Semi-Supervised Classification and Clustering Analysis for Variable Stars

Abstract

The immense amount of time series data produced by astronomical surveys has called for the use of machine learning algorithms to discover and classify several million celestial sources. In the case of variable stars, supervised learning approaches have become commonplace. However, this needs a considerable collection of expert-labeled light curves to achieve adequate performance, which is costly to construct. To solve this problem, we introduce two approaches. First, a semi-supervised hierarchical method, which requires substantially less trained data than supervised methods. Second, a clustering analysis procedure that finds groups that may correspond to classes or sub-classes of variable stars. Both methods are primarily supported by dimensionality reduction of the data for visualization and to avoid the curse of dimensionality. We tested our methods with catalogs collected from OGLE, CSS, and Gaia surveys. The semi-supervised method reaches a performance of around 90\% for all of our three selected catalogs of variable stars using only $5\%$ of the data in the training. This method is suitable for classifying the main classes of variable stars when there is only a small amount of training data. Our clustering analysis confirms that most of the clusters found have a purity over 90\% with respect to classes and 80\% with respect to sub-classes, suggesting that this type of analysis can be used in large-scale variability surveys as an initial step to identify which classes or sub-classes of variable stars are present in the data and/or to build training sets, among many other possible applications.

arXiv comment23 pages, 21 figures, 4 tables, submitted to MNRAS

References in corpus (53)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• SMOTE: Synthetic Minority Over-sampling Technique
• Astropy: A Community Python Package for Astronomy
• Gaia Data Release 2. Summary of the contents and survey properties
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• The Gaia mission
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• First Results from the Catalina Real-time Transient Survey
• The WASP Project and the SuperWASP Cameras
• VISTA Variables in the Via Lactea (VVV): The public ESO near-IR variability survey of the Milky Way
• Helioseismology
• The Catalina Surveys Periodic Variable Star Catalog
• The ASAS-SN Catalog of Variable Stars I: The Serendipitous Survey
• The VMC Survey - I. Strategy and First Data
• Probing the interior physics of stars through asteroseismology
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• Automated supervised classification of variable stars I. Methodology
• The ASAS-SN Catalog of Variable Stars II: Uniform Classification of 412,000 Known Variables
• Random forest automated supervised classification of Hipparcos periodic variable stars
• Optimal Time-Series Selection of Quasars
• Gaia Data Release 2. Cross-match with external catalogues - Algorithms and results
• A recurrent neural network for classification of unevenly sampled variable stars
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Solar structure and evolution
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• A Package for the Automated Classification of Periodic Variable Stars
• Light curve analysis of Variable stars using Fourier decomposition and Principal component analysis
• Gamma-Ray Active Galactic Nucleus Type through Machine-Learning Algorithms
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• Deep multi-survey classification of variable stars
• Gaia Data Release 2: All-sky classification of high-amplitude pulsating stars
• A machine learned classifier for RR Lyrae in the VVV survey
• Automatic Classification of Variable Stars in Catalogs with missing data
• Combining human and machine learning for morphological analysis of galaxy images
• An Information Theoretic Algorithm for Finding Periodicities in Stellar Light Curves
• Pulsation Modes of Long-Period Variables in the Period-Luminosity Plane
• Imbalance Learning for Variable Star Classification
• Unsupervised machine learning for transient discovery in Deeper, Wider, Faster light curves
• Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars
• The VVV Templates Project. Towards an Automated Classification of VVV Light-Curves. I. Building a database of stellar variability in the near-infrared
• Clustering Based Feature Learning on Variable Stars
• Unsupervised Classification of Variable Stars
• A First Look at creating mock catalogs with machine learning techniques
• Meta Classification for Variable Stars
• Variable star classification across the Galactic bulge and disc with the VISTA Variables in the Vía Láctea survey
• Automatic Survey-Invariant Variable Star Classification
• New Insights into Time Series Analysis II -- No Correlated Observations
• Searching transients in large-scale surveys. A method based on the Abbe value
• Uncertain classification of Variable Stars: handling observational GAPS and noise
• Machine learning techniques to select Be star candidates. An application in the OGLE-IV Gaia south ecliptic pole field
• Multivariate Time-series Analysis of Variable Objects in the Gaia Mission

Cited by in corpus (5)

• Semi-supervised classification of stars, galaxies and quasars using K-means and random-forest approaches
• Machine learning based stellar classification with highly sparse photometry data
• Unsupervised learning for variability detection with Gaia DR3 photometry. The main sequence-white dwarf valley
• Sparse logistic regression for RR Lyrae vs binaries classification
• Full-frame data reduction method: a data mining tool to detect the potential variations in optical photometry