A Convolutional Neural Network Neutrino Event Classifier

Abstract

Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

23 pages, 12 figures

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Big-Bang Nucleosynthesis
• Going Deeper with Convolutions

Cited by in corpus (112)

• A Survey of the Recent Architectures of Deep Convolutional Neural Networks
• Machine learning and the physical sciences
• A trans-disciplinary review of deep learning research for water resources scientists
• A high-bias, low-variance introduction to Machine Learning for physicists
• Deep Learning and its Application to LHC Physics
• Quantum convolutional neural network for classical data classification
• First measurement of neutrino oscillation parameters using neutrinos and antineutrinos by NOvA
• An Improved Measurement of Neutrino Oscillation Parameters by the NOvA Experiment
• New constraints on oscillation parameters from ${\nu }_e$ appearance and ${\nu }_{\mu }$ disappearance in the NOvA experiment
• Constraints on Oscillation Parameters from ${\nu }_e$ Appearance and ${\nu }_{\mu }$ Disappearance in NOvA
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Dark Matter Annihilation to Neutrinos
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Application of Deep Learning methods to analysis of Imaging Atmospheric Cherenkov Telescopes data
• Optimizing Event Selection with the Random Grid Search
• White Paper on New Opportunities at the Next-Generation Neutrino Experiments (Part 1: BSM Neutrino Physics and Dark Matter)
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Search for active-sterile neutrino mixing using neutral-current interactions in NOvA
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• A New Method to Observe Gravitational Waves emitted by Core Collapse Supernovae
• Modern Machine Learning and Particle Physics
• Background rejection in NEXT using deep neural networks
• FPGA-accelerated machine learning inference as a service for particle physics computing
• A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory
• Extensive deep neural networks for transferring small scale learning to large scale systems
• Gaseous and dual-phase time projection chambers for imaging rare processes
• Mapping Machine-Learned Physics into a Human-Readable Space
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Semantic Segmentation with a Sparse Convolutional Neural Network for Event Reconstruction in MicroBooNE
• End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• Deep Neural Networks for Energy and Position Reconstruction in EXO-200
• Neutrino mass ordering obscured by non-standard interactions
• Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks
• A Convolutional Neural Network for Multiple Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Event reconstruction for KM3NeT/ORCA using convolutional neural networks
• Electromagnetic Showers Beyond Shower Shapes
• Machine Learning Methods for Track Classification in the AT-TPC
• Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
• Machine-learning enhanced dark soliton detection in Bose-Einstein condensates
• Stacking machine learning classifiers to identify Higgs bosons at the LHC
• GPU-accelerated machine learning inference as a service for computing in neutrino experiments
• Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events
• Background Rejection in Atmospheric Cherenkov Telescopes using Recurrent Convolutional Neural Networks
• Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
• Jet-Parton Assignment in ttH Events using Deep Learning
• Hybrid Quantum-Classical Graph Convolutional Network
• Joint neutrino oscillation analysis from the T2K and NOvA experiments
• 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
• Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks
• A deep learning method for the trajectory reconstruction of cosmic rays with the DAMPE mission
• Learning to Identify Electrons
• Particle Identification In Camera Image Sensors Using Computer Vision
• Classification and Recovery of Radio Signals from Cosmic Ray Induced Air Showers with Deep Learning
• Invisible Higgs search through Vector Boson Fusion: A deep learning approach
• Machine learning techniques in searches for $t\bar{t}h$ in the $h\to b\bar{b}$ decay channel
• Deep Learning Jet Image as a Probe of Light Higgsino Dark Matter at the LHC
• Simulation of charge readout with segmented tiles in nEXO
• Expanding neutrino oscillation parameter measurements in NOvA using a Bayesian approach
• First Steps Toward Incorporating Image Based Diagnostics Into Particle Accelerator Control Systems Using Convolutional Neural Networks
• Detector signal characterization with a Bayesian network in XENONnT
• Application of Graph Networks to background rejection in Imaging Air Cherenkov Telescopes
• 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
• Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors
• Measurement of ${\nu }_{\mu }$ Charged-Current Inclusive ${\pi }^0$ Production in the NOvA Near Detector
• Pileup mitigation at the Large Hadron Collider with Graph Neural Networks
• Reconstruction of decays to merged photons using end-to-end deep learning with domain continuation in the CMS detector
• Dual-Baseline Search for Active-to-Sterile Neutrino Oscillations in NOvA
• Simulating the Time Projection Chamber responses at the MPD detector using Generative Adversarial Networks
• Event Selection and Background Rejection in Time Projection Chambers Using Convolutional Neural Networks and a Specific Application to the AdEPT Gamma-ray Polarimeter Mission
• Machine learning technique to improve anti-neutrino detection efficiency for the ISMRAN experiment
• Neutrino Characterisation using Convolutional Neural Networks in CHIPS water Cherenkov detectors
• Pulse Shape Simulation and Discrimination using Machine-Learning Techniques
• Muon reconstruction with a convolutional neural network in the JUNO detector
• Deep Learning strategies for ProtoDUNE raw data denoising
• Domain-informed neural networks for interaction localization within astroparticle experiments
• A simulation study to distinguish prompt photon from ${\pi }^0$ and beam halo in a granular calorimeter using deep networks
• Graph Neural Network for Neutrino Physics Event Reconstruction
• Interpretable Boosted Decision Tree Analysis for the Majorana Demonstrator
• Reconstruction of the event vertex in the PandaX-III experiment with convolution neural network
• Artificial intelligence for improved fitting of trajectories of elementary particles in inhomogeneous dense materials immersed in a magnetic field
• Using graph neural networks to reconstruct charged pion showers in the CMS High Granularity Calorimeter
• Report from the A.I. For Nuclear Physics Workshop
• Utilizing synthetic training data for the supervised classification of rat ultrasonic vocalizations
• Interpretable machine learning approach for electron antineutrino selection in a large liquid scintillator detector
• Transforming a rare event search into a not-so-rare event search in real-time with deep learning-based object detection
• Adversarial methods to reduce simulation bias in neutrino interaction event filtering at Liquid Argon Time Projection Chambers
• Direction Reconstruction using a CNN for GeV-Scale Neutrinos in IceCube
• Segmentation of EM showers for neutrino experiments with deep graph neural networks
• Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
• Optimization of convolutional neural networks for background suppression in the PandaX-III experiment
• NOvA Recent Results with Neutrino+Antineutrino Data
• CHIPS Event Reconstruction and Design Optimisation
• Search for active-sterile antineutrino mixing using neutral-current interactions with the NOvA experiment
• Machine Learning Classification of Sphalerons and Black Holes at the LHC
• Using Machine Learning to Separate Cherenkov and Scintillation Light in Hybrid Neutrino Detector
• Contrastive Learning for Robust Representations of Neutrino Data
• End-to-end analysis using image classification
• Constraining nuclear effects in Argon using machine learning algorithms
• EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAM
• Deep learning based track reconstruction on CEPC luminometer
• Improving the time resolution of the MRPC detector using deep-learning algorithms
• Reflections on the Physics and Astronomy Student Reading Society (PhASRS) at San Jose State University
• Progress of the Charged Pion Semi-Inclusive Neutrino Charged Current Cross Section in NOvA
• Neutral pion reconstruction using machine learning in the MINERvA experiment at $⟨E_{\nu }⟩\sim 6$ GeV
• Improvement of the NOvA Near Detector Event Reconstruction and Primary Vertexing through the Application of Machine Learning Methods
• Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
• Application of CNN to a fine segmented scintillator detector for a single particle and neutrino-nucleon event