A machine-learning photometric classifier for massive stars in nearby galaxies I. The method

Abstract

(abridged) Mass loss is a key parameter in the evolution of massive stars, with discrepancies between theory and observations and with unknown importance of the episodic mass loss. To address this we need increased numbers of classified sources stars spanning a range of metallicity environments. We aim to remedy the situation by applying machine learning techniques to recently available extensive photometric catalogs. We used IR/Spitzer and optical/Pan-STARRS, with Gaia astrometric information, to compile a large catalog of known massive stars in M31 and M33, which were grouped in Blue, Red, Yellow, B[e] supergiants, Luminous Blue Variables, Wolf-Rayet, and background galaxies. Due to the high imbalance, we implemented synthetic data generation to populate the underrepresented classes and improve separation by undersampling the majority class. We built an ensemble classifier using color indices. The probabilities from Support Vector Classification, Random Forests, and Multi-layer Perceptron were combined for the final classification. The overall weighted balanced accuracy is ~83%, recovering Red supergiants at ~94%, Blue/Yellow/B[e] supergiants and background galaxies at ~50-80%, Wolf-Rayets at ~45%, and Luminous Blue Variables at ~30%, mainly due to their small sample sizes. The mixing of spectral types (no strict boundaries in their color indices) complicates the classification. Independent application to IC 1613, WLM, and Sextans A galaxies resulted in an overall lower accuracy of ~70%, attributed to metallicity and extinction effects. The missing data imputation was explored using simple replacement with mean values and an iterative imputor, which proved more capable. We also found that r-i and y-[3.6] were the most important features. Our method, although limited by the sampling of the feature space, is efficient in classifying sources with missing data and at lower metallicitites.

27 pages, 18 figures, 6 tables; accepted for publication in A&A; typos and minor editing corrections

References in corpus (28)

• Array Programming with NumPy
• The Gaia mission
• Binary interaction dominates the evolution of massive stars
• Binary Population and Spectral Synthesis Version 2.1: construction, observational verification and new results
• A Survey of Local Group Galaxies Currently Forming Stars. I. UBVRI Photometry of Stars in M31 and M33
• Spitzer SAGE Infrared Photometry of Massive Stars in the Large Magellanic Cloud
• A Survey of Local Group Galaxies Currently Forming Stars: III. A Search for Luminous Blue Variables and Other H-alpha Emission-Lined Stars
• Spitzer SAGE-SMC Infrared Photometry of Massive Stars in the Small Magellanic Cloud
• The UKIRT Hemisphere Survey: Definition and J-band Data Release
• A recurrent neural network for classification of unevenly sampled variable stars
• VLT spectroscopy of blue supergiants in IC 1613
• Why binary interaction does not necessarily dominate the formation of Wolf-Rayet stars at low metallicity
• Comparative performance of selected variability detection techniques in photometric time series
• The Araucaria Project. VLT spectra of blue supergiants in WLM: classification and first abundances
• An Infrared Census of DUST in Nearby Galaxies with Spitzer (DUSTiNGS), I. Overview
• The SDSS-2MASS-WISE Ten Dimensional Stellar Color Locus
• Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning
• Luminous and Variable Stars in M31 and M33. II. Luminous Blue Variables, Candidate LBVs, Fe II Emission Line Stars, and Other Supergiants
• Machine learning search for variable stars
• Luminous and Variable Stars in M31 and M33. IV. Luminous Blue Variables, Candidate LBVs, and the B[e] Supergiants; How to Tell Them Apart
• Binary Red Supergiants II: Discovering and Characterizing B-type Companions
• Spitzer Photometry of ~1 Million Stars in M31 and 15 Other Galaxies
• Searching for Molecular Outflows with Support Vector Machines: Dark Cloud Complex in Cygnus
• Red Supergiants, Yellow Hypergiants, and Post-RSG Evolution
• A new automated tool for the spectral classification of OB stars
• Applications of Machine-Learning Algorithms for Infrared Colour Selection of Galactic Wolf-Rayet Stars
• Multi-Epoch BVRI Photometry of Luminous Stars in M31 and M33
• Classification of a black hole spin out of its shadow using support vector machines

Cited by in corpus (11)

• Data mining techniques on astronomical spectra data. II : Classification Analysis
• The effect of mass loss in models of red supergiants in the Small Magellanic Cloud
• Investigating episodic mass loss in evolved massive stars: I. Spectroscopy of dusty massive stars in ten southern galaxies
• Properties of luminous red supergiant stars in the Magellanic Clouds
• Investigating the metallicity dependence of the mass-loss rate relation of red supergiants
• Discovering new B[e] supergiants and candidate Luminous Blue Variables in nearby galaxies
• Investigating episodic mass loss in evolved massive stars: III. Spectroscopy of dusty massive stars in three northern galaxies
• Red Supergiants in the Milky Way and Nearby Galaxies
• A machine-learning photometric classifier for massive stars in nearby galaxies II. The catalog
• Heartbeat Stars Recognition Based on Recurrent Neural Networks: Method and Validation
• A search for new symbiotic stars in the Milky Way: Using machine learning techniques applied to photometric databases