CaltechAUTHORS
  A Caltech Library Service

Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers

Hewes, Jeremy and Aurisano, Adam and Cerati, Giuseppe and Kowalkowski, Jim and Lee, Claire and Liao, Wei-keng and Day, Alexandra and Agrawal, Ankit and Spiropulu, Maria and Vlimant, Jean-Roch and Gray, Lindsey and Klijnsma, Thomas and Calafiura, Paolo and Conlon, Sean and Farrell, Steve and Ju, Xiangyang and Murnane, Daniel (2021) Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers. EPJ Web of Conferences, 251 . Art. No. 03054. ISSN 2100-014X. doi:10.1051/epjconf/202125103054. https://resolver.caltech.edu/CaltechAUTHORS:20211006-190143297

[img] PDF - Published Version
Creative Commons Attribution.

888kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20211006-190143297

Abstract

This paper presents a graph neural network (GNN) technique for low-level reconstruction of neutrino interactions in a Liquid Argon Time Projection Chamber (LArTPC). GNNs are still a relatively novel technique, and have shown great promise for similar reconstruction tasks in the LHC. In this paper, a multihead attention message passing network is used to classify the relationship between detector hits by labelling graph edges, determining whether hits were produced by the same underlying particle, and if so, the particle type. The trained model is 84% accurate overall, and performs best on the EM shower and muon track classes. The model’s strengths and weaknesses are discussed, and plans for developing this technique further are summarised.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1051/epjconf/202125103054DOIArticle
ORCID:
AuthorORCID
Spiropulu, Maria0000-0001-8172-7081
Vlimant, Jean-Roch0000-0002-9705-101X
Additional Information:© The Authors, published by EDP Sciences, 2021. This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This research was supported in part by the Office of Science, Office of High Energy Physics, of the US Department of Energy under Contracts No. DE-AC02-05CH11231 (CompHEP Exa.TrkX) and No. DE-AC02-07CH11359 (FNAL LDRD 2019.017). This research used resources of the National Energy Research Scientific Computing Center (NERSC), a U.S. Department of Energy Office of Science User Facility located at Lawrence Berkeley National Laboratory, operated under Contract No. DE-AC02-05CH11231.
Funders:
Funding AgencyGrant Number
Department of Energy (DOE)DE-AC02-05CH11231
Department of Energy (DOE)DE-AC02-07CH11359
DOI:10.1051/epjconf/202125103054
Record Number:CaltechAUTHORS:20211006-190143297
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20211006-190143297
Official Citation:Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers. Jeremy Hewes, Adam Aurisano, Giuseppe Cerati, Jim Kowalkowski, Claire Lee, Wei-keng Liao, Alexandra Day, Ankit Agrawal, Maria Spiropulu, Jean-Roch Vlimant, Lindsey Gray, Thomas Klijnsma, Paolo Calafiura, Sean Conlon, Steve Farrell, Xiangyang Ju and Daniel Murnane. EPJ Web Conf., 251 (2021) 03054; DOI: https://doi.org/10.1051/epjconf/202125103054
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:111248
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:06 Oct 2021 19:10
Last Modified:06 Oct 2021 19:10

Repository Staff Only: item control page