A Caltech Library Service

VIA MACHINAE: Searching for stellar streams using unsupervised machine learning

Shih, David and Buckley, Matthew R. and Necib, Lina and Tamanas, John (2022) VIA MACHINAE: Searching for stellar streams using unsupervised machine learning. Monthly Notices of the Royal Astronomical Society, 509 (4). pp. 5992-6007. ISSN 0035-8711. doi:10.1093/mnras/stab3372.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Accepted Version
Creative Commons Attribution.


Use this Persistent URL to link to this item:


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 data set, for example debris flow and globular clusters.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Shih, David0000-0003-3408-3871
Necib, Lina0000-0003-2806-1414
Additional Information:© 2021 The Author(s). Published by Oxford University Press on behalf of Royal Astronomical Society. This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model ( Accepted 2021 No v ember 17. Received 2021 November 15; in original form 2021 July 12. Published: 24 November 2021. We would like to thank A. Bonaca, D. Hogg, S. Pearson, A. Price-Whelan for helpful conversations; and Ting Li, Ben Nachman, and Bryan Ostdiek for comments on the manuscript. MB and DS are supported by the DOE under Award Number DOE-SC0010008. LN is supported by the DOE under Award Number DESC0011632, the Sherman Fairchild fellowship, the University of California Presidential fellowship, and the fellowship of theoretical astrophysics at Carnegie Observatories. LN is grateful for the generous support and hospitality of the Rutgers NHETC Visitor Program, where this work was initiated. This research used resources of the National Energy Research Scientific Computing Center (NERSC), a U.S. Department of Energy Office of Science User Facility operated under Contract No. DE-AC02-05CH11231. This work has made use of data from the European Space Agency (ESA) mission Gaia (, processed by the Gaia Data Processing and Analysis Consortium (DPAC, Funding for the DPAC has been provided by national institutions, in particular the institutions participating in the Gaia Multilateral Agreement. Data Availability: This paper made use of the publicly available Gaia DR2 data. For the GD-1 stars identified through our analysis, please email the corresponding author.
Group:Walter Burke Institute for Theoretical Physics
Funding AgencyGrant Number
Department of Energy (DOE)DOE-SC0010008
Department of Energy (DOE)DESC0011632
Sherman Fairchild FoundationUNSPECIFIED
University of CaliforniaUNSPECIFIED
Carnegie ObservatoriesUNSPECIFIED
Department of Energy (DOE)DE-AC02-05CH11231
Gaia Multilateral AgreementUNSPECIFIED
Subject Keywords:stars: kinematics and dynamics –galaxy: stellar content –galaxy: structure
Issue or Number:4
Record Number:CaltechAUTHORS:20220719-155886300
Persistent URL:
Official Citation:David Shih, Matthew R Buckley, Lina Necib, John Tamanas, VIA MACHINAE: Searching for stellar streams using unsupervised machine learning, Monthly Notices of the Royal Astronomical Society, Volume 509, Issue 4, February 2022, Pages 5992–6007,
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:115681
Deposited By: Tony Diaz
Deposited On:20 Jul 2022 16:34
Last Modified:20 Jul 2022 16:34

Repository Staff Only: item control page