Graph Neural Network for Neutrino Physics Event Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hewes, V, Aurisano, Adam, Cerati, Giuseppe, Kowalkowski, Jim, Lee, Claire, Liao, Wei-keng, Grzenda, Daniel, Gumpula, Kaushal, Zhang, Xiaohe
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915359710248960
author Hewes, V
Aurisano, Adam
Cerati, Giuseppe
Kowalkowski, Jim
Lee, Claire
Liao, Wei-keng
Grzenda, Daniel
Gumpula, Kaushal
Zhang, Xiaohe
author_facet Hewes, V
Aurisano, Adam
Cerati, Giuseppe
Kowalkowski, Jim
Lee, Claire
Liao, Wei-keng
Grzenda, Daniel
Gumpula, Kaushal
Zhang, Xiaohe
contents Liquid Argon Time Projection Chamber (LArTPC) detector technology offers a wealth of high-resolution information on particle interactions, and leveraging that information to its full potential requires sophisticated automated reconstruction techniques. This article describes NuGraph2, a Graph Neural Network (GNN) for low-level reconstruction of simulated neutrino interactions in a LArTPC detector. Simulated neutrino interactions in the MicroBooNE detector geometry are described as heterogeneous graphs, with energy depositions on each detector plane forming nodes on planar subgraphs. The network utilizes a multi-head attention message-passing mechanism to perform background filtering and semantic labelling on these graph nodes, identifying those associated with the primary physics interaction with 98.0\% efficiency and labelling them according to particle type with 94.9\% efficiency. The network operates directly on detector observables across multiple 2D representations, but utilizes a 3D-context-aware mechanism to encourage consistency between these representations. Model inference takes 0.12~s/event on a CPU, and 0.005s/event batched on a GPU. This architecture is designed to be a general-purpose solution for particle reconstruction in neutrino physics, with the potential for deployment across a broad range of detector technologies, and offers a core convolution engine that can be leveraged for a variety of tasks beyond the two described in this article.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11872
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Neural Network for Neutrino Physics Event Reconstruction
Hewes, V
Aurisano, Adam
Cerati, Giuseppe
Kowalkowski, Jim
Lee, Claire
Liao, Wei-keng
Grzenda, Daniel
Gumpula, Kaushal
Zhang, Xiaohe
Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Experiment
Liquid Argon Time Projection Chamber (LArTPC) detector technology offers a wealth of high-resolution information on particle interactions, and leveraging that information to its full potential requires sophisticated automated reconstruction techniques. This article describes NuGraph2, a Graph Neural Network (GNN) for low-level reconstruction of simulated neutrino interactions in a LArTPC detector. Simulated neutrino interactions in the MicroBooNE detector geometry are described as heterogeneous graphs, with energy depositions on each detector plane forming nodes on planar subgraphs. The network utilizes a multi-head attention message-passing mechanism to perform background filtering and semantic labelling on these graph nodes, identifying those associated with the primary physics interaction with 98.0\% efficiency and labelling them according to particle type with 94.9\% efficiency. The network operates directly on detector observables across multiple 2D representations, but utilizes a 3D-context-aware mechanism to encourage consistency between these representations. Model inference takes 0.12~s/event on a CPU, and 0.005s/event batched on a GPU. This architecture is designed to be a general-purpose solution for particle reconstruction in neutrino physics, with the potential for deployment across a broad range of detector technologies, and offers a core convolution engine that can be leveraged for a variety of tasks beyond the two described in this article.
title Graph Neural Network for Neutrino Physics Event Reconstruction
topic Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2403.11872