Convolutional neural networks for transient candidate vetting in large-scale surveys
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/18687 |
Resumo: | Current synoptic sky surveys monitor large areas of the sky to find variable and transient astronomical sources. As the number of detections per night at a single telescope easily exceeds several thousand, current detection pipelines make intensive use of machine learning algorithms to classify the detected objects and to filter out the most interesting candidates. A number of upcoming surveys will produce up to three orders of magnitude more data, which renders high-precision classification systems essential to reduce the manual and, hence, expensive vetting by human experts. We present an approach based on convolutional neural networks to discriminate between true astrophysical sources and artefacts in reference-subtracted optical images. We show that relatively simple networks are already competitive with state-of-the-art systems and that their quality can further be improved via slightly deeper networks and additional pre-processing steps – eventually yielding models outperforming state-of-the-art systems. In particular, our best model correctly classifies about 97.3 per cent of all ‘real’ and 99.7 per cent of all ‘bogus’ instances on a test set containing 1942 ‘bogus’ and 227 ‘real’ instances in total. Furthermore, the networks considered in this work can also successfully classify these objects at hand without relying on difference images, which might pave the way for future detection pipelines not containing image subtraction steps at all. |
id |
RCAP_9b776504ac0e0630c2625183aa67e271 |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/18687 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Convolutional neural networks for transient candidate vetting in large-scale surveyssurveysTechniques: image processingMethods: data analysisSupernovae: generalCurrent synoptic sky surveys monitor large areas of the sky to find variable and transient astronomical sources. As the number of detections per night at a single telescope easily exceeds several thousand, current detection pipelines make intensive use of machine learning algorithms to classify the detected objects and to filter out the most interesting candidates. A number of upcoming surveys will produce up to three orders of magnitude more data, which renders high-precision classification systems essential to reduce the manual and, hence, expensive vetting by human experts. We present an approach based on convolutional neural networks to discriminate between true astrophysical sources and artefacts in reference-subtracted optical images. We show that relatively simple networks are already competitive with state-of-the-art systems and that their quality can further be improved via slightly deeper networks and additional pre-processing steps – eventually yielding models outperforming state-of-the-art systems. In particular, our best model correctly classifies about 97.3 per cent of all ‘real’ and 99.7 per cent of all ‘bogus’ instances on a test set containing 1942 ‘bogus’ and 227 ‘real’ instances in total. Furthermore, the networks considered in this work can also successfully classify these objects at hand without relying on difference images, which might pave the way for future detection pipelines not containing image subtraction steps at all.Oxford University Press2017-10-31T13:44:20Z2017-12-11T00:00:00Z2017-12-11info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10773/18687eng1365-296610.1093/mnras/stx2161Gieseke, FabianBloemen, Stevenvan den Bogaard, CasHeskes, TomKindler, JonasScalzo, Richard A.Ribeiro, Valério A. R. M.van Roestel, JanGroot, Paul J.Yuan, FangMöller, AnaisTucker, Brad E.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T11:36:11Zoai:ria.ua.pt:10773/18687Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T02:53:37.078049Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Convolutional neural networks for transient candidate vetting in large-scale surveys |
title |
Convolutional neural networks for transient candidate vetting in large-scale surveys |
spellingShingle |
Convolutional neural networks for transient candidate vetting in large-scale surveys Gieseke, Fabian surveys Techniques: image processing Methods: data analysis Supernovae: general |
title_short |
Convolutional neural networks for transient candidate vetting in large-scale surveys |
title_full |
Convolutional neural networks for transient candidate vetting in large-scale surveys |
title_fullStr |
Convolutional neural networks for transient candidate vetting in large-scale surveys |
title_full_unstemmed |
Convolutional neural networks for transient candidate vetting in large-scale surveys |
title_sort |
Convolutional neural networks for transient candidate vetting in large-scale surveys |
author |
Gieseke, Fabian |
author_facet |
Gieseke, Fabian Bloemen, Steven van den Bogaard, Cas Heskes, Tom Kindler, Jonas Scalzo, Richard A. Ribeiro, Valério A. R. M. van Roestel, Jan Groot, Paul J. Yuan, Fang Möller, Anais Tucker, Brad E. |
author_role |
author |
author2 |
Bloemen, Steven van den Bogaard, Cas Heskes, Tom Kindler, Jonas Scalzo, Richard A. Ribeiro, Valério A. R. M. van Roestel, Jan Groot, Paul J. Yuan, Fang Möller, Anais Tucker, Brad E. |
author2_role |
author author author author author author author author author author author |
dc.contributor.author.fl_str_mv |
Gieseke, Fabian Bloemen, Steven van den Bogaard, Cas Heskes, Tom Kindler, Jonas Scalzo, Richard A. Ribeiro, Valério A. R. M. van Roestel, Jan Groot, Paul J. Yuan, Fang Möller, Anais Tucker, Brad E. |
dc.subject.por.fl_str_mv |
surveys Techniques: image processing Methods: data analysis Supernovae: general |
topic |
surveys Techniques: image processing Methods: data analysis Supernovae: general |
description |
Current synoptic sky surveys monitor large areas of the sky to find variable and transient astronomical sources. As the number of detections per night at a single telescope easily exceeds several thousand, current detection pipelines make intensive use of machine learning algorithms to classify the detected objects and to filter out the most interesting candidates. A number of upcoming surveys will produce up to three orders of magnitude more data, which renders high-precision classification systems essential to reduce the manual and, hence, expensive vetting by human experts. We present an approach based on convolutional neural networks to discriminate between true astrophysical sources and artefacts in reference-subtracted optical images. We show that relatively simple networks are already competitive with state-of-the-art systems and that their quality can further be improved via slightly deeper networks and additional pre-processing steps – eventually yielding models outperforming state-of-the-art systems. In particular, our best model correctly classifies about 97.3 per cent of all ‘real’ and 99.7 per cent of all ‘bogus’ instances on a test set containing 1942 ‘bogus’ and 227 ‘real’ instances in total. Furthermore, the networks considered in this work can also successfully classify these objects at hand without relying on difference images, which might pave the way for future detection pipelines not containing image subtraction steps at all. |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-10-31T13:44:20Z 2017-12-11T00:00:00Z 2017-12-11 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10773/18687 |
url |
http://hdl.handle.net/10773/18687 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1365-2966 10.1093/mnras/stx2161 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Oxford University Press |
publisher.none.fl_str_mv |
Oxford University Press |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799137587836747776 |