Detecting outliers and learning complex structures with large spectroscopic surveys - a case study with APOGEE stars

Abstract

In this work we apply and expand on a recently introduced outlier detection algorithm that is based on an unsupervised random forest. We use the algorithm to calculate a similarity measure for stellar spectra from the Apache Point Observatory Galactic Evolution Experiment (APOGEE). We show that the similarity measure traces non-trivial physical properties and contains information about complex structures in the data. We use it for visualization and clustering of the dataset, and discuss its ability to find groups of highly similar objects, including spectroscopic twins. Using the similarity matrix to search the dataset for objects allows us to find objects that are impossible to find using their best fitting model parameters. This includes extreme objects for which the models fail, and rare objects that are outside the scope of the model. We use the similarity measure to detect outliers in the dataset, and find a number of previously unknown Be-type stars, spectroscopic binaries, carbon rich stars, young stars, and a few that we cannot interpret. Our work further demonstrates the potential for scientific discovery when combining machine learning methods with modern survey data.

Published version. Data products from this work are available online, see github.com/ireis/APOGEE_tSNE_nb

References in corpus (13)

• Target Selection for the SDSS-IV APOGEE-2 Survey
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• The APOGEE red-clump catalog: Precise distances, velocities, and high-resolution elemental abundances over a large area of the Milky Way's disk
• Tracing chemical evolution over the extent of the Milky Way's Disk with APOGEE Red Clump Stars
• Young [$\alpha$/Fe]-enhanced stars discovered by CoRoT and APOGEE: What is their origin?
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• IN-SYNC I: Homogeneous Stellar Parameters from High Resolution APOGEE Spectra for Thousands of Pre-main Sequence Star
• Atypical Mg-poor Milky Way field stars with globular cluster second-generation like chemical patterns
• High-resolution, H band Spectroscopy of Be Stars with SDSS-III/APOGEE: I. New Be Stars, Line Identifications, and Line Profiles
• Evidence of ongoing AGN-driven feedback in a quiescent post starburst E+A galaxy
• Machine learning in APOGEE: Unsupervised spectral classification with $K$-means
• Preparing for advanced LIGO: A Star-Galaxy Separation Catalog for the Palomar Transient Factory
• Climbing the cosmic ladder with stellar twins in RAVE with Gaia

Cited by in corpus (31)

• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Probabilistic Random Forest: A machine learning algorithm for noisy datasets
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Discovery and Characterization of 3000+ Main-Sequence Binaries from APOGEE Spectra
• Dissecting stellar chemical abundance space with t-SNE
• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• A review of unsupervised learning in astronomy
• Data mining techniques on astronomical spectra data. II : Classification Analysis
• Dynamical Orbital classification of selected N-rich stars with \textit{Gaia} DR2 astrometry
• Discovery of a nitrogen-enhanced mildly metal-poor binary system: Possible evidence for pollution from an extinct AGB Star
• Machine learning in APOGEE: Unsupervised spectral classification with $K$-means
• A method for finding anomalous astronomical light curves and their analogs
• The High Cadence Transient Survey (HITS): Compilation and characterization of light-curve catalogs
• A semi-supervised Machine Learning search for never-seen Gravitational-Wave sources
• Machine learning in APOGEE: Identification of stellar populations through chemical abundances
• Exploring X-ray variability with unsupervised machine learning I. Self-organizing maps applied to XMM-Newton data
• Wide Area VISTA Extra-galactic Survey (WAVES): Unsupervised star-galaxy separation on the WAVES-Wide photometric input catalogue using UMAP and $\mathrm{HDBSCAN}$
• The VVV near-IR galaxy catalogue in a Northern part of the Galactic disc
• A Census of Protostellar Outflows in Nearby Molecular Clouds
• The VMC Survey -- XLIX. Discovery of a population of quasars dominated by nuclear dust emission behind the Magellanic Clouds
• Redshifted broad absorption line quasars found via machine-learned spectral similarity
• Approximate analytical description of the high latitude extinction
• Characterization of Supernovae Based on the Spectral-Temporal Energy Distribution: Possible two SN Ib Subtypes
• Study on Outliers in the Big Stellar Spectral Dataset of the Fifth Data Release (DR5) of the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST)
• Spectroscopic observations of the machine-learning selected anomaly catalogue from the AllWISE Sky Survey
• Realizing the potential of astrostatistics and astroinformatics
• Interpreting anomaly detection of SDSS spectra
• Euclid preparation. Estimating galaxy physical properties using CatBoost chained regressors with attention
• Visualization in Astrophysics: Developing New Methods, Discovering Our Universe, and Educating the Earth
• Early Detection of Multiwavelength Blazar Variability
• Neural Symplectic Integrator with Hamiltonian Inductive Bias for the Gravitational $N$-body Problem