Via Machinae: Searching for Stellar Streams using Unsupervised Machine Learning

Abstract

We develop a new machine learning algorithm, Via Machinae, to identify cold stellar streams in data from the Gaia telescope. Via Machinae is based on ANODE, a general method that uses conditional density estimation and sideband interpolation to detect local overdensities in the data in a model agnostic way. By applying ANODE to the positions, proper motions, and photometry of stars observed by Gaia, Via Machinae obtains a collection of those stars deemed most likely to belong to a stellar stream. We further apply an automated line-finding method based on the Hough transform to search for line-like features in patches of the sky. In this paper, we describe the Via Machinae algorithm in detail and demonstrate our approach on the prominent stream GD-1. Though some parts of the algorithm are tuned to increase sensitivity to cold streams, the Via Machinae technique itself does not rely on astrophysical assumptions, such as the potential of the Milky Way or stellar isochrones. This flexibility suggests that it may have further applications in identifying other anomalous structures within the Gaia dataset, for example debris flow and globular clusters.

arXiv comment17 pages, 17 figures, v2: references added, minor corrections, v3: published version

References in corpus (60)

• Adam: A Method for Stochastic Optimization
• Astropy: A Community Python Package for Astronomy
• The Sloan Digital Sky Survey: Technical Summary
• Gaia Data Release 2. Summary of the contents and survey properties
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Gaia Data Release 2: The astrometric solution
• The merger that led to the formation of the Milky Way's inner stellar halo and thick disk
• Co-formation of the Galactic disc and the stellar halo
• The Field of Streams: Sagittarius and its Siblings
• The First Data Release (DR1) of the LAMOST general survey
• The Ghost of Sagittarius and Lumps in the Halo of the Milky Way
• Detection of massive tidal tails around the globular cluster Pal 5 with SDSS commissioning data
• Great Circle tidal streams: evidence for a nearly spherical massive dark halo around the Milky Way
• Building up the Stellar Halo of the Galaxy
• Constraining the Milky Way potential with a 6-D phase-space map of the GD-1 stellar stream
• Streams, substructures and the early history of the Milky Way
• Detection of a 63 Degree Cold Stellar Stream in the Sloan Digital Sky Survey
• Anomaly Detection with Density Estimation
• Fossil Signatures of Ancient Accretion Events in the Halo
• Cosmological simulations of the formation of the stellar haloes around disc galaxies
• Stellar Streams Discovered in the Dark Energy Survey
• A Prescription for Building the Milky Way's Halo from Disrupted Satellites
• Detection of a 60 Degree-Long Dwarf Galaxy Debris Stream
• Lambda-Cold Dark Matter, Stellar Feedback, and the Galactic Halo Abundance Pattern
• Tidal Streams as Probes of the Galactic Potential
• The Spur and the Gap in GD-1: Dynamical evidence for a dark substructure in the Milky Way halo
• Globular Cluster Streams as Galactic High-Precision Scales - The Poster Child Palomar 5
• Ghostly Tributaries to the Milky Way: Charting the Halo's Stellar Streams with the Gaia DR2 catalogue
• The Streams of the Gaping Abyss: A population of entangled stellar streams surrounding the Inner Galaxy
• Charting the Galactic acceleration field I. A search for stellar streams with Gaia DR2 and EDR3 with follow-up from ESPaDOnS and UVES
• A sharper view of Pal 5's tails: Discovery of stream perturbations with a novel non-parametric technique
• Phase-Space Distributions of Chemical Abundances in Milky Way-type Galaxy Halos
• Constraining the Milky Way Halo Potential with the GD-1 stellar stream
• Off the beaten path: Gaia reveals GD-1 stars outside of the main stream
• STREAMFINDER I: A New Algorithm for detecting Stellar Streams
• Inferred Evidence For Dark Matter Kinematic Substructure with SDSS-Gaia
• Extended stellar systems in the solar neighborhood - I. The tidal tails of the Hyades
• Stream-orbit misalignment I: The dangers of orbit-fitting
• Extended stellar systems in the solar neighborhood - II. Discovery of a nearby 120° stellar stream in Gaia DR2
• The Pal 5 Star Stream Gaps
• Stellar Streams as Probes of Dark Halo Mass and Morphology: A Bayesian Reconstruction
• Direct Detection of Dark Matter Debris Flows
• Evidence of a population of dark subhalos from Gaia and Pan-STARRS observations of the GD-1 stream
• Effects of baryonic and dark matter substructure on the Pal 5 stream
• Normalizing Flows on Tori and Spheres
• Completeness of the Gaia-verse II: what are the odds that a star is missing from Gaia DR2?
• Dynamics of stream-subhalo interactions
• StarGO: A New Method to Identify the Galactic Origins of Halo Stars
• Evidence of a dwarf galaxy stream populating the inner Milky Way Halo
• Under the Firelight: Stellar Tracers of the Local Dark Matter Velocity Distribution in the Milky Way
• Dark Matter Direct Search Rates in Simulations of the Milky Way and Sagittarius Stream
• Probing the nature of dark matter with accreted globular cluster streams
• High-resolution spectroscopy of the GD-1 stellar stream localizes the perturber near the orbital plane of Sagittarius
• Identifying Stellar Streams in Gaia DR2 with Data Mining Techniques
• Galactic potential constraints from clustering in action space of combined stellar stream data
• Phase-space correlation in stellar streams of the Milky Way halo: The clash of Kshir and GD-1
• The Hough Stream Spotter: A New Method for Detecting Linear Structure in Resolved Stars and Application to the Stellar Halo of M31
• Detecting Thin Stellar Streams in External Galaxies: Resolved Stars & Integrated Light
• STREAMFINDER II: A possible fanning structure parallel to the GD-1 stream in Pan-STARRS1

Cited by in corpus (21)

• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• The Hough Stream Spotter: A New Method for Detecting Linear Structure in Resolved Stars and Application to the Stellar Halo of M31
• The Interplay of Machine Learning--based Resonant Anomaly Detection Methods
• Anomaly Detection under Coordinate Transformations
• High-dimensional and Permutation Invariant Anomaly Detection
• Measuring Galactic Dark Matter through Unsupervised Machine Learning
• Prospects for Detecting Gaps in Globular Cluster Stellar Streams in External Galaxies with the Nancy Grace Roman Space Telescope
• Hidden deep in the halo: selection of a reduced proper motion halo catalogue and mining retrograde streams in the velocity space
• How well can we unravel the accreted constituents of the Milky Way stellar halo? A test on cosmological hydrodynamical simulations
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Exploring the ex-situ components within Gaia DR3
• Weakly-Supervised Anomaly Detection in the Milky Way
• Non-resonant Anomaly Detection with Background Extrapolation
• Simulation-based Anomaly Detection for Multileptons at the LHC
• GalaxyFlow: Upsampling Hydrodynamical Simulations for Realistic Mock Stellar Catalogs
• Sensitivity Estimation for Dark Matter Subhalos in Synthetic Gaia DR2 using Deep Learning
• Orbital phase-driven biases in Galactic mass constraints from stellar streams
• StarStream: Automatic detection algorithm for stellar streams
• Applying machine learning to Galactic Archaeology: how well can we recover the origin of stars in Milky Way-like galaxies?
• OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics