Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers. Issue 1 (1st February 2023)

• Record Type: Journal Article
• Authors: Gumpula, K; Koloskov, N; Grzenda, D; Hewes, V; Aurisano, A; Cerati, G; Day, A; Kowalkowski, J; Lee, C; Wang, K; Liao, W; Spiropulu, M; Agrawal, A; Vlimant, J; Gray, L; Klijnsma, T; Calafiura, P; Conlon, S; Farrell, S; Ju, X; Murnane, D
• Is Part Of: Journal of physics. Volume 2438:Issue 1(2023)
• Publication Date: 2023-02-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2438/1/012091
• Languages: English
• ISSNs: 1742-6588

Abstract

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.