Weakly-Supervised Anomaly Detection in the Milky Way

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pettee, Mariel, Thanvantri, Sowmya, Nachman, Benjamin, Shih, David, Buckley, Matthew R., Collins, Jack H.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917863250460672
author Pettee, Mariel
Thanvantri, Sowmya
Nachman, Benjamin
Shih, David
Buckley, Matthew R.
Collins, Jack H.
author_facet Pettee, Mariel
Thanvantri, Sowmya
Nachman, Benjamin
Shih, David
Buckley, Matthew R.
Collins, Jack H.
contents Large-scale astrophysics datasets present an opportunity for new machine learning techniques to identify regions of interest that might otherwise be overlooked by traditional searches. To this end, we use Classification Without Labels (CWoLa), a weakly-supervised anomaly detection method, to identify cold stellar streams within the more than one billion Milky Way stars observed by the Gaia satellite. CWoLa operates without the use of labeled streams or knowledge of astrophysical principles. Instead, we train a classifier to distinguish between mixed samples for which the proportions of signal and background samples are unknown. This computationally lightweight strategy is able to detect both simulated streams and the known stream GD-1 in data. Originally designed for high-energy collider physics, this technique may have broad applicability within astrophysics as well as other domains interested in identifying localized anomalies.
format Preprint
id arxiv_https___arxiv_org_abs_2305_03761
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Weakly-Supervised Anomaly Detection in the Milky Way
Pettee, Mariel
Thanvantri, Sowmya
Nachman, Benjamin
Shih, David
Buckley, Matthew R.
Collins, Jack H.
Astrophysics of Galaxies
Machine Learning
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
Large-scale astrophysics datasets present an opportunity for new machine learning techniques to identify regions of interest that might otherwise be overlooked by traditional searches. To this end, we use Classification Without Labels (CWoLa), a weakly-supervised anomaly detection method, to identify cold stellar streams within the more than one billion Milky Way stars observed by the Gaia satellite. CWoLa operates without the use of labeled streams or knowledge of astrophysical principles. Instead, we train a classifier to distinguish between mixed samples for which the proportions of signal and background samples are unknown. This computationally lightweight strategy is able to detect both simulated streams and the known stream GD-1 in data. Originally designed for high-energy collider physics, this technique may have broad applicability within astrophysics as well as other domains interested in identifying localized anomalies.
title Weakly-Supervised Anomaly Detection in the Milky Way
topic Astrophysics of Galaxies
Machine Learning
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2305.03761