University of Hertfordshire

From the same journal

From the same journal

By the same authors

An automatic taxonomy of galaxy morphology using unsupervised machine learning

Research output: Contribution to journalArticle

Standard

An automatic taxonomy of galaxy morphology using unsupervised machine learning. / Hocking, Alex; Geach, James E.; Sun, Yi; Davey, Neil.

In: Monthly Notices of the Royal Astronomical Society, Vol. 473, No. 1, 15.09.2017, p. 1108-1129.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Bibtex

@article{f1bc4eb19c4744bdbf5a25bb77263595,
title = "An automatic taxonomy of galaxy morphology using unsupervised machine learning",
abstract = "We present an unsupervised machine learning technique that automatically segments and labels galaxies in astronomical imaging surveys using only pixel data. Distinct from previous unsupervised machine learning approaches used in astronomy we use no pre-selection or pre-filtering of target galaxy type to identify galaxies that are similar. We demonstrate the technique on the Hubble Space Telescope (HST) Frontier Fields. By training the algorithm using galaxies from one field (Abell 2744) and applying the result to another (MACS 0416.1-2403), we show how the algorithm can cleanly separate early and late type galaxies without any form of pre-directed training for what an 'early' or 'late' type galaxy is. We then apply the technique to the HST Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) fields, creating a catalogue of approximately 60 000 classifications. We show how the automatic classification groups galaxies of similar morphological (and photometric) type and make the classifications public via a catalogue, a visual catalogue and galaxy similarity search. We compare the CANDELS machine-based classifications to human-classifications from the Galaxy Zoo: CANDELS project. Although there is not a direct mapping between Galaxy Zoo and our hierarchical labelling, we demonstrate a good level of concordance between human and machine classifications. Finally, we show how the technique can be used to identify rarer objects and present lensed galaxy candidates from the CANDELS imaging.",
keywords = "Methods: data analysis, Methods: observational, Methods: statistical",
author = "Alex Hocking and Geach, {James E.} and Yi Sun and Neil Davey",
note = "This article has been accepted for publication in Monthly Notices of the Royal Astronomical Society {\textcopyright}: 2017 the Author (s). Published by Oxford University Press on behalf of the Royal Astronomical Society. All rights reserved",
year = "2017",
month = sep,
day = "15",
doi = "10.1093/mnras/stx2351",
language = "English",
volume = "473",
pages = "1108--1129",
journal = "Monthly Notices of the Royal Astronomical Society",
issn = "0035-8711",
publisher = "Oxford University Press",
number = "1",

}

RIS

TY - JOUR

T1 - An automatic taxonomy of galaxy morphology using unsupervised machine learning

AU - Hocking, Alex

AU - Geach, James E.

AU - Sun, Yi

AU - Davey, Neil

N1 - This article has been accepted for publication in Monthly Notices of the Royal Astronomical Society ©: 2017 the Author (s). Published by Oxford University Press on behalf of the Royal Astronomical Society. All rights reserved

PY - 2017/9/15

Y1 - 2017/9/15

N2 - We present an unsupervised machine learning technique that automatically segments and labels galaxies in astronomical imaging surveys using only pixel data. Distinct from previous unsupervised machine learning approaches used in astronomy we use no pre-selection or pre-filtering of target galaxy type to identify galaxies that are similar. We demonstrate the technique on the Hubble Space Telescope (HST) Frontier Fields. By training the algorithm using galaxies from one field (Abell 2744) and applying the result to another (MACS 0416.1-2403), we show how the algorithm can cleanly separate early and late type galaxies without any form of pre-directed training for what an 'early' or 'late' type galaxy is. We then apply the technique to the HST Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) fields, creating a catalogue of approximately 60 000 classifications. We show how the automatic classification groups galaxies of similar morphological (and photometric) type and make the classifications public via a catalogue, a visual catalogue and galaxy similarity search. We compare the CANDELS machine-based classifications to human-classifications from the Galaxy Zoo: CANDELS project. Although there is not a direct mapping between Galaxy Zoo and our hierarchical labelling, we demonstrate a good level of concordance between human and machine classifications. Finally, we show how the technique can be used to identify rarer objects and present lensed galaxy candidates from the CANDELS imaging.

AB - We present an unsupervised machine learning technique that automatically segments and labels galaxies in astronomical imaging surveys using only pixel data. Distinct from previous unsupervised machine learning approaches used in astronomy we use no pre-selection or pre-filtering of target galaxy type to identify galaxies that are similar. We demonstrate the technique on the Hubble Space Telescope (HST) Frontier Fields. By training the algorithm using galaxies from one field (Abell 2744) and applying the result to another (MACS 0416.1-2403), we show how the algorithm can cleanly separate early and late type galaxies without any form of pre-directed training for what an 'early' or 'late' type galaxy is. We then apply the technique to the HST Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) fields, creating a catalogue of approximately 60 000 classifications. We show how the automatic classification groups galaxies of similar morphological (and photometric) type and make the classifications public via a catalogue, a visual catalogue and galaxy similarity search. We compare the CANDELS machine-based classifications to human-classifications from the Galaxy Zoo: CANDELS project. Although there is not a direct mapping between Galaxy Zoo and our hierarchical labelling, we demonstrate a good level of concordance between human and machine classifications. Finally, we show how the technique can be used to identify rarer objects and present lensed galaxy candidates from the CANDELS imaging.

KW - Methods: data analysis

KW - Methods: observational

KW - Methods: statistical

UR - http://www.scopus.com/inward/record.url?scp=85032578083&partnerID=8YFLogxK

U2 - 10.1093/mnras/stx2351

DO - 10.1093/mnras/stx2351

M3 - Article

AN - SCOPUS:85032578083

VL - 473

SP - 1108

EP - 1129

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

SN - 0035-8711

IS - 1

ER -