Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV

Autores
Cabral, Juan Bautista; Lares, M.; Gurovich, Sebastian; Minniti, D.; Granitto, Pablo Miguel
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Context. As most of the modern astronomical sky surveys produce data faster than humans can analyse it, machine learning (ML) has become a central tool in astronomy. Modern ML methods can be characterised as highly resistant to some experimental errors. However, small changes in the data over long angular distances or long periods of time, which cannot be easily detected by statistical methods, can be detrimental to these methods. Aims. We develop a new strategy to cope with this problem, using ML methods in an innovative way to identify these potentially detrimental features. Methods. We introduce and discuss the notion of drifting features, related with small changes in the properties as measured in the data features. We use the identification techniques of RR Lyrae variable objects (RRLs) in the VVV based on an earlier work and introduce a method for detecting drifting features. For the VVV, each sky observation zone is called a tile. Our method forces the classifier to learn from the sources (mostly stellar 'point sources') which tile the source originated from and to select the features that are most relevant to the task of finding candidate drifting features. Results. We show that this method can efficiently identify a reduced set of features that contains useful information about the tile of origin of the sources. For our particular example of detecting RRLs in the VVV, we find that drifting features are mostly related to colour indices. On the other hand, we show that even if we have a clear set of drifting features in our problem, they are mostly insensitive to the identification of RRLs. Conclusions. Drifting features can be efficiently identified using ML methods. However, in our example removing drifting features does not improve the identification of RRLs.
Fil: Cabral, Juan Bautista. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; Argentina
Fil: Lares, M.. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; Argentina
Fil: Gurovich, Sebastian. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; Argentina
Fil: Minniti, D.. Universidad Andrés Bello; Chile. Vatican Observatory; Chile. Instituto Milenio de Astrofísica; Chile
Fil: Granitto, Pablo Miguel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; Argentina
Materia
CATALOGS
GALAXY: BULGE
METHODS: DATA ANALYSIS
METHODS: STATISTICAL
STARS: VARIABLES: RR LYRAE
SURVEYS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/182876

id CONICETDig_017d6a53bc35134e739d2b28f237df96
oai_identifier_str oai:ri.conicet.gov.ar:11336/182876
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVVCabral, Juan BautistaLares, M.Gurovich, SebastianMinniti, D.Granitto, Pablo MiguelCATALOGSGALAXY: BULGEMETHODS: DATA ANALYSISMETHODS: STATISTICALSTARS: VARIABLES: RR LYRAESURVEYShttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Context. As most of the modern astronomical sky surveys produce data faster than humans can analyse it, machine learning (ML) has become a central tool in astronomy. Modern ML methods can be characterised as highly resistant to some experimental errors. However, small changes in the data over long angular distances or long periods of time, which cannot be easily detected by statistical methods, can be detrimental to these methods. Aims. We develop a new strategy to cope with this problem, using ML methods in an innovative way to identify these potentially detrimental features. Methods. We introduce and discuss the notion of drifting features, related with small changes in the properties as measured in the data features. We use the identification techniques of RR Lyrae variable objects (RRLs) in the VVV based on an earlier work and introduce a method for detecting drifting features. For the VVV, each sky observation zone is called a tile. Our method forces the classifier to learn from the sources (mostly stellar 'point sources') which tile the source originated from and to select the features that are most relevant to the task of finding candidate drifting features. Results. We show that this method can efficiently identify a reduced set of features that contains useful information about the tile of origin of the sources. For our particular example of detecting RRLs in the VVV, we find that drifting features are mostly related to colour indices. On the other hand, we show that even if we have a clear set of drifting features in our problem, they are mostly insensitive to the identification of RRLs. Conclusions. Drifting features can be efficiently identified using ML methods. However, in our example removing drifting features does not improve the identification of RRLs.Fil: Cabral, Juan Bautista. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; ArgentinaFil: Lares, M.. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; ArgentinaFil: Gurovich, Sebastian. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; ArgentinaFil: Minniti, D.. Universidad Andrés Bello; Chile. Vatican Observatory; Chile. Instituto Milenio de Astrofísica; ChileFil: Granitto, Pablo Miguel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; ArgentinaEDP Sciences2021-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/182876Cabral, Juan Bautista; Lares, M.; Gurovich, Sebastian; Minniti, D.; Granitto, Pablo Miguel; Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV; EDP Sciences; Astronomy and Astrophysics; 652; A151; 8-2021; 1-120004-6361CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1051/0004-6361/202141247info:eu-repo/semantics/altIdentifier/url/https://www.aanda.org/articles/aa/full_html/2021/08/aa41247-21/aa41247-21.htmlinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:31:50Zoai:ri.conicet.gov.ar:11336/182876instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:31:51.088CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
title Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
spellingShingle Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
Cabral, Juan Bautista
CATALOGS
GALAXY: BULGE
METHODS: DATA ANALYSIS
METHODS: STATISTICAL
STARS: VARIABLES: RR LYRAE
SURVEYS
title_short Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
title_full Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
title_fullStr Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
title_full_unstemmed Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
title_sort Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV
dc.creator.none.fl_str_mv Cabral, Juan Bautista
Lares, M.
Gurovich, Sebastian
Minniti, D.
Granitto, Pablo Miguel
author Cabral, Juan Bautista
author_facet Cabral, Juan Bautista
Lares, M.
Gurovich, Sebastian
Minniti, D.
Granitto, Pablo Miguel
author_role author
author2 Lares, M.
Gurovich, Sebastian
Minniti, D.
Granitto, Pablo Miguel
author2_role author
author
author
author
dc.subject.none.fl_str_mv CATALOGS
GALAXY: BULGE
METHODS: DATA ANALYSIS
METHODS: STATISTICAL
STARS: VARIABLES: RR LYRAE
SURVEYS
topic CATALOGS
GALAXY: BULGE
METHODS: DATA ANALYSIS
METHODS: STATISTICAL
STARS: VARIABLES: RR LYRAE
SURVEYS
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Context. As most of the modern astronomical sky surveys produce data faster than humans can analyse it, machine learning (ML) has become a central tool in astronomy. Modern ML methods can be characterised as highly resistant to some experimental errors. However, small changes in the data over long angular distances or long periods of time, which cannot be easily detected by statistical methods, can be detrimental to these methods. Aims. We develop a new strategy to cope with this problem, using ML methods in an innovative way to identify these potentially detrimental features. Methods. We introduce and discuss the notion of drifting features, related with small changes in the properties as measured in the data features. We use the identification techniques of RR Lyrae variable objects (RRLs) in the VVV based on an earlier work and introduce a method for detecting drifting features. For the VVV, each sky observation zone is called a tile. Our method forces the classifier to learn from the sources (mostly stellar 'point sources') which tile the source originated from and to select the features that are most relevant to the task of finding candidate drifting features. Results. We show that this method can efficiently identify a reduced set of features that contains useful information about the tile of origin of the sources. For our particular example of detecting RRLs in the VVV, we find that drifting features are mostly related to colour indices. On the other hand, we show that even if we have a clear set of drifting features in our problem, they are mostly insensitive to the identification of RRLs. Conclusions. Drifting features can be efficiently identified using ML methods. However, in our example removing drifting features does not improve the identification of RRLs.
Fil: Cabral, Juan Bautista. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; Argentina
Fil: Lares, M.. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; Argentina
Fil: Gurovich, Sebastian. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Astronomía Teórica y Experimental. Universidad Nacional de Córdoba. Observatorio Astronómico de Córdoba. Instituto de Astronomía Teórica y Experimental; Argentina
Fil: Minniti, D.. Universidad Andrés Bello; Chile. Vatican Observatory; Chile. Instituto Milenio de Astrofísica; Chile
Fil: Granitto, Pablo Miguel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas. Universidad Nacional de Rosario. Centro Internacional Franco Argentino de Ciencias de la Información y de Sistemas; Argentina
description Context. As most of the modern astronomical sky surveys produce data faster than humans can analyse it, machine learning (ML) has become a central tool in astronomy. Modern ML methods can be characterised as highly resistant to some experimental errors. However, small changes in the data over long angular distances or long periods of time, which cannot be easily detected by statistical methods, can be detrimental to these methods. Aims. We develop a new strategy to cope with this problem, using ML methods in an innovative way to identify these potentially detrimental features. Methods. We introduce and discuss the notion of drifting features, related with small changes in the properties as measured in the data features. We use the identification techniques of RR Lyrae variable objects (RRLs) in the VVV based on an earlier work and introduce a method for detecting drifting features. For the VVV, each sky observation zone is called a tile. Our method forces the classifier to learn from the sources (mostly stellar 'point sources') which tile the source originated from and to select the features that are most relevant to the task of finding candidate drifting features. Results. We show that this method can efficiently identify a reduced set of features that contains useful information about the tile of origin of the sources. For our particular example of detecting RRLs in the VVV, we find that drifting features are mostly related to colour indices. On the other hand, we show that even if we have a clear set of drifting features in our problem, they are mostly insensitive to the identification of RRLs. Conclusions. Drifting features can be efficiently identified using ML methods. However, in our example removing drifting features does not improve the identification of RRLs.
publishDate 2021
dc.date.none.fl_str_mv 2021-08
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/182876
Cabral, Juan Bautista; Lares, M.; Gurovich, Sebastian; Minniti, D.; Granitto, Pablo Miguel; Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV; EDP Sciences; Astronomy and Astrophysics; 652; A151; 8-2021; 1-12
0004-6361
CONICET Digital
CONICET
url http://hdl.handle.net/11336/182876
identifier_str_mv Cabral, Juan Bautista; Lares, M.; Gurovich, Sebastian; Minniti, D.; Granitto, Pablo Miguel; Drifting features: Detection and evaluation in the context of automatic RR Lyrae identification in the VVV; EDP Sciences; Astronomy and Astrophysics; 652; A151; 8-2021; 1-12
0004-6361
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1051/0004-6361/202141247
info:eu-repo/semantics/altIdentifier/url/https://www.aanda.org/articles/aa/full_html/2021/08/aa41247-21/aa41247-21.html
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv EDP Sciences
publisher.none.fl_str_mv EDP Sciences
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614330218184704
score 13.070432