NOνA (E929)
NuMI Off-Axis νe Appearance Experiment

NOvA Home       Fermilab at Work

NOVA Document 24642-v2

[NOvA DocDB Home]

Understanding neutrino interactions using deep learning

Document #:
Document type:
Submitted by:
Adam Aurisano
Updated by:
Maury Goodman
Document Created:
31 Oct 2017, 11:51
Contents Revised:
05 Nov 2017, 20:35
Metadata Revised:
29 Nov 2017, 15:04
Viewable by:
  • Public document
Modifiable by:

Quick Links:
Latest Version

Other Versions:
The 2015 Nobel Prize in Physics was awarded for the discovery of neutrino oscillations, which indicates that neutrinos have mass. This phenomenon was unexpected and is one of the clearest signs of new physics beyond the Standard Model.

The NOvA experiment aims to deepen our understanding of neutrino oscillations by measuring the properties of a muon neutrino beam produced at Fermi National Accelerator Laboratory at a Near Detector close to the beam source, and measuring the rate that muon neutrinos oscillate into electron neutrinos over an 810 km trip to a 14,000 ton Far Detector in Ash River, MN. Understanding this process may explain why the universe is made of matter instead of antimatter.

Performing this measurement requires a high precision method for classifying neutrino interactions. To this end, we developed a convolutional neural network which gave a 30% improvement in electron neutrino selection over previous methods – equivalent increasing the Far Detector mass by 4,000 tons. In this presentation, I will discuss recent improvements to our convolutional neural network through better handling of sparse input data and redesigning category labels. I will also describe efforts to move beyond full image categorization to networks simultaneously performing classification and characterization tasks.

Notes and Changes:
As given
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