Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
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/10316/105043 https://doi.org/10.1007/JHEP01(2021)189 |
Resumo: | Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in 136Xe. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6MeV gamma rays from a 228Th calibration source. We train a network on Monte Carlosimulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offers significant improvement in signal efficiency and background rejection when compared to previous non-CNN-based analyses. |
id |
RCAP_ecdc04975b37d2fd42076296e7590c97 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/105043 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experimentDark Matter and Double Beta Decay (experiments)Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in 136Xe. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6MeV gamma rays from a 228Th calibration source. We train a network on Monte Carlosimulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offers significant improvement in signal efficiency and background rejection when compared to previous non-CNN-based analyses.This study used computing resources from Artemisa, co-funded by the European Union through the 2014-2020 FEDER Operative Programme of the Comunitat Valenciana, project DIFEDER/2018/048. This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357. The NEXT collaboration acknowledges support from the following agencies and institutions: Xunta de Galicia (Centro singularde investigación de Galicia accreditation 2019-2022), by European Union ERDF, and by the “María de Maeztu” Units of Excellence program MDM-2016-0692 and the Spanish Research State Agency”; the European Research Council (ERC) under the Advanced Grant 339787-NEXT; the European Union’s Framework Programme for Research and Innovation Horizon 2020 (2014-2020) under the Grant Agreements No. 674896, 690575 and 740055; the Ministerio de Economía y Competitividad and the Ministerio de Ciencia, Innovación y Universidades of Spain under grants FIS2014-53371-C04, RTI2018-095979, the Severo Ochoa Program grants SEV-2014- 0398 and CEX2018-000867-S; the GVA of Spain under grants PROMETEO/2016/120 and SEJI/2017/011; the Portuguese FCT under project PTDC/FIS- NUC/2525/2014 and under projects UID/FIS/04559/2020 to fund the activities of LIBPhys-UC; the U.S. Department of Energy under contracts number DE-AC02-07CH11359 (Fermi National Accelerator Laboratory), DE-FG02-13ER42020 (Texas A&M) and DE-SC0019223/DE SC0019054 (University of Texas at Arlington); and the University of Texas at Arlington. DGD acknowledges Ramon y Cajal program (Spain) under contract number RYC-2015 18820. JMA acknowledges support from Fundación Bancaria “la Caixa” (ID 100010434), grant code LCF/BQ/PI19/11690012. We also warmly acknowledge the Laboratori Nazionali del Gran Sasso (LNGS) and the Dark Side collaboration for their help with TPB coating of various parts of the NEXT-White TPC. Finally, we are grateful to the Laboratorio Subterráneo de Canfranc for hosting and supporting the NEXT experiment.Springer Nature2021-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/105043http://hdl.handle.net/10316/105043https://doi.org/10.1007/JHEP01(2021)189engBorges, F. I. G. M.Conde, C. A. N.Fernandes, A. F. M.Fernandes, L. M. P.Freitas, E. D. C.Henriques, C. A. O.Escada, J.Mano, R.D.P.Monteiro, C. M. B.Santos, F. P.Santos, J. M. F. dosNEXT Collaborationinfo: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:RCAAP2023-01-30T12:49:07Zoai:estudogeral.uc.pt:10316/105043Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:21:38.336686Repositório 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 |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment |
title |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment |
spellingShingle |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment Borges, F. I. G. M. Dark Matter and Double Beta Decay (experiments) |
title_short |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment |
title_full |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment |
title_fullStr |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment |
title_full_unstemmed |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment |
title_sort |
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment |
author |
Borges, F. I. G. M. |
author_facet |
Borges, F. I. G. M. Conde, C. A. N. Fernandes, A. F. M. Fernandes, L. M. P. Freitas, E. D. C. Henriques, C. A. O. Escada, J. Mano, R.D.P. Monteiro, C. M. B. Santos, F. P. Santos, J. M. F. dos NEXT Collaboration |
author_role |
author |
author2 |
Conde, C. A. N. Fernandes, A. F. M. Fernandes, L. M. P. Freitas, E. D. C. Henriques, C. A. O. Escada, J. Mano, R.D.P. Monteiro, C. M. B. Santos, F. P. Santos, J. M. F. dos NEXT Collaboration |
author2_role |
author author author author author author author author author author author |
dc.contributor.author.fl_str_mv |
Borges, F. I. G. M. Conde, C. A. N. Fernandes, A. F. M. Fernandes, L. M. P. Freitas, E. D. C. Henriques, C. A. O. Escada, J. Mano, R.D.P. Monteiro, C. M. B. Santos, F. P. Santos, J. M. F. dos NEXT Collaboration |
dc.subject.por.fl_str_mv |
Dark Matter and Double Beta Decay (experiments) |
topic |
Dark Matter and Double Beta Decay (experiments) |
description |
Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in 136Xe. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6MeV gamma rays from a 228Th calibration source. We train a network on Monte Carlosimulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offers significant improvement in signal efficiency and background rejection when compared to previous non-CNN-based analyses. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01 |
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/10316/105043 http://hdl.handle.net/10316/105043 https://doi.org/10.1007/JHEP01(2021)189 |
url |
http://hdl.handle.net/10316/105043 https://doi.org/10.1007/JHEP01(2021)189 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Springer Nature |
publisher.none.fl_str_mv |
Springer Nature |
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_ |
1799134106714374144 |