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

K. Gumpula, N. Koloskov, D. Grzenda, V. Hewes, A. Aurisano, G. Cerati, A. Day, J. Kowalkowski, C. Lee, K. Wang, W. Liao, M. Spiropulu, A. Agrawal, J. Vlimant, L. Gray, T. Klijnsma, P. Calafiura, S. Conlon, S. Farrell, X. JuD. Murnane

Research output: Contribution to journalConference articlepeer-review

Abstract

The Exa.TrkX project 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 Large Hadron Collider (LHC). Graphs describing particle interactions are formed by treating each detector hit as a node, with edges describing the relationships between hits. We utilise a multi-head attention message passing network which performs graph convolutions in order to label each node with a particle type. We present an updated variant of our GNN architecture, with several improvements. After testing the model on more realistic simulation with regions of unresponsive wires, the target was modified from edge classification to node classification in order to increase robustness. Removing edges as a classification target opens up a broader possibility space for edge-forming techniques; we explore the model's performance across a variety of approaches, such as Delaunay triangulation, kNN, and radius-based methods. We also extend this model to the 3D context, sharing information between detector views. By using reconstructed 3D spacepoints to map detector hits from each wire plane, the model naively constructs 2D representations that are independent yet fully consistent.

Original languageEnglish (US)
Article number012091
JournalJournal of Physics: Conference Series
Volume2438
Issue number1
DOIs
StatePublished - 2023
Event20th International Workshop on Advanced Computing and Analysis Techniques in Physics Research, ACAT 2021 - Daejeon, Virtual, Korea, Republic of
Duration: Nov 29 2021Dec 3 2021

ASJC Scopus subject areas

  • General Physics and Astronomy

Fingerprint

Dive into the research topics of 'Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers'. Together they form a unique fingerprint.

Cite this