Academic Journal

Classification of electron and muon neutrino events for the ESSνSB near water Cherenkov detector using Graph Neural Networks

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Classification of electron and muon neutrino events for the ESSνSB near water Cherenkov detector using Graph Neural Networks
Συγγραφείς: Aguilar, J., Zormpa, O., Bolling, B., Burgman, A., Carlile, C. J., Cederkall, J., Christiansen, P., Collins, M., Danared, H., Eshraqi, M., Iversen, K. E., Lindroos, M., Park, J., et al.
Συνεισφορές: Lund University, Faculty of Science, Department of Physics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Originator, Lund University, Faculty of Science, Department of Physics, Astrophysics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Astrofysik, Originator, Lund University, Faculty of Science, Department of Physics, Particle and nuclear physics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Partikel- och kärnfysik, Originator
Πηγή: Journal of Instrumentation. 20(8)
Θεματικοί όροι: Natural Sciences, Physical Sciences, Subatomic Physics, Naturvetenskap, Fysik, Subatomär fysik
Περιγραφή: In the effort to obtain a precise measurement of leptonic CP-violation with the ESSνSB experiment, accurate and fast reconstruction of detector events plays a pivotal role. In this work, we examine the possibility of replacing the currently proposed likelihood-based reconstruction method with an approach based on Graph Neural Networks (GNNs). As the likelihood-based reconstruction method is reasonably accurate but computationally expensive, one of the benefits of a Machine Learning (ML) based method is enabling fast event reconstruction in the detector development phase, allowing for easier investigation of the effects of changes to the detector design. Focusing on classification of flavour and interaction type in muon and electron events and muon- and electron neutrino interaction events, we demonstrate that the GNN reconstructs events with greater accuracy than the likelihood method for events with greater complexity, and with increased speed for all types of events. The GNN flavour classification of neutrino interaction events results in a true positive rate of 85.87 % (57.90 %) for muon (electron) neutrinos, compared to 35.55 % (0.21 %) for the likelihood-based method with identical constraints on the false positive rate, while the reconstruction speed is increased by a factor of 104. Additionally, we investigate the key factors impacting reconstruction performance, and demonstrate how separation of events by pion production using another GNN classifier can benefit flavour classification.
Σύνδεσμος πρόσβασης: https://doi.org/10.1088/1748-0221/20/08/P08030
Βάση Δεδομένων: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doi.org/10.1088/1748-0221/20/08/P08030#
    Name: EDS - SwePub (ns324271)
    Category: fullText
    Text: View record in SwePub
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.portal.research.lu.se.publications.9ec717e8.8857.4d56.b9ff.8a5390fc52f0
RelevancyScore: 1102
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1102.21545410156
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Classification of electron and muon neutrino events for the ESSνSB near water Cherenkov detector using Graph Neural Networks
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Aguilar%2C+J%2E%22">Aguilar, J.</searchLink><br /><searchLink fieldCode="AR" term="%22Zormpa%2C+O%2E%22">Zormpa, O.</searchLink><br /><searchLink fieldCode="AR" term="%22Bolling%2C+B%2E%22">Bolling, B.</searchLink><br /><searchLink fieldCode="AR" term="%22Burgman%2C+A%2E%22">Burgman, A.</searchLink><br /><searchLink fieldCode="AR" term="%22Carlile%2C+C%2E+J%2E%22">Carlile, C. J.</searchLink><br /><searchLink fieldCode="AR" term="%22Cederkall%2C+J%2E%22">Cederkall, J.</searchLink><br /><searchLink fieldCode="AR" term="%22Christiansen%2C+P%2E%22">Christiansen, P.</searchLink><br /><searchLink fieldCode="AR" term="%22Collins%2C+M%2E%22">Collins, M.</searchLink><br /><searchLink fieldCode="AR" term="%22Danared%2C+H%2E%22">Danared, H.</searchLink><br /><searchLink fieldCode="AR" term="%22Eshraqi%2C+M%2E%22">Eshraqi, M.</searchLink><br /><searchLink fieldCode="AR" term="%22Iversen%2C+K%2E+E%2E%22">Iversen, K. E.</searchLink><br /><searchLink fieldCode="AR" term="%22Lindroos%2C+M%2E%22">Lindroos, M.</searchLink><br /><searchLink fieldCode="AR" term="%22Park%2C+J%2E%22">Park, J.</searchLink><br /><searchLink fieldCode="AR" term="%22et+al%2E%22">et al.</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Lund University, Faculty of Science, Department of Physics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Originator<br />Lund University, Faculty of Science, Department of Physics, Astrophysics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Astrofysik, Originator<br />Lund University, Faculty of Science, Department of Physics, Particle and nuclear physics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Partikel- och kärnfysik, Originator
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Journal of Instrumentation</i>. 20(8)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Natural+Sciences%22">Natural Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Physical+Sciences%22">Physical Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Subatomic+Physics%22">Subatomic Physics</searchLink><br /><searchLink fieldCode="DE" term="%22Naturvetenskap%22">Naturvetenskap</searchLink><br /><searchLink fieldCode="DE" term="%22Fysik%22">Fysik</searchLink><br /><searchLink fieldCode="DE" term="%22Subatomär+fysik%22">Subatomär fysik</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: In the effort to obtain a precise measurement of leptonic CP-violation with the ESSνSB experiment, accurate and fast reconstruction of detector events plays a pivotal role. In this work, we examine the possibility of replacing the currently proposed likelihood-based reconstruction method with an approach based on Graph Neural Networks (GNNs). As the likelihood-based reconstruction method is reasonably accurate but computationally expensive, one of the benefits of a Machine Learning (ML) based method is enabling fast event reconstruction in the detector development phase, allowing for easier investigation of the effects of changes to the detector design. Focusing on classification of flavour and interaction type in muon and electron events and muon- and electron neutrino interaction events, we demonstrate that the GNN reconstructs events with greater accuracy than the likelihood method for events with greater complexity, and with increased speed for all types of events. The GNN flavour classification of neutrino interaction events results in a true positive rate of 85.87 % (57.90 %) for muon (electron) neutrinos, compared to 35.55 % (0.21 %) for the likelihood-based method with identical constraints on the false positive rate, while the reconstruction speed is increased by a factor of 104. Additionally, we investigate the key factors impacting reconstruction performance, and demonstrate how separation of events by pion production using another GNN classifier can benefit flavour classification.
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doi.org/10.1088/1748-0221/20/08/P08030" linkWindow="_blank">https://doi.org/10.1088/1748-0221/20/08/P08030</link>
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.portal.research.lu.se.publications.9ec717e8.8857.4d56.b9ff.8a5390fc52f0
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1088/1748-0221/20/08/P08030
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Natural Sciences
        Type: general
      – SubjectFull: Physical Sciences
        Type: general
      – SubjectFull: Subatomic Physics
        Type: general
      – SubjectFull: Naturvetenskap
        Type: general
      – SubjectFull: Fysik
        Type: general
      – SubjectFull: Subatomär fysik
        Type: general
    Titles:
      – TitleFull: Classification of electron and muon neutrino events for the ESSνSB near water Cherenkov detector using Graph Neural Networks
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Aguilar, J.
      – PersonEntity:
          Name:
            NameFull: Zormpa, O.
      – PersonEntity:
          Name:
            NameFull: Bolling, B.
      – PersonEntity:
          Name:
            NameFull: Burgman, A.
      – PersonEntity:
          Name:
            NameFull: Carlile, C. J.
      – PersonEntity:
          Name:
            NameFull: Cederkall, J.
      – PersonEntity:
          Name:
            NameFull: Christiansen, P.
      – PersonEntity:
          Name:
            NameFull: Collins, M.
      – PersonEntity:
          Name:
            NameFull: Danared, H.
      – PersonEntity:
          Name:
            NameFull: Eshraqi, M.
      – PersonEntity:
          Name:
            NameFull: Iversen, K. E.
      – PersonEntity:
          Name:
            NameFull: Lindroos, M.
      – PersonEntity:
          Name:
            NameFull: Park, J.
      – PersonEntity:
          Name:
            NameFull: et al.
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Science, Department of Physics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Originator
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Science, Department of Physics, Astrophysics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Astrofysik, Originator
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Science, Department of Physics, Particle and nuclear physics, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Partikel- och kärnfysik, Originator
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 17480221
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: LU_SWEPUB
          Numbering:
            – Type: volume
              Value: 20
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Journal of Instrumentation
              Type: main
ResultId 1