Machine Learning the 6th Dimension: Stellar Radial Velocities from 5D Phase-Space Correlations

Abstract

The Gaia satellite will observe the positions and velocities of over a billion Milky Way stars. In the early data releases, the majority of observed stars do not have complete 6D phase-space information. In this Letter, we demonstrate the ability to infer the missing line-of-sight velocities until more spectroscopic observations become available. We utilize a novel neural network architecture that, after being trained on a subset of data with complete phase-space information, takes in a star's 5D astrometry (angular coordinates, proper motions, and parallax) and outputs a predicted line-of-sight velocity with an associated uncertainty. Working with a mock Gaia catalog, we show that the network can successfully recover the distributions and correlations of each velocity component for stars that fall within ~5 kpc of the Sun. We also demonstrate that the network can accurately reconstruct the velocity distribution of a kinematic substructure in the stellar halo that is spatially uniform, even when it comprises a small fraction of the total star count.

arXiv comment7+9 pages, 3+4 figures, v2: minor revisions (typos and clarification), method and conclusions unchanged, published in ApJL

References in corpus (24)

• Astropy: A Community Python Package for Astronomy
• The NumPy array: a structure for efficient numerical computation
• The Gaia mission
• Variational Inference: A Review for Statisticians
• The Apache Point Observatory Galactic Evolution Experiment (APOGEE)
• The merger that led to the formation of the Milky Way's inner stellar halo and thick disk
• SEGUE: A Spectroscopic Survey of 240,000 stars with g=14-20
• Tracing Galaxy Formation with Stellar Halos I: Methods
• Co-formation of the Galactic disc and the stellar halo
• The GALAH+ Survey: Third Data Release
• The Radial Velocity Experiment (RAVE): Fifth Data Release
• Gaia Data Release 2: Mapping the Milky Way disc kinematics
• Galaxia: a code to generate a synthetic survey of the Milky Way
• Fossil Signatures of Ancient Accretion Events in the Halo
• A Prescription for Building the Milky Way's Halo from Disrupted Satellites
• On Galactic density modeling in the presence of dust extinction
• Gaia Data Release 2: Properties and validation of the radial velocities
• Characterization and history of the Helmi streams with Gaia DR2
• Inferred Evidence For Dark Matter Kinematic Substructure with SDSS-Gaia
• Spectroscopic Survey of the Galaxy with Gaia II. The expected science yield from the Radial Velocity Spectrometer
• Deep-Learning Jets with Uncertainties and More
• A Gaia DR2 Mock Stellar Catalog
• Hierarchical Inference With Bayesian Neural Networks: An Application to Strong Gravitational Lensing
• Application of Bayesian Neural Networks to Energy Reconstruction in EAS Experiments for ground-based TeV Astrophysics

Cited by in corpus (8)

• Neural networks: solving the chemistry of the interstellar medium
• Star-Image Centering with Deep Learning: HST/WFPC2 Images
• The missing radial velocities of Gaia: blind predictions for DR3
• Revealing the Milky Way's Most Recent Major Merger with a Gaia EDR3 Catalog of Machine-Learned Line-of-Sight Velocities
• The missing radial velocities of Gaia: a catalogue of Bayesian estimates for DR3
• Analysis of a hadron beam in five-dimensional phase space
• The 3D Galactocentric velocities of Kepler stars: marginalizing over missing RVs
• Charting galactic accelerations II: how to 'learn' accelerations in the solar neighbourhood