Automatic Catalog of RRLyrae from $\sim$ 14 million VVV Light Curves: How far can we go with traditional machine-learning?

Abstract

The creation of a 3D map of the bulge using RRLyrae (RRL) is one of the main goals of the VVV(X) surveys. The overwhelming number of sources under analysis request the use of automatic procedures. In this context, previous works introduced the use of Machine Learning (ML) methods for the variable star classification. Our goal is the development and analysis of an automatic procedure, based on ML, for the identification of RRLs in the VVV Survey. This procedure will be use to generate reliable catalogs integrated over several tiles in the survey. After the reconstruction of light-curves, we extract a set of period and intensity-based features. We use for the first time a new subset of pseudo color features. We discuss all the appropriate steps needed to define our automatic pipeline: selection of quality measures; sampling procedures; classifier setup and model selection. As final result, we construct an ensemble classifier with an average Recall of 0.48 and average Precision of 0.86 over 15 tiles. We also make available our processed datasets and a catalog of candidate RRLs. Perhaps most interestingly, from a classification perspective based on photometric broad-band data, is that our results indicate that Color is an informative feature type of the RRL that should be considered for automatic classification methods via ML. We also argue that Recall and Precision in both tables and curves are high quality metrics for this highly imbalanced problem. Furthermore, we show for our VVV data-set that to have good estimates it is important to use the original distribution more than reduced samples with an artificial balance. Finally, we show that the use of ensemble classifiers helps resolve the crucial model selection step, and that most errors in the identification of RRLs are related to low quality observations of some sources or to the difficulty to resolve the RRL-C type given the date.

References in corpus (44)

• Astropy: A Community Python Package for Astronomy
• The NumPy array: a structure for efficient numerical computation
• Gaia Data Release 2. Summary of the contents and survey properties
• The Gaia mission
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Stellar mass-to-light ratios and the Tully-Fisher relation
• The VizieR database of Astronomical Catalogues
• Understanding the Lomb-Scargle Periodogram
• VISTA Variables in the Via Lactea (VVV): The public ESO near-IR variability survey of the Milky Way
• Achieving better than 1 minute accuracy in the Heliocentric and Barycentric Julian Dates
• Interstellar Extinction Law toward the Galactic Center III: J, H, Ks bands in the 2MASS and the MKO systems, and 3.6, 4.5, 5.8, 8.0 micron in the Spitzer/IRAC system
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• Machine-Learned Identification of RR Lyrae Stars from Sparse, Multi-band Data: the PS1 Sample
• The VISTA ZYJHKs Photometric System: Calibration from 2MASS
• Reddening and metallicity maps of the Milky Way Bulge from VVV and 2MASS. I.The method and minor axis maps
• Mapping the Milky Way bulge at high resolution: the 3D dust extinction, CO, and X factor maps
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• Construction of a Calibrated Probabilistic Classification Catalog: Application to 50k Variable Sources in the All-Sky Automated Survey
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• K2 Variable Catalogue: Variable Stars and Eclipsing Binaries in K2 Campaigns 1 and 0
• Milky Way demographics with the VVV survey. IV. PSF photometry from almost one billion stars in the Galactic bulge and adjacent southern disk
• The slope of the Baryonic Tully-Fisher relation
• Empirical relations for cluster RR Lyrae stars revisited
• Machine learning search for variable stars
• Mapping the outer bulge with RRab stars from the VVV Survey
• Catalog of fundamental mode RR Lyrae stars in the Galactic bulge from the Optical Gravitational Lensing Experiment
• A machine learned classifier for RR Lyrae in the VVV survey
• Detecting Variability in Massive Astronomical Time-Series Data I: application of an infinite Gaussian mixture model
• Metallicity Analysis of MACHO Galactic Bulge RR0 Lyrae stars from their Lightcurves
• Cyclic variations in O-C diagrams of field RR Lyrae stars as a result of LiTE
• Imbalance Learning for Variable Star Classification
• The Extinction Toward the Galactic Bulge from RR Lyrae Stars
• Blazhko effect in the Galactic bulge fundamental mode RR~Lyrae stars I: Incidence rate and differences between modulated and non-modulated stars
• RR Lyrae Variables in the Globular Clusters of M31: a First Detection of Likely Candidates
• Catalogue of variable stars in open cluster fields
• Toward an internally consistent astronomical distance scale
• Clustering Based Feature Learning on Variable Stars
• Observation of the Halo of NGC 3077 Near the "Garland" Region Using the Hubble Space Telescope
• Bulge RR Lyrae stars in the VVV tile $\text{b201}$
• A Mid-infrared Study of RR Lyrae Stars with the WISE All-Sky Data Release
• Establishing the Galactic Centre Distance Using VVV Bulge RR Lyrae Variables
• Detecting Variability in Massive Astronomical Time-Series Data II: Variable Candidates in the Northern Sky Variability Survey
• Corral Framework: Trustworthy and Fully Functional Data Intensive Parallel Astronomical Pipelines
• Variability search in M 31 using Principal Component Analysis and the Hubble Source Catalog

Cited by in corpus (5)

• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• A microlensing search of 700 million VVV light curves
• VVV catalog of ab-type RR Lyrae in the inner Galactic bulge
• Light Curve Classification with DistClassiPy: a new distance-based classifier
• Drifting Features: Detection and evaluation in the context of automatic RRLs identification in VVV