View in EDS HTML Full Text PDF Full Text

Neutrino interaction vertex reconstruction in DUNE with Pandora deep learning.

Saved in:
Bibliographic Details
Title: Neutrino interaction vertex reconstruction in DUNE with Pandora deep learning.
Authors: Abud, A. Abed1 (AUTHOR), Acciarri, R.2 (AUTHOR), Acero, M. A.3 (AUTHOR), Adames, M. R.4 (AUTHOR), Adamov, G.5 (AUTHOR), Adamowski, M.2 (AUTHOR), Adams, D.6 (AUTHOR), Adinolfi, M.7 (AUTHOR), Adriano, C.8 (AUTHOR), Aduszkiewicz, A.9 (AUTHOR), Aguilar, J.10 (AUTHOR), Akbar, F.11 (AUTHOR), Alemanno, F.12 (AUTHOR), Alex, N. S.11 (AUTHOR), Allison, K.13 (AUTHOR), Alrashed, M.14 (AUTHOR), Alton, A.15 (AUTHOR), Alvarez, R.16 (AUTHOR), Alves, T.17 (AUTHOR), Aman, A.18 (AUTHOR)
Source: European Physical Journal C -- Particles & Fields. Jun2025, Vol. 85 Issue 6, p1-24. 24p.
Subjects: Neutrino interactions, Software development tools, Liquid argon, Artificial intelligence, Machine learning
Abstract: The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20% increase in the efficiency of sub-1 cm vertex reconstruction across all neutrino flavours. [ABSTRACT FROM AUTHOR]
Copyright of European Physical Journal C -- Particles & Fields is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 186711225
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Neutrino interaction vertex reconstruction in DUNE with Pandora deep learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Abud%2C+A%2E+Abed%22">Abud, A. Abed</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Acciarri%2C+R%2E%22">Acciarri, R.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Acero%2C+M%2E+A%2E%22">Acero, M. A.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Adames%2C+M%2E+R%2E%22">Adames, M. R.</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Adamov%2C+G%2E%22">Adamov, G.</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Adamowski%2C+M%2E%22">Adamowski, M.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Adams%2C+D%2E%22">Adams, D.</searchLink><relatesTo>6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Adinolfi%2C+M%2E%22">Adinolfi, M.</searchLink><relatesTo>7</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Adriano%2C+C%2E%22">Adriano, C.</searchLink><relatesTo>8</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Aduszkiewicz%2C+A%2E%22">Aduszkiewicz, A.</searchLink><relatesTo>9</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Aguilar%2C+J%2E%22">Aguilar, J.</searchLink><relatesTo>10</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Akbar%2C+F%2E%22">Akbar, F.</searchLink><relatesTo>11</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Alemanno%2C+F%2E%22">Alemanno, F.</searchLink><relatesTo>12</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Alex%2C+N%2E+S%2E%22">Alex, N. S.</searchLink><relatesTo>11</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Allison%2C+K%2E%22">Allison, K.</searchLink><relatesTo>13</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Alrashed%2C+M%2E%22">Alrashed, M.</searchLink><relatesTo>14</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Alton%2C+A%2E%22">Alton, A.</searchLink><relatesTo>15</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Alvarez%2C+R%2E%22">Alvarez, R.</searchLink><relatesTo>16</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Alves%2C+T%2E%22">Alves, T.</searchLink><relatesTo>17</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Aman%2C+A%2E%22">Aman, A.</searchLink><relatesTo>18</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22European+Physical+Journal+C+--+Particles+%26+Fields%22">European Physical Journal C -- Particles & Fields</searchLink>. Jun2025, Vol. 85 Issue 6, p1-24. 24p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Neutrino+interactions%22">Neutrino interactions</searchLink><br /><searchLink fieldCode="DE" term="%22Software+development+tools%22">Software development tools</searchLink><br /><searchLink fieldCode="DE" term="%22Liquid+argon%22">Liquid argon</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20% increase in the efficiency of sub-1 cm vertex reconstruction across all neutrino flavours. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of European Physical Journal C -- Particles & Fields is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=186711225
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1140/epjc/s10052-025-14313-8
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 1
    Subjects:
      – SubjectFull: Neutrino interactions
        Type: general
      – SubjectFull: Software development tools
        Type: general
      – SubjectFull: Liquid argon
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Machine learning
        Type: general
    Titles:
      – TitleFull: Neutrino interaction vertex reconstruction in DUNE with Pandora deep learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Abud, A. Abed
      – PersonEntity:
          Name:
            NameFull: Acciarri, R.
      – PersonEntity:
          Name:
            NameFull: Acero, M. A.
      – PersonEntity:
          Name:
            NameFull: Adames, M. R.
      – PersonEntity:
          Name:
            NameFull: Adamov, G.
      – PersonEntity:
          Name:
            NameFull: Adamowski, M.
      – PersonEntity:
          Name:
            NameFull: Adams, D.
      – PersonEntity:
          Name:
            NameFull: Adinolfi, M.
      – PersonEntity:
          Name:
            NameFull: Adriano, C.
      – PersonEntity:
          Name:
            NameFull: Aduszkiewicz, A.
      – PersonEntity:
          Name:
            NameFull: Aguilar, J.
      – PersonEntity:
          Name:
            NameFull: Akbar, F.
      – PersonEntity:
          Name:
            NameFull: Alemanno, F.
      – PersonEntity:
          Name:
            NameFull: Alex, N. S.
      – PersonEntity:
          Name:
            NameFull: Allison, K.
      – PersonEntity:
          Name:
            NameFull: Alrashed, M.
      – PersonEntity:
          Name:
            NameFull: Alton, A.
      – PersonEntity:
          Name:
            NameFull: Alvarez, R.
      – PersonEntity:
          Name:
            NameFull: Alves, T.
      – PersonEntity:
          Name:
            NameFull: Aman, A.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 14346044
          Numbering:
            – Type: volume
              Value: 85
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: European Physical Journal C -- Particles & Fields
              Type: main
ResultId 1