2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore

The IceCube Collaboration

2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore

The IceCube Collaboration

Chair of Experimental Physics with Cosmic Particles

Loyola University Chicago
Deutsches Elektronen-Synchrotron (DESY)
University of Canterbury
University of Wisconsin-Madison
Institute of Physics Bhubaneswar
Université Libre de Bruxelles
Niels Bohr Institutet
pro3dure medical GmbH
University of Delaware
Marquette University
Friedrich-Alexander Universitat Erlangen-Nurnberg (FAU)
The Broad Institute of MIT and Harvard
University of Utah
South Dakota School of Mines and Technology
University of California, Irvine
University of California at Berkeley
Ohio State University
Max-Planck-lnstitut für Kohlenforschung
Chalmers University of Technology
Uppsala University
Technical University of Munich
RWTH Aachen University
University of Rochester
University of Maryland
University of Padova
University of Kansas
Humanoid Technologies Lab (H2T)
Johannes Gutenberg University
Georgia Institute of Technology
University of Adelaide
University of Münster
Drexel University
SUNY
Sungkyunkwan University
Massachusetts Institute of Technology
VUB Neurology
The Pennsylvania State University
Eberly College of Science
University of Alabama
Oskar Klein Centre
Centre Hospitalier Universitaire (CHU) Mont-Godinne
Michigan State University
Bergische Universität Wuppertal
Chiba-U
Southern University and A&M College
Academia Sinica Taipei
Humboldt-Universität zu Berlin
Lawrence Berkeley National Laboratory
Queen's University
University of Tokyo
Clark-Atlanta University
University of Texas at Arlington
University of Nevada, Las Vegas
University of Alberta
University of Geneva
Columbia University
Yale University
Mercer University at Macon
Ghent University
University of Alaska Anchorage
University of Oxford
University of Wisconsin-River Falls

Research output: Contribution to journal › Conference article › peer-review

Abstract

IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions for the purpose of neutrino oscillation studies. Distinguishing muon neutrinos from other flavors and reconstructing inelasticity are especially difficult tasks at GeV scale energies in IceCube DeepCore due to sparse instrumentation. Convolutional neural networks (CNNs) have been found to have better success at neutrino event reconstruction than conventional likelihood-based methods. In this contribution, we present a new CNN model that exploits time and depth translational symmetry in IceCube DeepCore data and present the model’s performance, specifically for flavor identification and inelasticity reconstruction.

Original language	English
Article number	1129
Journal	Proceedings of Science
Volume	444
State	Published - 27 Sep 2024
Event	38th International Cosmic Ray Conference, ICRC 2023 - Nagoya, Japan Duration: 26 Jul 2023 → 3 Aug 2023

Cite this

@article{0d90b4da642042f29623aa674f6c050b,

title = "2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore",

abstract = "IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions for the purpose of neutrino oscillation studies. Distinguishing muon neutrinos from other flavors and reconstructing inelasticity are especially difficult tasks at GeV scale energies in IceCube DeepCore due to sparse instrumentation. Convolutional neural networks (CNNs) have been found to have better success at neutrino event reconstruction than conventional likelihood-based methods. In this contribution, we present a new CNN model that exploits time and depth translational symmetry in IceCube DeepCore data and present the model{\textquoteright}s performance, specifically for flavor identification and inelasticity reconstruction.",

author = "\{The IceCube Collaboration\} and R. Abbasi and M. Ackermann and J. Adams and Agarwalla, \{S. K.\} and Aguilar, \{J. A.\} and M. Ahlers and Alameddine, \{J. M.\} and Amin, \{N. M.\} and K. Andeen and G. Anton and C. Arg{\"u}elles and Y. Ashida and S. Athanasiadou and Axani, \{S. N.\} and X. Bai and Balagopal, \{A. V.\} and M. Baricevic and Barwick, \{S. W.\} and V. Basu and R. Bay and Beatty, \{J. J.\} and \{Becker Tjus\}, J. and J. Beise and C. Bellenghi and C. Benning and S. BenZvi and D. Berley and E. Bernardini and Besson, \{D. Z.\} and E. Blaufuss and S. Blot and F. Bontempo and Book, \{J. Y.\} and \{Boscolo Meneguolo\}, C. and S. B{\"o}ser and O. Botner and J. B{\"o}ttcher and E. Bourbeau and J. Braun and B. Brinson and J. Brostean-Kaiser and Burley, \{R. T.\} and Busse, \{R. S.\} and D. Butterfield and Campana, \{M. A.\} and K. Carloni and Carnie-Bronca, \{E. G.\} and S. Chattopadhyay and N. Chau and E. Resconi",

note = "Publisher Copyright: {\textcopyright} Copyright owned by the author(s) under the terms of the Creative Commons.; 38th International Cosmic Ray Conference, ICRC 2023 ; Conference date: 26-07-2023 Through 03-08-2023",

year = "2024",

month = sep,

day = "27",

language = "English",

volume = "444",

journal = "Proceedings of Science",

issn = "1824-8039",

publisher = "Sissa Medialab Srl",

}

TY - JOUR

T1 - 2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore

AU - The IceCube Collaboration

AU - Abbasi, R.

AU - Ackermann, M.

AU - Adams, J.

AU - Agarwalla, S. K.

AU - Aguilar, J. A.

AU - Ahlers, M.

AU - Alameddine, J. M.

AU - Amin, N. M.

AU - Andeen, K.

AU - Anton, G.

AU - Argüelles, C.

AU - Ashida, Y.

AU - Athanasiadou, S.

AU - Axani, S. N.

AU - Bai, X.

AU - Balagopal, A. V.

AU - Baricevic, M.

AU - Barwick, S. W.

AU - Basu, V.

AU - Bay, R.

AU - Beatty, J. J.

AU - Becker Tjus, J.

AU - Beise, J.

AU - Bellenghi, C.

AU - Benning, C.

AU - BenZvi, S.

AU - Berley, D.

AU - Bernardini, E.

AU - Besson, D. Z.

AU - Blaufuss, E.

AU - Blot, S.

AU - Bontempo, F.

AU - Book, J. Y.

AU - Boscolo Meneguolo, C.

AU - Böser, S.

AU - Botner, O.

AU - Böttcher, J.

AU - Bourbeau, E.

AU - Braun, J.

AU - Brinson, B.

AU - Brostean-Kaiser, J.

AU - Burley, R. T.

AU - Busse, R. S.

AU - Butterfield, D.

AU - Campana, M. A.

AU - Carloni, K.

AU - Carnie-Bronca, E. G.

AU - Chattopadhyay, S.

AU - Chau, N.

AU - Resconi, E.

PY - 2024/9/27

Y1 - 2024/9/27

N2 - IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions for the purpose of neutrino oscillation studies. Distinguishing muon neutrinos from other flavors and reconstructing inelasticity are especially difficult tasks at GeV scale energies in IceCube DeepCore due to sparse instrumentation. Convolutional neural networks (CNNs) have been found to have better success at neutrino event reconstruction than conventional likelihood-based methods. In this contribution, we present a new CNN model that exploits time and depth translational symmetry in IceCube DeepCore data and present the model’s performance, specifically for flavor identification and inelasticity reconstruction.

AB - IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions for the purpose of neutrino oscillation studies. Distinguishing muon neutrinos from other flavors and reconstructing inelasticity are especially difficult tasks at GeV scale energies in IceCube DeepCore due to sparse instrumentation. Convolutional neural networks (CNNs) have been found to have better success at neutrino event reconstruction than conventional likelihood-based methods. In this contribution, we present a new CNN model that exploits time and depth translational symmetry in IceCube DeepCore data and present the model’s performance, specifically for flavor identification and inelasticity reconstruction.

UR - https://www.scopus.com/pages/publications/85212251475

M3 - Conference article

AN - SCOPUS:85212251475

SN - 1824-8039

VL - 444

JO - Proceedings of Science

JF - Proceedings of Science

M1 - 1129

T2 - 38th International Cosmic Ray Conference, ICRC 2023

Y2 - 26 July 2023 through 3 August 2023

ER -

2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore

Abstract

Other files and links

Fingerprint

Cite this