Identifying new X-ray binary candidates in M31 using random forest classification

ABSTRACT Identifying X-ray binary (XRB) candidates in nearby galaxies requires distinguishing them from possible contaminants including foreground stars and background active galactic nuclei. This work investigates the use of supervised machine learning algorithms to identify high-probability XRB ca...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Monthly notices of the Royal Astronomical Society 2020-03, Vol.492 (4), p.5075-5088
Hauptverfasser: Arnason, R M, Barmby, P, Vulic, N
Format: Artikel
Sprache:eng
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 5088
container_issue 4
container_start_page 5075
container_title Monthly notices of the Royal Astronomical Society
container_volume 492
creator Arnason, R M
Barmby, P
Vulic, N
description ABSTRACT Identifying X-ray binary (XRB) candidates in nearby galaxies requires distinguishing them from possible contaminants including foreground stars and background active galactic nuclei. This work investigates the use of supervised machine learning algorithms to identify high-probability XRB candidates. Using a catalogue of 943 Chandra X-ray sources in the Andromeda galaxy, we trained and tested several classification algorithms using the X-ray properties of 163 sources with previously known types. Amongst the algorithms tested, we find that random forest classifiers give the best performance and work better in a binary classification (XRB/non-XRB) context compared to the use of multiple classes. Evaluating our method by comparing with classifications from visible-light and hard X-ray observations as part of the Panchromatic Hubble Andromeda Treasury, we find compatibility at the 90 per cent level, although we caution that the number of source in common is rather small. The estimated probability that an object is an XRB agrees well between the random forest binary and multiclass approaches and we find that the classifications with the highest confidence are in the XRB class. The most discriminating X-ray bands for classification are the 1.7–2.8, 0.5–1.0, 2.0–4.0, and 2.0–7.0 keV photon flux ratios. Of the 780 unclassified sources in the Andromeda catalogue, we identify 16 new high-probability XRB candidates and tabulate their properties for follow-up.
doi_str_mv 10.1093/mnras/staa207
format Article
fullrecord <record><control><sourceid>oup_TOX</sourceid><recordid>TN_cdi_crossref_primary_10_1093_mnras_staa207</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/mnras/staa207</oup_id><sourcerecordid>10.1093/mnras/staa207</sourcerecordid><originalsourceid>FETCH-LOGICAL-c309t-15e00399d600e9daec823478eaf38f5d15e39e4dc0866c08dc0ab0293d31760d3</originalsourceid><addsrcrecordid>eNqFkMtLxDAQh4MoWFeP3nP0EnfStGlzlMXHwooICt7KbB4S2aZL0kX635t93L3MDDMfw4-PkFsO9xyUmPchYpqnEbGE5owUXMialUrKc1IAiJq1DeeX5CqlHwCoRCkL8r40NozeTT5802B_6ReLONG1DxgnqjEYb3C0ifpAXwWnu7QHY94PPXVDtGmkeoMpeec1jn4I1-TC4SbZm1Ofkc-nx4_FC1u9PS8XDyumBaiR8drmTEoZCWCVQavbUlRNa9GJ1tUm34WyldHQSplLHnANpRJG8EaCETPCjn91HFKK1nXb6PucuuPQ7X10Bx_dyUfm7478sNv-g_4B5FpkDg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Identifying new X-ray binary candidates in M31 using random forest classification</title><source>Oxford Journals Open Access Collection</source><creator>Arnason, R M ; Barmby, P ; Vulic, N</creator><creatorcontrib>Arnason, R M ; Barmby, P ; Vulic, N</creatorcontrib><description>ABSTRACT Identifying X-ray binary (XRB) candidates in nearby galaxies requires distinguishing them from possible contaminants including foreground stars and background active galactic nuclei. This work investigates the use of supervised machine learning algorithms to identify high-probability XRB candidates. Using a catalogue of 943 Chandra X-ray sources in the Andromeda galaxy, we trained and tested several classification algorithms using the X-ray properties of 163 sources with previously known types. Amongst the algorithms tested, we find that random forest classifiers give the best performance and work better in a binary classification (XRB/non-XRB) context compared to the use of multiple classes. Evaluating our method by comparing with classifications from visible-light and hard X-ray observations as part of the Panchromatic Hubble Andromeda Treasury, we find compatibility at the 90 per cent level, although we caution that the number of source in common is rather small. The estimated probability that an object is an XRB agrees well between the random forest binary and multiclass approaches and we find that the classifications with the highest confidence are in the XRB class. The most discriminating X-ray bands for classification are the 1.7–2.8, 0.5–1.0, 2.0–4.0, and 2.0–7.0 keV photon flux ratios. Of the 780 unclassified sources in the Andromeda catalogue, we identify 16 new high-probability XRB candidates and tabulate their properties for follow-up.</description><identifier>ISSN: 0035-8711</identifier><identifier>EISSN: 1365-2966</identifier><identifier>DOI: 10.1093/mnras/staa207</identifier><language>eng</language><publisher>Oxford University Press</publisher><ispartof>Monthly notices of the Royal Astronomical Society, 2020-03, Vol.492 (4), p.5075-5088</ispartof><rights>2020 The Author(s) Published by Oxford University Press on behalf of the Royal Astronomical Society 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c309t-15e00399d600e9daec823478eaf38f5d15e39e4dc0866c08dc0ab0293d31760d3</citedby><cites>FETCH-LOGICAL-c309t-15e00399d600e9daec823478eaf38f5d15e39e4dc0866c08dc0ab0293d31760d3</cites><orcidid>0000-0003-2767-0090 ; 0000-0001-7855-8336</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,1598,27901,27902</link.rule.ids><linktorsrc>$$Uhttps://dx.doi.org/10.1093/mnras/staa207$$EView_record_in_Oxford_University_Press$$FView_record_in_$$GOxford_University_Press</linktorsrc></links><search><creatorcontrib>Arnason, R M</creatorcontrib><creatorcontrib>Barmby, P</creatorcontrib><creatorcontrib>Vulic, N</creatorcontrib><title>Identifying new X-ray binary candidates in M31 using random forest classification</title><title>Monthly notices of the Royal Astronomical Society</title><description>ABSTRACT Identifying X-ray binary (XRB) candidates in nearby galaxies requires distinguishing them from possible contaminants including foreground stars and background active galactic nuclei. This work investigates the use of supervised machine learning algorithms to identify high-probability XRB candidates. Using a catalogue of 943 Chandra X-ray sources in the Andromeda galaxy, we trained and tested several classification algorithms using the X-ray properties of 163 sources with previously known types. Amongst the algorithms tested, we find that random forest classifiers give the best performance and work better in a binary classification (XRB/non-XRB) context compared to the use of multiple classes. Evaluating our method by comparing with classifications from visible-light and hard X-ray observations as part of the Panchromatic Hubble Andromeda Treasury, we find compatibility at the 90 per cent level, although we caution that the number of source in common is rather small. The estimated probability that an object is an XRB agrees well between the random forest binary and multiclass approaches and we find that the classifications with the highest confidence are in the XRB class. The most discriminating X-ray bands for classification are the 1.7–2.8, 0.5–1.0, 2.0–4.0, and 2.0–7.0 keV photon flux ratios. Of the 780 unclassified sources in the Andromeda catalogue, we identify 16 new high-probability XRB candidates and tabulate their properties for follow-up.</description><issn>0035-8711</issn><issn>1365-2966</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNqFkMtLxDAQh4MoWFeP3nP0EnfStGlzlMXHwooICt7KbB4S2aZL0kX635t93L3MDDMfw4-PkFsO9xyUmPchYpqnEbGE5owUXMialUrKc1IAiJq1DeeX5CqlHwCoRCkL8r40NozeTT5802B_6ReLONG1DxgnqjEYb3C0ifpAXwWnu7QHY94PPXVDtGmkeoMpeec1jn4I1-TC4SbZm1Ofkc-nx4_FC1u9PS8XDyumBaiR8drmTEoZCWCVQavbUlRNa9GJ1tUm34WyldHQSplLHnANpRJG8EaCETPCjn91HFKK1nXb6PucuuPQ7X10Bx_dyUfm7478sNv-g_4B5FpkDg</recordid><startdate>20200311</startdate><enddate>20200311</enddate><creator>Arnason, R M</creator><creator>Barmby, P</creator><creator>Vulic, N</creator><general>Oxford University Press</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-2767-0090</orcidid><orcidid>https://orcid.org/0000-0001-7855-8336</orcidid></search><sort><creationdate>20200311</creationdate><title>Identifying new X-ray binary candidates in M31 using random forest classification</title><author>Arnason, R M ; Barmby, P ; Vulic, N</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c309t-15e00399d600e9daec823478eaf38f5d15e39e4dc0866c08dc0ab0293d31760d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Arnason, R M</creatorcontrib><creatorcontrib>Barmby, P</creatorcontrib><creatorcontrib>Vulic, N</creatorcontrib><collection>CrossRef</collection><jtitle>Monthly notices of the Royal Astronomical Society</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Arnason, R M</au><au>Barmby, P</au><au>Vulic, N</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Identifying new X-ray binary candidates in M31 using random forest classification</atitle><jtitle>Monthly notices of the Royal Astronomical Society</jtitle><date>2020-03-11</date><risdate>2020</risdate><volume>492</volume><issue>4</issue><spage>5075</spage><epage>5088</epage><pages>5075-5088</pages><issn>0035-8711</issn><eissn>1365-2966</eissn><abstract>ABSTRACT Identifying X-ray binary (XRB) candidates in nearby galaxies requires distinguishing them from possible contaminants including foreground stars and background active galactic nuclei. This work investigates the use of supervised machine learning algorithms to identify high-probability XRB candidates. Using a catalogue of 943 Chandra X-ray sources in the Andromeda galaxy, we trained and tested several classification algorithms using the X-ray properties of 163 sources with previously known types. Amongst the algorithms tested, we find that random forest classifiers give the best performance and work better in a binary classification (XRB/non-XRB) context compared to the use of multiple classes. Evaluating our method by comparing with classifications from visible-light and hard X-ray observations as part of the Panchromatic Hubble Andromeda Treasury, we find compatibility at the 90 per cent level, although we caution that the number of source in common is rather small. The estimated probability that an object is an XRB agrees well between the random forest binary and multiclass approaches and we find that the classifications with the highest confidence are in the XRB class. The most discriminating X-ray bands for classification are the 1.7–2.8, 0.5–1.0, 2.0–4.0, and 2.0–7.0 keV photon flux ratios. Of the 780 unclassified sources in the Andromeda catalogue, we identify 16 new high-probability XRB candidates and tabulate their properties for follow-up.</abstract><pub>Oxford University Press</pub><doi>10.1093/mnras/staa207</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0003-2767-0090</orcidid><orcidid>https://orcid.org/0000-0001-7855-8336</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 0035-8711
ispartof Monthly notices of the Royal Astronomical Society, 2020-03, Vol.492 (4), p.5075-5088
issn 0035-8711
1365-2966
language eng
recordid cdi_crossref_primary_10_1093_mnras_staa207
source Oxford Journals Open Access Collection
title Identifying new X-ray binary candidates in M31 using random forest classification
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T14%3A47%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-oup_TOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Identifying%20new%20X-ray%20binary%20candidates%20in%20M31%20using%20random%20forest%20classification&rft.jtitle=Monthly%20notices%20of%20the%20Royal%20Astronomical%20Society&rft.au=Arnason,%20R%20M&rft.date=2020-03-11&rft.volume=492&rft.issue=4&rft.spage=5075&rft.epage=5088&rft.pages=5075-5088&rft.issn=0035-8711&rft.eissn=1365-2966&rft_id=info:doi/10.1093/mnras/staa207&rft_dat=%3Coup_TOX%3E10.1093/mnras/staa207%3C/oup_TOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_oup_id=10.1093/mnras/staa207&rfr_iscdi=true