Related papers: Machine learning in APOGEE: Unsupervised spectral …
The second phase of the APOGEE survey is providing near-infrared, high-resolution, high signal-to-noise spectra of stars in the halo, disk, bar and bulge of the Milky Way. The near-infrared spectral window is especially important in the…
We are posting this 10-year-old white paper to support an upcoming survey description paper for the SDSS-III Apache Point Galactic Evolution Experiment (APOGEE) led by PI Dr. Steven Majewski. The white paper presented here was a…
Unveiling the evolutionary history of galaxies necessitates a precise understanding of their physical properties. Traditionally, astronomers achieve this through spectral energy distribution (SED) fitting. However, this approach can be…
K-means (MacQueen, 1967) [1] is one of the simplest unsupervised learning algorithms that solve the well-known clustering problem. The procedure follows a simple and easy way to classify a given data set to a predefined, say K number of…
The observable spectrum of an unresolved binary star system is a superposition of two single-star spectra. Even without a detectable velocity offset between the two stellar components, the combined spectrum of a binary system is in general…
We aim at searching for exoplanets on the whole ESO/VLT-SPHERE archive with improved and unsupervised data analysis algorithm that could allow to detect massive giant planets at 5 au. To prepare, test and optimize our approach, we gathered…
Chemical tagging of stars based on their similar compositions can offer new insights about the star formation and dynamical history of the Milky Way. We investigate the feasibility of identifying groups of stars in chemical space by…
Unsupervised feature selection has been always attracting research attention in the communities of machine learning and data mining for decades. In this paper, we propose an unsupervised feature selection method seeking a feature…
Stars born from the same molecular cloud should be nearly homogeneous in their element abundances. The concept of chemical tagging is to identify members of disrupted clusters by their clustering in element abundance space. Chemical tagging…
Learning from class-imbalanced data continues to be a common and challenging problem in supervised learning as standard classification algorithms are designed to handle balanced class distributions. While different strategies exist to…
We consider the problem of data clustering with unidentified feature quality and when a small amount of labelled data is provided. An unsupervised sparse clustering method can be employed in order to detect the subgroup of features…
Chemically tagging groups of stars born in the same birth cluster is a major goal of spectroscopic surveys. To investigate the feasibility of such strong chemical tagging, we perform a blind chemical tagging experiment on abundances…
With contemporary infrared spectroscopic surveys like APOGEE, red-giant stars can be observed to distances and extinctions at which Gaia parallaxes are not highly informative. Yet the combination of effective temperature, surface gravity,…
In order to obtain morphological information of unlabeled galaxies, we present an unsupervised machine-learning (UML) method for morphological classification of galaxies, which can be summarized as two aspects: (1) the methodology of…
In the search for metal-poor stars, large spectroscopic surveys are an invaluable tool. However, the spectra of metal-poor stars can be difficult to analyse because of the relative lack of available lines, which can also lead to…
The Open Cluster Chemical Abundances and Mapping (OCCAM) survey aims to produce a comprehensive, uniform, infrared-based spectroscopic dataset for hundreds of open clusters, and to constrain key Galactic dynamical and chemical parameters…
Constraints on the formation and evolution of the Milky Way Galaxy require multi-dimensional measurements of kinematics, abundances, and ages for a large population of stars. Ages for luminous giants, which can be seen to large distances,…
Every field of Science is undergoing unprecedented changes in the discovery process, and Astronomy has been a main player in this transition since the beginning. The ongoing and future large and complex multi-messenger sky surveys impose a…
Spectral clustering has found extensive use in many areas. Most traditional spectral clustering algorithms work in three separate steps: similarity graph construction; continuous labels learning; discretizing the learned labels by k-means…
Large catalogues are ubiquitous throughout astronomy, but most scientific analyses are carried out on smaller samples selected from these catalogues by chosen cuts on catalogued quantities. The selection function of that scientific sample -…