Neutrino interaction classification with a convolutional neural network in the DUNE far detector

Abstract

The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on a convolutional neural network has been developed to provide highly efficient and pure selections of electron neutrino and muon neutrino charged-current interactions. The electron neutrino (antineutrino) selection efficiency peaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between 2-5 GeV. The muon neutrino (antineutrino) event selection is found to have a maximum efficiency of 96% (97%) and exceeds 90% (95%) efficiency for reconstructed neutrino energies above 2 GeV. When considering all electron neutrino and antineutrino interactions as signal, a selection purity of 90% is achieved. These event selections are critical to maximize the sensitivity of the experiment to $CP$-violating effects.

39 pages, 11 figures

References in corpus (3)

• Observation of electron-antineutrino disappearance at Daya Bay
• Measurement of Neutrino Oscillation by the K2K Experiment
• Enhancing Neutrino Event Reconstruction with Pixel-Based 3D Readout for Liquid Argon Time Projection Chambers

Cited by in corpus (22)

• Applications and Techniques for Fast Machine Learning in Science
• GPU-accelerated machine learning inference as a service for computing in neutrino experiments
• Hybrid Quantum-Classical Graph Convolutional Network
• Detector signal characterization with a Bayesian network in XENONnT
• Application of Transfer Learning to Neutrino Interaction Classification
• Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors
• Pulse shape discrimination using a convolutional neural network for organic liquid scintillator signals
• Separation of track- and shower-like energy deposits in ProtoDUNE-SP using a convolutional neural network
• A deep-learning based raw waveform region-of-interest finder for the liquid argon time projection chamber
• Neural Network predictions of inclusive electron-nucleus cross sections
• Deep-Learning-Based Kinematic Reconstruction for DUNE
• Neutrino Characterisation using Convolutional Neural Networks in CHIPS water Cherenkov detectors
• Pulse Shape Simulation and Discrimination using Machine-Learning Techniques
• Deep Learning strategies for ProtoDUNE raw data denoising
• Artificial intelligence for improved fitting of trajectories of elementary particles in inhomogeneous dense materials immersed in a magnetic field
• Graph Neural Network for Neutrino Physics Event Reconstruction
• Adversarial methods to reduce simulation bias in neutrino interaction event filtering at Liquid Argon Time Projection Chambers
• Constraining nuclear effects in Argon using machine learning algorithms
• Contrastive Learning for Robust Representations of Neutrino Data
• End-to-end analysis using image classification
• Using Machine Learning to Separate Cherenkov and Scintillation Light in Hybrid Neutrino Detector
• LArTPC hit-based topology classification with quantum machine learning and symmetry