NOνA (E929)
NuMI Off-Axis νe Appearance Experiment

NOvA Home       Fermilab at Work

NOVA Document 40354-v4

[NOvA DocDB Home]

Reco & ML in Neutrino Experiments - Particle Identification Using Convolutional Neural Networks in the NOvA Experiment

Document #:
Document type:
Submitted by:
Ryan Murphy
Updated by:
Maury Goodman
Document Created:
11 Sep 2019, 10:30
Contents Revised:
17 Sep 2019, 04:38
Metadata Revised:
24 Sep 2019, 15:36
Viewable by:
  • Public document
Modifiable by:

Quick Links:
Latest Version

Other Versions:
In 2016, NOvA was the first HEP experiment to employ a convolutional neural network (CNN) in a physics result, using the CNN to classify neutrino events. The physics analyses performed by NOvA can be improved by further identification and reconstruction of particles in the interaction final states. We have developed the first implementation of a CNN for single particle classification which employs context-enhanced inputs. Using contextual information from the neutrino interaction that produces the particles provides additional information to the training, extending the capabilities of our original classifier. This implementation uses a four-tower siamese architecture for separation of independent inputs and inclusion of contextual information. This classifier distinguishes between electrons, muons, photons, pions, and protons with a global efficiency and purity of 83.7% and 83.5%, respectively. In this talk I will describe our implementation of NOvA's single particle CNN, discuss the advantages of adding context information, provide case-studies of the applications and planned future improvements to the classifier.
Files in Document:
Notes and Changes:
v3 - Final version
Associated with Events:
held on 11 Sep 2019 in The Disappearance Room-WH13SW
held on 13 Sep 2019 in Field Cage WH13SX
DocDB Home ]  [ Search ] [ Last 20 Days ] [ List Authors ] [ List Topics ]

Security, Privacy, LegalFermi National Accelerator Laboratory

DocDB Version 8.8.9, contact Document Database Administrators