Machine learning in APOGEE: Identification of stellar populations through chemical abundances

Abstract

The vast volume of data generated by modern astronomical surveys offers test beds for the application of machine-learning. It is important to evaluate potential existing tools and determine those that are optimal for extracting scientific knowledge from the available observations. We explore the possibility of using clustering algorithms to separate stellar populations with distinct chemical patterns. Star clusters are likely the most chemically homogeneous populations in the Galaxy, and therefore any practical approach to identifying distinct stellar populations should at least be able to separate clusters from each other. We applied eight clustering algorithms combined with four dimensionality reduction strategies to automatically distinguish stellar clusters using chemical abundances of 13 elements. Our sample includes 18 stellar clusters with a total of 453 stars. We use statistical tests showing that some pairs of clusters are indistinguishable from each other when chemical abundances from the Apache Point Galactic Evolution Experiment (APOGEE) are used. However, for most clusters we are able to automatically assign membership with metric scores similar to previous works. The confusion level of the automatically selected clusters is consistent with statistical tests that demonstrate the impossibility of perfectly distinguishing all the clusters from each other. These statistical tests and confusion levels establish a limit for the prospect of blindly identifying stars born in the same cluster based solely on chemical abundances. We find that some of the algorithms we explored are capable of blindly identify stellar populations with similar ages and chemical distributions in the APOGEE data. Because some stellar clusters are chemically indistinguishable, our study supports the notion of extending weak chemical tagging that involves families of clusters instead of individual clusters

References in corpus (52)

• The 2.5 m Telescope of the Sloan Digital Sky Survey
• The Apache Point Observatory Galactic Evolution Experiment (APOGEE)
• Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
• The New Galaxy: Signatures of its Formation
• New catalogue of optically visible open clusters and candidates
• ASPCAP: The Apogee Stellar Parameter and Chemical Abundances Pipeline
• The ACS Survey of Galactic Globular Clusters. VII. Relative Ages
• A Spectroscopic Study of the Ancient Milky Way: F- and G-Type Stars in the Third Data Release of the Sloan Digital Sky Survey
• Abundances, Stellar Parameters, and Spectra From the SDSS-III/APOGEE Survey
• High-Dimensional Data Clustering
• APOGEE Data Releases 13 and 14: Data and Analysis
• Chemical tagging with APOGEE: Discovery of a large population of N-rich stars in the inner Galaxy
• The influence of atomic diffusion on stellar ages and chemical tagging
• APOGEE Data Releases 13 and 14: Stellar Parameter and Abundance Comparisons With Independent Analyses
• The chemical homogeneity of open clusters
• Automated Classification of Stellar Spectra. II: Two-Dimensional Classification with Neural Networks and Principal Components Analysis
• The Open Cluster Chemical Analysis and Mapping Survey: Local Galactic Metallicity Gradient with APOGEE using SDSS DR10
• Accurate and homogeneous abundance patterns in solar-type stars of the solar neighbourhood: a chemo-chronological analysis
• Systematic search for extremely metal poor galaxies in the Sloan Digital Sky Survey
• Principal Component Analysis on Chemical Abundances Spaces
• Galactic Doppelganger: The chemical similarity among field stars and among stars with a common birth origin
• Dissecting stellar chemical abundance space with t-SNE
• Atypical Mg-poor Milky Way field stars with globular cluster second-generation like chemical patterns
• Automatic unsupervised classification of all SDSS/DR7 galaxy spectra
• Sodium and Oxygen Abundances in the Open Cluster NGC 6791 from APOGEE H-Band Spectroscopy
• The Galah Survey: Classification and diagnostics with t-SNE reduction of spectral information
• Chemical Abundances of Main-Sequence, Turn-off, Subgiant and red giant Stars from APOGEE spectra I: Signatures of Diffusion in the Open Cluster M67
• Testing the chemical tagging technique with open clusters
• Chemical tagging can work: Identification of stellar phase-space structures purely by chemical-abundance similarity
• Search for Extremely Metal-poor Galaxies in the Sloan Digital Sky Survey (II): high electron temperature objects
• Two estimates of the distance to the Galactic centre
• Reducing the Dimensionality of Data: Locally Linear Embedding of Sloan Galaxy Spectra
• The GALAH survey: Chemical Tagging of Star Clusters and New Members in the Pleiades
• Cosmic phylogeny: reconstructing the chemical history of the solar neighbourhood with an evolutionary tree
• Very metal-poor stars observed by the RAVE survey
• Quantifying Chemical Tagging: Towards Robust Group Finding in the Galaxy
• Detecting outliers and learning complex structures with large spectroscopic surveys - a case study with APOGEE stars
• RAVE stars in K2 - I. Improving RAVE red giants spectroscopy using asteroseismology from K2 Campaign 1
• Classification of Stellar Spectra with LLE
• Cosmic variance in [O/Fe] in the Galactic disk
• Automated unsupervised classification of the Sloan Digital Sky Survey stellar spectra using k-means clustering
• OB Stars in the Solar Neighborhood II: Kinematics
• Blind chemical tagging with DBSCAN: prospects for spectroscopic surveys
• The dimensionality of stellar chemical space using spectra from the Apache Point Observatory Galactic Evolution Experiment
• Chemical Abundances in a Sample of Red Giants in the Open Cluster NGC 2420 from APOGEE
• Timing the Evolution of the Galactic Disk with NGC 6791: An Open Cluster with Peculiar High-$\alpha$ Chemistry as seen by APOGEE
• BVI Photometry and the Luminosity Function of the Globular Cluster M92
• Search for blue compact dwarf galaxies during quiescence II: metallicities of gas and stars, ages, and star-formation rates
• Machine learning in APOGEE: Unsupervised spectral classification with $K$-means
• Chemo-Dynamical Clustering applied to APOGEE data: Re-Discovering Globular Clusters
• Clustering in the Stellar Abundances Space
• Comparing Simulated Emission from Molecular Clouds Using Experimental Design

Cited by in corpus (12)

• A review of unsupervised learning in astronomy
• Strong chemical tagging with APOGEE: 21 candidate star clusters that have dissolved across the Milky Way disc
• Open Cluster Chemical Homogeneity Throughout the Milky Way
• The (im)possibility of strong chemical tagging
• Data mining techniques on astronomical spectra data. I : Clustering Analysis
• A metallicity study of F, G, K and M dwarfs in the Coma Berenices open cluster from the APOGEE survey
• From birth associations to field stars: mapping the small-scale orbit distribution in the Galactic disc
• The Gaia-ESO Survey: Chemical tagging in the thin disk. Open clusters blindly recovered in the elemental abundance space
• The chemical enrichment of the Milky Way disk evaluated using conditional abundances
• Using heritability of stellar chemistry to reveal the history of the Milky Way
• Effects of secular growth and mergers on the evolution of metallicity gradients and azimuthal variations in a Milky Way-like galaxy
• Deep chemical tagging -- Identifying open clusters and moving groups in chemical space with graph attention networks