Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars

Abstract

Upcoming synoptic surveys are set to generate an unprecedented amount of data. This requires an automatic framework that can quickly and efficiently provide classification labels for several new object classification challenges. Using data describing 11 types of variable stars from the Catalina Real-Time Transient Surveys (CRTS), we illustrate how to capture the most important information from computed features and describe detailed methods of how to robustly use Information Theory for feature selection and evaluation. We apply three Machine Learning (ML) algorithms and demonstrate how to optimize these classifiers via cross-validation techniques. For the CRTS dataset, we find that the Random Forest (RF) classifier performs best in terms of balanced-accuracy and geometric means. We demonstrate substantially improved classification results by converting the multi-class problem into a binary classification task, achieving a balanced-accuracy rate of $\sim$99 per cent for the classification of $\delta$-Scuti and Anomalous Cepheids (ACEP). Additionally, we describe how classification performance can be improved via converting a 'flat-multi-class' problem into a hierarchical taxonomy. We develop a new hierarchical structure and propose a new set of classification features, enabling the accurate identification of subtypes of cepheids, RR Lyrae and eclipsing binary stars in CRTS data.

16 pages, 11 figures, accepted for publication in MNRAS

References in corpus (20)

• Scikit-learn: Machine Learning in Python
• First Results from the Catalina Real-time Transient Survey
• Oversampling for Imbalanced Learning Based on K-Means and SMOTE
• Limits on the Macho Content of the Galactic Halo from the EROS-2 Survey of the Magellanic Clouds
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• Fifty Years of Pulsar Candidate Selection: From simple filters to a new principled real-time classification approach
• Photometric Supernova Classification With Machine Learning
• Discovery of $\sim$ 9,000 new RR Lyrae in the Southern Catalina Surveys
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• A Package for the Automated Classification of Periodic Variable Stars
• Lightcurve Classification in Massive Variability Surveys
• Automated classification of variable stars for ASAS 1-2 data
• The High Time Resolution Universe Survey II: Discovery of 5 Millisecond Pulsars
• STACCATO: A Novel Solution to Supernova Photometric Classification with Biased Training Sets
• FATS: Feature Analysis for Time Series
• Absolute Magnitudes and Colors of RR Lyrae stars in DECam Passbands from Photometry of the Globular Cluster M5
• Real-Time Data Mining of Massive Data Streams from Synoptic Sky Surveys
• Parametrization and Classification of 20 Billion LSST Objects: Lessons from SDSS
• A study of supervised classification of Hipparcos variable stars using PCA and Support Vector Machines
• Real Time Classification of Transient Events in Synoptic Sky Surveys

Cited by in corpus (11)

• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• Imbalance Learning for Variable Star Classification
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Searching for AGN and Pulsar Candidates in 4FGL Unassociated Sources Using Machine Learning
• MeerCRAB: MeerLICHT Classification of Real and Bogus Transients using Deep Learning
• Deep Transfer Learning for Classification of Variable Sources
• Semi-Supervised Classification and Clustering Analysis for Variable Stars
• Automated classification of eclipsing binary systems in the VVV Survey
• Deep-learning Real/Bogus classification for the Tomo-e Gozen transient survey
• A New Period Determination Method for Periodic Variable Stars