification through supervised machine learning. We present an expansion of existing work on the field by analyzing variable stars in the {\em Kepler} field using an ensemble approach, combining multiple characterization and classification techniques to produce improved classification rates. Classifications for each of the roughly 150,000 stars observed by {\em Kepler} are produced separating the stars into one of 14 variable star classes.

arXiv comment18 pages, 22 figures

References in corpus (26)

• SMOTE: Synthetic Minority Over-sampling Technique
• The NumPy array: a structure for efficient numerical computation
• The K2 Mission: Characterization and Early results
• Kepler Mission Design, Realized Photometric Performance, and Early Science
• Kepler Input Catalog: Photometric Calibration and Stellar Classification
• Overview of the Kepler Science Processing Pipeline
• Kepler Asteroseismology Program: Introduction and First Results
• Kepler Eclipsing Binary Stars. II. 2165 Eclipsing Binaries in the Second Data Release
• The Kepler characterization of the variability among A- and F-type stars. I. General overview
• Asteroseismic classification of stellar populations among 13000 red giants observed by Kepler
• Automated supervised classification of variable stars I. Methodology
• Random forest automated supervised classification of Hipparcos periodic variable stars
• Instrument Performance in Kepler's First Months
• Global stellar variability study in the field-of-view of the Kepler satellite
• The MACHO Project Large Magellanic Cloud variable star inventory. XI. Frequency analysis of the fundamental mode RR Lyrae stars
• Detection of a large sample of Gamma Dor stars from Kepler space photometry and high-resolution ground-based spectroscopy
• Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification
• The Classificiation of Kepler B star Variables
• A Fast Chi-squared Technique For Period Search of Irregularly Sampled Data
• Automated Classification of Periodic Variable Stars detected by the Wide-field Infrared Survey Explorer
• Automated classification of Hipparcos unsolved variables
• Automated classification of variable stars in the asteroseismology program of the Kepler space mission
• The Gaia Project - technique, performance and status
• Automated classification of periodic variable stars{Improved methodology for the automated classification of periodic variable stars}
• Automatic classification of time-variable X-ray sources
• Comparative clustering analysis of variable stars in the Hipparcos, OGLE Large Magellanic Cloud and CoRoT exoplanet databases

Cited by in corpus (11)

• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Separation of pulsar signals from noise with supervised machine learning algorithms
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• Data preparation for asteroseismology with TESS
• Variability, periodicity and contact binaries in WISE
• Machine learning techniques to select Be star candidates. An application in the OGLE-IV Gaia south ecliptic pole field
• On the Use of Logistic Regression for stellar classification. An application to colour-colour diagrams
• Variable Star Classification Using Multi-View Metric Learning
• Identification of emission-line stars in transition phase from pre-main sequence to main sequence
• A case study of ACV variables discovered in the Zwicky Transient Facility survey
• Advanced Astroinformatics for Variable Star Classification