Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks

Abstract

In neutrino experiments, neutrino energy reconstruction is crucial because neutrino oscillations and differential cross-sections are functions of neutrino energy. It is also challenging due to the complexity in the detector response and kinematics of final state particles. We propose a regression Convolutional Neural Network (CNN) based method to reconstruct electron neutrino energy and electron energy in the NOvA neutrino experiment. We demonstrate that with raw detector pixel inputs, a regression CNN can reconstruct event energy even with complicated final states involving lepton and hadrons. Compared with kinematics-based energy reconstruction, this method shows a significantly better energy resolution. The reconstructed to true energy ratio shows comparable or less dependence on true energy, hadronic energy fractions, and interaction modes. The regression CNN also shows smaller systematic uncertainties from the simulation of neutrino interactions. The proposed energy estimator provides improvements of $16\%$ and $12\%$ in RMS for ${\nu }_e$ CC and electron, respectively. This method can also be extended to solve other regression problems in HEP, taking over kinematics-based reconstruction tasks.

20 pages, 24 figures, accepted by Physical Review D

References in corpus (17)

• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• The GENIE Neutrino Monte Carlo Generator
• The NuMI Neutrino Beam
• First measurement of electron neutrino appearance in NOvA
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• A Convolutional Neural Network Neutrino Event Classifier
• New constraints on oscillation parameters from ${\nu }_e$ appearance and ${\nu }_{\mu }$ disappearance in the NOvA experiment
• Neutrino Flux Predictions for the NuMI Beam
• Constraints on Oscillation Parameters from ${\nu }_e$ Appearance and ${\nu }_{\mu }$ Disappearance in NOvA
• Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Background rejection in NEXT using deep neural networks
• Deep Neural Networks for Energy and Position Reconstruction in EXO-200
• Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment
• Revealing Fundamental Physics from the Daya Bay Neutrino Experiment using Deep Neural Networks
• First Results of ${\nu }_e$ Appearance Analysis and Electron Neutrino Identification at NOvA
• Electron Neutrino Energy Reconstruction in NOvA Using CNN Particle IDs

Cited by in corpus (16)

• Event reconstruction for KM3NeT/ORCA using convolutional neural networks
• Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• A flexible event reconstruction based on machine learning and likelihood principles
• Optimizing Observables with Machine Learning for Better Unfolding
• Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics
• Neural network--featured timing systems for radiation detectors: performance evaluation based on bound analysis
• Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Convolutional Neural Networks for Shower Energy Prediction in Liquid Argon Time Projection Chambers
• 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
• Domain-informed neural networks for interaction localization within astroparticle experiments
• Transforming a rare event search into a not-so-rare event search in real-time with deep learning-based object detection
• Improvement of the NOvA Near Detector Event Reconstruction and Primary Vertexing through the Application of Machine Learning Methods