Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors

Abstract

Deep learning tools are being used extensively in high energy physics and are becoming central in the reconstruction of neutrino interactions in particle detectors. In this work, we report on the performance of a graph neural network in assisting with particle flow event reconstruction. The three-dimensional reconstruction of particle tracks produced in neutrino interactions can be subject to ambiguities due to high multiplicity signatures in the detector or leakage of signal between neighboring active detector volumes. Graph neural networks potentially have the capability of identifying all these features to boost the reconstruction performance. As an example case study, we tested a graph neural network, inspired by the GraphSAGE algorithm, on a novel 3D-granular plastic-scintillator detector, that will be used to upgrade the near detector of the T2K experiment. The developed neural network has been trained and tested on diverse neutrino interaction samples, showing very promising results: the classification of particle track voxels produced in the detector can be done with efficiencies and purities of 94-96% per event and most of the ambiguities can be identified and rejected, while being robust against systematic effects.

References in corpus (30)

• Semi-Supervised Classification with Graph Convolutional Networks
• Evidence for oscillation of atmospheric neutrinos
• Deep Residual Learning for Image Recognition
• Observation of electron-antineutrino disappearance at Daya Bay
• Graph Neural Networks: A Review of Methods and Applications
• Measurement of Neutrino Oscillation with KamLAND: Evidence of Spectral Distortion
• The GENIE Neutrino Monte Carlo Generator
• Measurement of Neutrino Oscillation by the K2K Experiment
• Electron Energy Spectra, Fluxes, and Day-Night Asymmetries of ${}^8$B Solar Neutrinos from the 391-Day Salt Phase SNO Data Set
• Constraint on the Matter-Antimatter Symmetry-Violating Phase in Neutrino Oscillations
• Submanifold Sparse Convolutional Networks
• First measurement of neutrino oscillation parameters using neutrinos and antineutrinos by NOvA
• A Convolutional Neural Network Neutrino Event Classifier
• The T2K Neutrino Flux Prediction
• Combined analysis of ${\nu }_{\mu }$ disappearance and ${\nu }_{\mu }\to {\nu }_e$ appearance in MINOS using accelerator and atmospheric neutrinos
• New constraints on oscillation parameters from ${\nu }_e$ appearance and ${\nu }_{\mu }$ disappearance in the NOvA experiment
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• T2K ND280 Upgrade -- Technical Design Report
• Deep Underground Neutrino Experiment (DUNE), Far Detector Technical Design Report, Volume II: DUNE Physics
• A fully active fine grained detector with three readout views
• The SuperFGD Prototype Charged Particle Beam Tests
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• Beam test results of 3D fine-grained scintillator detector prototype for a T2K ND280 neutrino active target
• Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks
• Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
• Sensitivity of a tonne-scale NEXT detector for neutrinoless double beta decay searches
• Simulation of charge readout with segmented tiles in nEXO

Cited by in corpus (4)

• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Neural Network predictions of inclusive electron-nucleus cross sections
• Artificial intelligence for improved fitting of trajectories of elementary particles in inhomogeneous dense materials immersed in a magnetic field
• A novel range telescope concept for proton CT