Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning

Abstract

With the availability of large-scale surveys like Kepler and TESS, there is a pressing need for automated methods to classify light curves according to known classes of variable stars. We introduce a new algorithm for classifying light curves that compares 7000 time-series features to find those which most effectively classify a given set of light curves. We apply our method to Kepler light curves for stars with effective temperatures in the range 6500--10,000K. We show that the sample can be meaningfully represented in an interpretable five-dimensional feature space that separates seven major classes of light curves (delta Scuti stars, gamma Doradus stars, RR Lyrae stars, rotational variables, contact eclipsing binaries, detached eclipsing binaries, and non-variables). We achieve a balanced classification accuracy of 82% on an independent test set of Kepler stars using a Gaussian mixture model classifier. We use our method to classify 12,000 Kepler light curves from Quarter 9 and provide a catalogue of the results. We further outline a confidence heuristic based on probability density with which to search our catalogue, and extract candidate lists of correctly-classified variable stars.

arXiv commentpublished by MNRAS

References in corpus (51)

• Rotation Periods of 34,030 Kepler Main-Sequence Stars: The Full Autocorrelation Sample
• Kepler Eclipsing Binary Stars. VII. The Catalog of Eclipsing Binaries Found in the Entire Kepler Data-Set
• Highly comparative time-series analysis: The empirical structure of time series and their methods
• Data Mining and Machine Learning in Astronomy
• Highly comparative feature-based time-series classification
• Automatic time-series phenotyping using massive feature extraction
• Revised Stellar Properties of Kepler Targets for the Q1-17 (DR25) Transit Detection Run
• Rotation periods of 12 000 main-sequence Kepler stars: Dependence on stellar spectral type and comparison with v sin i observations
• Gamma Doradus Stars: Defining a New Class of Pulsating Variables
• Asteroseismology of 16000 Kepler Red Giants: Global Oscillation Parameters, Masses, and Radii
• Kepler Eclipsing Binary Stars. III. Classification of Kepler Eclipsing Binary Light Curves with Locally Linear Embedding
• {\em Gaia}-derived luminosities of {\em Kepler} A/F stars and the pulsator fraction across the δ Scuti instability strip
• Metal Abundances, Radial Velocities and other Physical Characteristics for the RR Lyrae Stars in the Kepler Field
• Characterising the observational properties of δ Sct stars in the era of space photometry from the Kepler mission
• On the sensitivity of gravito-inertial modes to differential rotation in intermediate-mass main-sequence stars
• Global stellar variability study in the field-of-view of the Kepler satellite
• Very regular high-frequency pulsation modes in young intermediate-mass stars
• K2 Variable Catalogue II: Machine Learning Classification of Variable Stars and Eclipsing Binaries in K2 Fields 0-4
• Finding binaries from phase modulation of pulsating stars with Kepler: V. Orbital parameters, with eccentricity and mass-ratio distributions of 341 new binaries
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• γ Doradus stars as test of angular momentum transport models
• Asteroseismic masses, ages, and core properties of $\gamma$ Doradus stars using gravito-inertial dipole modes and spectroscopy
• Deep Learning Classification in Asteroseismology
• Blue large-amplitude pulsators as a new class of variable stars
• Period spacings of $\gamma$ Doradus pulsators in the \textit{Kepler} field: Rossby and gravity modes in 82 stars
• Gravity-mode period spacings and near-core rotation rates of 611 $\gamma$ Doradus stars with \textit{Kepler}
• Deep Learning Classification in Asteroseismology Using an Improved Neural Network: Results on 15000 Kepler Red Giants and Applications to K2 and TESS Data
• Machine learning search for variable stars
• Deep Learning for Image Sequence Classification of Astronomical Events
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• Gaia luminosities of pulsating A-F stars in the Kepler field
• Automated classification of variable stars in the asteroseismology program of the Kepler space mission
• Automated classification of periodic variable stars{Improved methodology for the automated classification of periodic variable stars}
• Imbalance Learning for Variable Star Classification
• Detecting Solar-like Oscillations in Red Giants with Deep Learning
• Highlights of Discoveries for $\delta$ Scuti Variable Stars From the Kepler Era
• On the co-existence of chemically peculiar Bp stars, slowly pulsating B stars and constant B stars in the same part of the H-R diagram
• TESS Data for Asteroseismology (T'DA) Stellar Variability Classification Pipeline: Set-Up and Application to the Kepler Q9 Data
• Transiting Planets near the Snow Line from Kepler. I. Catalog
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• Supervised Ensemble Classification of Kepler Variable Stars
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Overstable Convective Modes in Rotating Early Type Stars
• Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks
• A spectroscopic test of the rotational modulation origin of periodic \emph{Kepler} photometric variability of A-type stars
• Density Based Outlier Scoring on Kepler Data
• Clumpiness: Time-domain classification of red-giant evolutionary states
• Variable Star Classification Using Multi-View Metric Learning
• A Detection Metric Designed for O'Connell Effect Eclipsing Binaries
• Finding binaries from phase modulation of pulsating stars with \textit{Kepler}: VI. Orbits for 10 new binaries with mischaracterised primaries
• Automatic Catalog of RRLyrae from $\sim$ 14 million VVV Light Curves: How far can we go with traditional machine-learning?

Cited by in corpus (8)

• Bake off redux: a review and experimental evaluation of recent time series classification algorithms
• Confronting sparse Gaia DR3 photometry with TESS for a sample of around 60,000 OBAF-type pulsators
• Multiscale entropy analysis of astronomical time series. Discovering subclusters of hybrid pulsators
• Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
• Removing Aliases in Time-Series Photometry
• Disentangling stellar atmospheric parameters in astronomical spectra using Generative Adversarial Neural Networks
• FALCO: a Foundation model of Astronomical Light Curves for time dOmain astronomy
• Heartbeat Stars Recognition Based on Recurrent Neural Networks: Method and Validation