Neutral pion reconstruction using machine learning in the MINERvA experiment at $⟨E_{\nu }⟩\sim 6$ GeV

Abstract

This paper presents a novel neutral-pion reconstruction that takes advantage of the machine learning technique of semantic segmentation using MINERvA data collected between 2013-2017, with an average neutrino energy of $6$ GeV. Semantic segmentation improves the purity of neutral pion reconstruction from two gammas from 71\% to 89\% and improves the efficiency of the reconstruction by approximately 40\%. We demonstrate our method in a charged current neutral pion production analysis where a single neutral pion is reconstructed. This technique is applicable to modern tracking calorimeters, such as the new generation of liquid-argon time projection chambers, exposed to neutrino beams with $⟨E_{\nu }⟩$ between 1-10 GeV. In such experiments it can facilitate the identification of ionization hits which are associated with electromagnetic showers, thereby enabling improved reconstruction of charged-current ${\nu }_e$ events arising from ${\nu }_{\mu }\to {\nu }_e$ appearance.

arXiv comment26 pages, v2 matches published version

References in corpus (32)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The GENIE Neutrino Monte Carlo Generator
• Deep Learning and its Application to LHC Physics
• The magnetized steel and scintillator calorimeters of the MINOS experiment
• The NuMI Neutrino Beam
• A Convolutional Neural Network Neutrino Event Classifier
• Design, Calibration, and Performance of the MINERvA Detector
• Measurement of Muon Antineutrino Quasi-Elastic Scattering on a Hydrocarbon Target at E_ν ~ 3.5 GeV
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• Higher Twist, ${\xi }_w$ Scaling, and Effective $LOPDFs$ for Lepton Scattering in the Few GeV Region
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Charged Pion Production in ${\nu }_{\mu }$ Interactions on Hydrocarbon at $⟨E_{\nu }⟩$= 4.0 GeV
• Measurement of Neutrino Flux from Neutrino-Electron Elastic Scattering
• Constraint of the MINERvA Medium Energy Neutrino Flux using Neutrino-Electron Elastic Scattering
• Measurement of Quasielastic-Like Neutrino Scattering at $⟨E_{\nu }⟩\sim 3.5$~ GeV on a Hydrocarbon Target
• Measurement of Ratios of ${\nu }_{\mu }$ Charged-Current Cross Sections on C, Fe, and Pb to CH at Neutrino Energies 2-20 GeV
• Single neutral pion production by charged-current ${\bar{\nu }}_{\mu }$ interactions on hydrocarbon at $⟨E_{\nu }⟩=$ 3.6 GeV
• Tuning the GENIE Pion Production Model with MINERvA Data
• Measurement of ${\nu }_{\mu }$ charged-current single ${\pi }^0$ production on hydrocarbon in the few-GeV region using MINERvA
• Measurement of electron neutrino quasielastic and quasielastic-like scattering on hydrocarbon at $⟨E_{\nu }⟩$ = 3.6 GeV
• Reconstruction and Measurement of $\mathcal{O}$(100) MeV Energy Electromagnetic Activity from ${\pi }^0\to \gamma \gamma$ Decays in the MicroBooNE LArTPC
• High-statistics measurement of neutrino quasielastic-like scattering at <E_nu>=~6 GeV on a hydrocarbon target
• Probing nuclear effects with neutrino-induced charged-current neutral pion production
• Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events
• Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment
• A Review on Machine Learning for Neutrino Experiments
• The MINER$\nu$A Data Acquisition System and Infrastructure
• Evidence for neutral-current diffractive neutral pion production from hydrogen in neutrino interactions on hydrocarbon
• Measurement of single ${\pi }^0$ production by coherent neutral-current $\nu$ Fe interactions in the MINOS Near Detector
• Measurement of Neutrino-Induced Neutral-Current Coherent ${\pi }^0$ Production in the NOvA Near Detector
• Arachne - A web-based event viewer for MINERvA