NuGraph2: A Graph Neural Network for Neutrino Physics Event Reconstruction

📅 2024-03-18
📈 Citations: 1
Influential: 0
📄 PDF

career value

216K/year
🤖 AI Summary
To address the challenges of background suppression and low-accuracy particle semantic labeling in neutrino event reconstruction for Liquid Argon Time Projection Chambers (LArTPCs), this paper proposes a heterogeneous graph-based multi-plane joint modeling approach. It represents multi-view 2D energy depositions as a heterogeneous graph and designs a multi-head attention-driven message-passing mechanism that fuses 2D observations with 3D geometric consistency constraints. A lightweight, transferable graph neural network architecture is developed, enabling cross-detector deployment and multi-task extensibility. Experiments demonstrate a primary interaction identification accuracy of 98.0% and a particle-type labeling accuracy of 94.9%. Inference time per event is merely 0.12 seconds on CPU and drops to 0.005 seconds/event under GPU batch processing. This work achieves, for the first time, end-to-end LArTPC event reconstruction with high accuracy, high efficiency, and strong generalizability.

Technology Category

Application Category

📝 Abstract
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 0.005 s/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.
Problem

Research questions and friction points this paper is trying to address.

Reconstructing neutrino interactions in LArTPC detectors
Filtering background noise in particle interaction data
Labeling particle types accurately in neutrino events
Innovation

Methods, ideas, or system contributions that make the work stand out.

Graph Neural Network for neutrino event reconstruction
Multi-head attention message-passing mechanism
3D-context-aware multi-representation consistency
🔎 Similar Papers
No similar papers found.
A
A. Aurisano
University of Cincinnati, Cincinnati, OH 45221, USA
V
V. Hewes
University of Cincinnati, Cincinnati, OH 45221, USA
G
G. Cerati
Fermi National Accelerator Laboratory, Batavia, IL 60510, USA
J
J. Kowalkowski
Fermi National Accelerator Laboratory, Batavia, IL 60510, USA
C
C. Lee
Northwestern University, Evanston, Il 60208, USA
W
W. Liao
Northwestern University, Evanston, Il 60208, USA
D
D. Grzenda
Data Science Institute, University of Chicago, Chicago, IL 60637, USA
K
K. Gumpula
Data Science Institute, University of Chicago, Chicago, IL 60637, USA
X
Xiaohe Zhang
Data Science Institute, University of Chicago, Chicago, IL 60637, USA and also at University of California, Los Angeles, Los Angeles, CA 90095, USA