The Convolutional Visual Network for Identification and Reconstruction of NOvA Events

Psihas, Fernanda

doi:10.1088/1742-6596/898/7/072053

Title: The Convolutional Visual Network for Identification and Reconstruction of NOvA Events

Abstract

In 2016 the NOvA experiment released results for the observation of oscillations in the vμ and ve channels as well as ve cross section measurements using neutrinos from Fermilab’s NuMI beam. These and other measurements in progress rely on the accurate identification and reconstruction of the neutrino flavor and energy recorded by our detectors. This presentation describes the first application of convolutional neural network technology for event identification and reconstruction in particle detectors like NOvA. The Convolutional Visual Network (CVN) Algorithm was developed for identification, categorization, and reconstruction of NOvA events. It increased the selection efficiency of the ve appearance signal by 40% and studies show potential impact to the vμ disappearance analysis.

Authors:

Psihas, Fernanda ^[1]

Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States); et al.

Publication Date:: Sun Oct 01 00:00:00 EDT 2017

Research Org.:: Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)

Sponsoring Org.:: USDOE Office of Science (SC), High Energy Physics (HEP)

Contributing Org.:: NOvA Collaboration

OSTI Identifier:: 1423233

Report Number(s):: FERMILAB-CONF-16-737
Journal ID: ISSN 1742-6588; 1638573

Grant/Contract Number:: AC02-07CH11359

Resource Type:: Accepted Manuscript

Journal Name:: Journal of Physics. Conference Series

Additional Journal Information:: Journal Volume: 898; Journal Issue: 7; Conference: 22nd International Conference on Computing in High Energy and Nuclear Physics, San Francisco, CA, 10/10-10/14/2016; Journal ID: ISSN 1742-6588

Publisher:: IOP Publishing

Country of Publication:: United States

Language:: English

Subject:: 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats


                    Psihas, Fernanda. The Convolutional Visual Network for Identification and Reconstruction of NOvA Events.  United States: N. p., 2017. 
Web.  doi:10.1088/1742-6596/898/7/072053.

Copy to clipboard


                    Psihas, Fernanda. The Convolutional Visual Network for Identification and Reconstruction of NOvA Events.  United States.  https://doi.org/10.1088/1742-6596/898/7/072053

Copy to clipboard


                    Psihas, Fernanda. Sun .  
"The Convolutional Visual Network for Identification and Reconstruction of NOvA Events".  United States.  https://doi.org/10.1088/1742-6596/898/7/072053.  https://www.osti.gov/servlets/purl/1423233.

Copy to clipboard


                    
@article{osti_1423233,

  title        = {The Convolutional Visual Network for Identification and Reconstruction of NOvA Events},

  author       = {Psihas, Fernanda},

  abstractNote = {In 2016 the NOvA experiment released results for the observation of oscillations in the vμ and ve channels as well as ve cross section measurements using neutrinos from Fermilab’s NuMI beam. These and other measurements in progress rely on the accurate identification and reconstruction of the neutrino flavor and energy recorded by our detectors. This presentation describes the first application of convolutional neural network technology for event identification and reconstruction in particle detectors like NOvA. The Convolutional Visual Network (CVN) Algorithm was developed for identification, categorization, and reconstruction of NOvA events. It increased the selection efficiency of the ve appearance signal by 40% and studies show potential impact to the vμ disappearance analysis.},

  doi          = {10.1088/1742-6596/898/7/072053},

  journal      = {Journal of Physics. Conference Series},

  number       = 7,

  volume       = 898,

  place        = {United States},

  year         = {Sun Oct 01 00:00:00 EDT 2017},

  month        = {Sun Oct 01 00:00:00 EDT 2017}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1088/1742-6596/898/7/072053

Other availability

Search WorldCat to find libraries that may hold this journal

Figures / Tables:

Figure 1: NOvA characteristic data events. Side views of 3x11 meter sections of the detector. The color of the hits indicates deposited charge (measured in ADC counts). The neutrino neutral current interactions (bottom), as well as the charged current interactions for electron (middle) and muon (top) flavor are each themore »

All figures and tables (6 total)

Save / Share:

Export Metadata

Save to My Library

Figures / Tables found in this record:

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

Similar Records in DOE PAGES and OSTI.GOV collections:

NOvA Reconstruction using Deep Learning [Slides]

Technical Report Groh, Micah

The NOvA experiment has made measurements of the disappearance of νμ and the appearance of νe in the NuMI beam at Fermilab. Key to these measurements is the identification of the neutrino flavor and measurement of the neutrino energy, for which NOvA has implemented deep learning algorithms utilizing tools from the field of computer vision. These algorithms, first applied to NOvA's 2016 results, showed significant improvement over previous reconstruction methods. I will present NOvA's implementation of deep learning algorithms using convolutional neural networks for identification of event neutrino flavor and single particles used in the 2018 analysis.
https://doi.org/10.2172/1462092

Full Text Available
Data-Driven Validation of NOvA's Convolutional Neural Network for Electron (Anti)Neutrino Selection

Thesis/Dissertation Hall, Anna Maureen

NOvA is a long-baseline neutrino oscillation experiment, designed to make measurements of several oscillation parameters using muon neutrino disappearance and electron neutrino appearance. It consists of two functionally equivalent detectors and utilizes the Fermilab NuMI neutrino beam. NOvA uses a convolutional neural network for particle identification of electron neutrino events with a validation process that includes several data-driven techniques. These Muon Removed studies ensure that our classifier performs the same on data as it does on simulation. In particular, Muon Removed Electron-Added studies involve selecting muon neutrino charged current events from both data and simulation and replacing the muon withmore »« less
https://doi.org/10.18130/p9c2-mw37

Full Text Available
Muon Neutrino Disappearance in NOvA with a Deep Convolutional Neural Network Classifier

Thesis/Dissertation Rocco, Dominick Rosario

The NuMI Off-axis Neutrino Appearance Experiment (NOvA) is designed to study neutrino oscillation in the NuMI (Neutrinos at the Main Injector) beam. NOvA observes neutrino oscillation using two detectors separated by a baseline of 810 km; a 14 kt Far Detector in Ash River, MN and a functionally identical 0.3 kt Near Detector at Fermilab. The experiment aims to provide new measurements of Δm² and θ23 and has potential to determine the neutrino mass hierarchy as well as observe CP violation in the neutrino sector. Essential to these analyses is the classification of neutrino interaction events in NOvA detectors. Rawmore »« less
https://doi.org/10.2172/1294514

Full Text Available
Interpretable Joint Event-Particle Reconstruction for Neutrino Physics at NOvA with Sparse CNNs and Transformers

Conference Shmakov, Alexander ; Yankelevich, Alejandro ; Bian, Jianming ; ...

The complex events observed at the NOvA long-baseline neutrino oscillation experiment contain vital information for understanding the most elusive particles in the standard model. The NOvA detectors observe interactions of neutrinos from the NuMI beam at Fermilab. Associating the particles produced in these interaction events to their source particles, a process known as reconstruction, is critical for accurately measuring key parameters of the standard model. Events may contain several particles, each producing sparse high-dimensional spatial observations, and current methods are limited to evaluating individual particles. To accurately label these numerous, high-dimensional observations, we present a novel neural network architecture thatmore »« less
Full Text Available
Event Reconstruction in the NOvA Experiment

Conference Behera, Biswaranjan ; Davies, Gavin ; Psihas, Fernanda

The NOvA experiment observes oscillations in two channels (electron-neutrino appearance and muon-neutrino disappearance) using a predominantly muon-neutrino NuMI beam. The Near Detector records multiple overlapping neutrino interactions in each event and the Far Detector has a large background of cosmic rays due to being located on the surface. The oscillation analyses rely on the accurate reconstruction of neutrino interactions in order to precisely measure the neutrino energy and identify the neutrino flavor and interaction mode. Similarly, measurements of neutrino cross sections using the Near Detector require accurate identification of the particle content of each interaction. A series of pattern recognitionmore »« less
Full Text Available

Similar Records