An Unsupervised Machine Learning Approach to Identify Spectral Energy Distribution Outliers: Application to the S-PLUS DR4 data

Abstract

Identification of specific stellar populations using photometry for spectroscopic follow-up is a first step to confirm and better understand their nature. In this context, we present an unsupervised machine learning approach to identify candidates for spectroscopic follow-up using data from the Southern Photometric Local Universe Survey (S-PLUS). First, using an anomaly detection technique based on an autoencoder model, we select a large sample of objects ($\sim 19,000$) whose Spectral Energy Distribution (SED) is not well reconstructed by the model after training it on a well-behaved star sample. Then, we apply the t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm to the 66 color measurements from S-PLUS, complemented by information from the SIMBAD database, to identify stellar populations. Our analysis reveals 69 carbon-rich star candidates that, based on their spatial and kinematic characteristics, may belong to the CH or Carbon-Enhanced Metal-Poor (CEMP) categories. Among these chemically peculiar candidates, we identify four as likely carbon dwarf stars. We show that it is feasible to identify three primary white dwarf (WD) populations: WDs with hydrogen-dominated atmospheres (DA), WDs with neutral helium-dominated atmospheres (DB), and the WDs main sequence binaries (WD + MS). Furthermore, by using eROSITA X-ray data, we also highlight the identification of candidates for very active low-mass stars. Finally, we identified a large number of binary systems using the autoencoder model, but did not observe a clear association between the overdensities in the t-SNE map and their orbital properties.

19 pages, 12 figures, 2 tables

References in corpus (46)

• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• Measuring Reddening with SDSS Stellar Spectra and Recalibrating SFD
• Gaia Data Release 3: Summary of the content and survey properties
• Deep Learning for Anomaly Detection: A Review
• The Galaxy Evolution Explorer: A Space Ultraviolet Survey Mission
• Estimating distances from parallaxes. V: Geometric and photogeometric distances to 1.47 billion stars in Gaia Early Data Release 3
• The Apache Point Observatory Galactic Evolution Experiment (APOGEE)
• Trigonometric Parallaxes of High Mass Star Forming Regions: the Structure and Kinematics of the Milky Way
• The Radial Velocity Experiment (RAVE): first data release
• The GALAH Survey: Scientific Motivation
• Gaia Data Release 2: Photometric content and validation
• Rotation and Activity in Mid-M to L Dwarfs
• X-ray astronomy of stellar coronae (Review)
• The SRG/eROSITA all-sky survey: First X-ray catalogues and data release of the western Galactic hemisphere
• The H$\alpha$ emission of nearby M dwarfs and its relation to stellar rotation
• Gaia Data Release 3: Stellar multiplicity, a teaser for the hidden treasure
• The Pristine survey I: Mining the Galaxy for the most metal-poor stars
• J-PLUS: The Javalambre Photometric Local Universe Survey
• Effective temperature scale and bolometric corrections from 2MASS photometry
• The Southern Photometric Local Universe Survey (S-PLUS): improved SEDs, morphologies and redshifts with 12 optical filters
• Fluxes in Hαand Ca II H and K for a sample of Southern stars
• Disentangling the Galactic Halo with APOGEE: I. Chemical and Kinematical Investigation of Distinct Metal-Poor Populations
• The stellar content of the Hamburg/ESO survey. II. A large, homogeneously-selected sample of high latitude carbon stars
• Current challenges in the physics of white dwarf stars
• A classifier for spurious astrometric solutions in Gaia EDR3
• Dissecting stellar chemical abundance space with t-SNE
• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• The Galah Survey: Classification and diagnostics with t-SNE reduction of spectral information
• The SkyMapper DR1.1 Search for Extremely Metal-Poor Stars
• Selection of Metal-poor Giant Stars Using the Sloan Digital Sky Survey Photometric System
• The chemical composition of carbon stars: The R-type stars
• Population synthesis of helium white dwarf--red giant star mergers and the formation of lithium-rich giants and carbon stars
• The Photometric Metallicity and Carbon Distributions of the Milky Way's Halo and Solar Neighborhood from S-PLUS Observations of SDSS Stripe 82
• Reprocessing the Hipparcos data for evolved giant stars II. Absolute magnitudes for the R-type carbon stars
• Detailed Chemical Abundances for a Benchmark Sample of M Dwarfs from the APOGEE Survey
• Cool carbon stars in the halo: a new survey based on 2MASS
• On the discovery of stars, quasars, and galaxies in the Southern Hemisphere with S-PLUS DR2
• Characterisation of Galactic carbon stars and related stars from Gaia-EDR3
• J-PLUS: Spectral evolution of white dwarfs by PDF analysis
• An autoencoder of stellar spectra and its application in automatically estimating atmospheric parameters
• Carbon-Enhanced Metal-Poor star candidates from BP/RP Spectra in $Gaia$ DR3
• A metallicity study of F, G, K and M dwarfs in the Coma Berenices open cluster from the APOGEE survey
• The GALAH survey: a catalogue of carbon-enhanced stars and CEMP candidates
• Learning about stars from their colors
• Closing the stellar labels gap: Stellar label independent evidence for [$\alpha /M$] information in Gaia BP/RP spectra
• Stellar atmospheric parameters and chemical abundances of about 5 million stars from S-PLUS multi-band photometry

Cited by in corpus (1)

• Interpreting anomaly detection of SDSS spectra