Automatic catalog of RR Lyrae from∼14 million VVV light curves:How far can we go with traditional machine-learning?

J.B. CABRAL; F. RAMOS; S. GUROVICH; P. GRANITTO

ASTRONOMY AND ASTROPHYSICS

EDP SCIENCES S A

Lugar: Paris; Año: 2020 vol. 642

0004-6361

Context.The creation of a 3D map of the bulge using RR Lyrae (RRL) is one of the main goals of the VISTA Variables in the ViaLactea Survey (VVV) and VVV(X) surveys. The overwhelming number of sources undergoing analysis undoubtedly requires the useof automatic procedures. In this context, previous studies have introduced the use of machine learning (ML) methods for the task ofvariable star classification.Aims.Our goal is to develop and test an entirely automatic ML-based procedure for the identification of RRLs in the VVV Survey.This automatic procedure is meant to be used to generate reliable catalogs integrated over several tiles in the survey.Methods.Following the reconstruction of light curves, we extracted a set of period- and intensity-based features, which were alreadydefined in previous works. Also, for the first time, we put a new subset of useful color features to use. We discuss in considerabledetail all the appropriate steps needed to define our fully automatic pipeline, namely: the selection of quality measurements; samplingprocedures; classifier setup, and model selection.Results.As a result, we were able to construct an ensemble classifier with an average recall of 0.48 and average precision of 0.86over 15 tiles. We also made all our processed datasets available and we published a catalog of candidate RRLs.Conclusions.Perhaps most interestingly, from a classification perspective based on photometric broad-band data, our results indicatethat color is an informative feature type of the RRL objective class that should always be considered in automatic classificationmethods via ML. We also argue that recall and precision in both tables and curves are high-quality metrics with regard to this highlyimbalanced problem. Furthermore, we show for our VVV data-set that to have good estimates, it is important to use the originaldistribution more abundantly than reduced samples with an artificial balance. Finally, we show that the use of ensemble classifiershelps resolve the crucial model selection step and that most errors in the identification of RRLs are related to low-quality observationsof some sources or to the increased difficulty in resolving the RRL-C type given the data.