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

Saúl Alonso-Monsalve,Federico Sánchez,Davide Sgalaberna,Sebastian Pina-Otey,Dana Douqa,Leigh H Whitehead,Thorsten Lux,César Jesús-Valls

doi:10.1103/physrevd.103.032005

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.

Highlights

Since 1999, a series of neutrino oscillation experiments have provided deep insight into the nature of neutrinos [1,2,3,4,5,6,7,8]
We report on the performance of a graph neural network in assisting with particle set event reconstruction
To the best of our knowledge, the approach we present in this paper is one of the first attempts of using graph neural networks (GNNs) for node classification in neutrino experiments

Summary

Introduction

Since 1999, a series of neutrino oscillation experiments have provided deep insight into the nature of neutrinos [1,2,3,4,5,6,7,8]. A number of these experiments are long-baseline neutrino oscillation experiments that use two detectors to characterize a beam of (anti)neutrinos: a near detector, located a few hundred meters away from the target that measures the original beam composition, and a far detector, located several hundred kilometres away, that allows for the determination of the beam composition after neutrino flavor oscillations. Charged particles can be produced in neutrino interactions, and the energy that they

Objectives

Methods

Findings

Conclusion