2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peterson, J. H., Rodriguez, M. Prado, Hanson, K.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912860233269248
author Peterson, J. H.
Rodriguez, M. Prado
Hanson, K.
author_facet Peterson, J. H.
Rodriguez, M. Prado
Hanson, K.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2307_16373
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle 2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore
Peterson, J. H.
Rodriguez, M. Prado
Hanson, K.
High Energy Astrophysical Phenomena
Instrumentation and Methods for Astrophysics
High Energy Physics - Experiment
Machine Learning
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.
title 2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore
topic High Energy Astrophysical Phenomena
Instrumentation and Methods for Astrophysics
High Energy Physics - Experiment
Machine Learning
url https://arxiv.org/abs/2307.16373