Supervised detection of anomalous light-curves in massive astronomical catalogs

Abstract

The development of synoptic sky surveys has led to a massive amount of data for which resources needed for analysis are beyond human capabilities. To process this information and to extract all possible knowledge, machine learning techniques become necessary. Here we present a new method to automatically discover unknown variable objects in large astronomical catalogs. With the aim of taking full advantage of all the information we have about known objects, our method is based on a supervised algorithm. In particular, we train a random forest classifier using known variability classes of objects and obtain votes for each of the objects in the training set. We then model this voting distribution with a Bayesian network and obtain the joint voting distribution among the training objects. Consequently, an unknown object is considered as an outlier insofar it has a low joint probability. Our method is suitable for exploring massive datasets given that the training process is performed offline. We tested our algorithm on 20 millions light-curves from the MACHO catalog and generated a list of anomalous candidates. We divided the candidates into two main classes of outliers: artifacts and intrinsic outliers. Artifacts were principally due to air mass variation, seasonal variation, bad calibration or instrumental errors and were consequently removed from our outlier list and added to the training set. After retraining, we selected about 4000 objects, which we passed to a post analysis stage by perfoming a cross-match with all publicly available catalogs. Within these candidates we identified certain known but rare objects such as eclipsing Cepheids, blue variables, cataclysmic variables and X-ray sources. For some outliers there were no additional information. Among them we identified three unknown variability types and few individual outliers that will be followed up for a deeper analysis.

arXiv comment16 pages, 18 figures, published in The Astrophysical Journal

References in corpus (41)

• Towards a unified model for black hole X-ray binary jets
• Modelling the behaviour of accretion flows in X-ray binaries
• SparsePak: A Formatted Fiber Field Unit for The WIYN Telescope Bench Spectrograph. I. Design, Construction, and Calibration
• Millisecond Oscillations in X-Ray Binaries
• The MACHO Project LMC Microlensing Results from the First Two Years and the Nature of the Galactic Dark Halo
• Hydrogen-poor superluminous stellar explosions
• SkyMapper and the Southern Sky Survey
• The XMM-Newton Serendipitous Survey. V. The Second XMM-Newton Serendipitous Source Catalogue
• A catalogue of low-mass X-ray binaries in the Galaxy, LMC, and SMC (Fourth edition)
• Comprehensive Photometric Histories of All Known Galactic Recurrent Novae
• Large Synoptic Survey Telescope: Overview
• The MACHO Project: 45 Candidate Microlensing Events from the First Year Galactic Bulge Data
• Finding Anomalous Periodic Time Series: An Application to Catalogs of Periodic Variable Stars
• Accurate dynamical mass determination of a classical Cepheid in an eclipsing binary system
• Variability-Selected Quasars in MACHO Project Magellanic Cloud Fields
• 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
• Finding outlier light-curves in catalogs of periodic variable stars
• Variable stars in the Magellanic Clouds: II. The data and infrared properties
• The MACHO Project LMC Variable Star Inventory IV: Multimode RR Lyrae Stars, Distance to the LMC and Age of the Oldest Stars
• Long Period Variables in the Magellanic Clouds: OGLE + 2MASS + DENIS
• The Properties of Long-Period Variables in the Large Magellanic Cloud from MACHO
• First detection of a gravitational microlensing candidate towards the Small Magellanic Cloud
• Blue Variable Stars from the MACHO database I: Photometry and Spectroscopy of the LMC sample
• The Eclipsing Binary Cepheid OGLE-LMC-CEP-0227 in the Large Magellanic Cloud: pulsation modelling of light and radial velocity curves
• Large Magellanic Cloud Bump Cepheids: Probing the Stellar Mass-Luminosity Relation
• A Classical Cepheid in a LMC eclipsing binary: evidence of shortcomings in current stellar evolutionary models?
• Eight New Radio Pulsars in the Large Magellanic Cloud
• The MACHO Project Large Magellanic Cloud Variable Star Inventory. VIII. The Recent Star Formation History of the LMC from the Cepheid Period Distribution
• The MACHO Project Large Magellanic Cloud Variable Star Inventory. XIII. Fourier Parameters for the First Overtone RR Lyrae Variables and the LMC Distance
• Chandra LETGS Observation of the Active Binary Algol
• Automatic Classification of Variable Stars in Catalogs with missing data
• Magellanic Cloud X-ray Sources: III. Completion of a ROSAT Survey
• An improved quasar detection method in EROS-2 and MACHO LMC datasets
• The MACHO Project LMC Variable Star Inventory: XII. Three Cepheid Variables in Eclipsing Binaries
• A Refined QSO Selection Method Using Diagnostics Tests: 663 QSO Candidates in the LMC
• Galactic Bulge Microlensing Events from the MACHO Collaboration
• Photometric and Spectroscopic Properties of Novae in the Large Magellanic Cloud
• Discovery of four X-ray quasars behind the Large Magellanic Cloud
• Contact Binary Variables as X-ray Sources

Cited by in corpus (26)

• A recurrent neural network for classification of unevenly sampled variable stars
• K2 Variable Catalogue II: Machine Learning Classification of Variable Stars and Eclipsing Binaries in K2 Fields 0-4
• A Package for the Automated Classification of Periodic Variable Stars
• Deep multi-survey classification of variable stars
• Active Anomaly Detection for time-domain discoveries
• Anomaly Detection in the Open Supernova Catalog
• The Outer Halo of the Milky Way as Probed by RR Lyr Variables from the Palomar Transient Facility
• Automatic vetting of planet candidates from ground based surveys: Machine learning with NGTS
• Clustering Based Feature Learning on Variable Stars
• Unsupervised Classification of Variable Stars
• Real-Time Detection of Anomalies in Large-Scale Transient Surveys
• Meta Classification for Variable Stars
• Automatic Survey-Invariant Variable Star Classification
• The VVV Infrared Variability Catalog (VIVA-I)
• Uncertain classification of Variable Stars: handling observational GAPS and noise
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• Streaming Classification of Variable Stars
• Classification of the \emph{Fermi}-LAT Blazar Candidates of Uncertain type using eXtreme Gradient Boosting
• Data challenges as a tool for time-domain astronomy
• Informative Bayesian model selection for RR Lyrae star classifiers
• An Algorithm for the Visualization of Relevant Patterns in Astronomical Light Curves
• YOUNG Star detrending for Transiting Exoplanet Recovery (YOUNGSTER) II: Using Self-Organising Maps to explore young star variability in Sectors 1-13 of TESS data
• The influential effect of blending, bump, changing period and eclipsing Cepheids on the Leavitt law
• Quantum Machine Learning for Identifying Transient Events in X-ray Light Curves
• Informative regularization for a multi-layer perceptron RR Lyrae classifier under data shift
• Advanced Astroinformatics for Variable Star Classification