skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks

Abstract

Experiments in particle physics produce enormous quantities of data that must be analyzed and interpreted by teams of physicists. This analysis is often exploratory, where scientists are unable to enumerate the possible types of signal prior to performing the experiment. Thus, tools for summarizing, clustering, visualizing and classifying high-dimensional data are essential. Here in this work, we show that meaningful physical content can be revealed by transforming the raw data into a learned high-level representation using deep neural networks, with measurements taken at the Daya Bay Neutrino Experiment as a case study. We further show how convolutional deep neural networks can provide an effective classification filter with greater than 97% accuracy across different classes of physics events, significantly better than other machine learning approaches.

Authors:
 [1];  [2];  [3];  [1];  [1];  [1];  [3];  [1]
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  2. Seoul National Univ. (Korea, Republic of)
  3. Univ. of California, Irvine, CA (United States)
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
OSTI Identifier:
1379700
Grant/Contract Number:  
AC02-05CH11231
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)
Additional Journal Information:
Journal Name: 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA); Conference: 15. IEEE International Conference on Machine Learning and Applications (ICMLA) , Anaheim, CA (United States), 18-20 Dec 2016
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS; High-Energy Physics; Unsupervised Learning; Deep Learning; Autoencoders; Computer architecture; Mesons; Convolution; Data visualization; Detectors; Physics; Neural networks

Citation Formats

Racah, Evan, Ko, Seyoon, Sadowski, Peter, Bhimji, Wahid, Tull, Craig, Oh, Sang-Yun, Baldi, Pierre, and Prabhat, . Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks. United States: N. p., 2017. Web. doi:10.1109/ICMLA.2016.0160.
Racah, Evan, Ko, Seyoon, Sadowski, Peter, Bhimji, Wahid, Tull, Craig, Oh, Sang-Yun, Baldi, Pierre, & Prabhat, . Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks. United States. doi:10.1109/ICMLA.2016.0160.
Racah, Evan, Ko, Seyoon, Sadowski, Peter, Bhimji, Wahid, Tull, Craig, Oh, Sang-Yun, Baldi, Pierre, and Prabhat, . Thu . "Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks". United States. doi:10.1109/ICMLA.2016.0160. https://www.osti.gov/servlets/purl/1379700.
@article{osti_1379700,
title = {Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks},
author = {Racah, Evan and Ko, Seyoon and Sadowski, Peter and Bhimji, Wahid and Tull, Craig and Oh, Sang-Yun and Baldi, Pierre and Prabhat, .},
abstractNote = {Experiments in particle physics produce enormous quantities of data that must be analyzed and interpreted by teams of physicists. This analysis is often exploratory, where scientists are unable to enumerate the possible types of signal prior to performing the experiment. Thus, tools for summarizing, clustering, visualizing and classifying high-dimensional data are essential. Here in this work, we show that meaningful physical content can be revealed by transforming the raw data into a learned high-level representation using deep neural networks, with measurements taken at the Daya Bay Neutrino Experiment as a case study. We further show how convolutional deep neural networks can provide an effective classification filter with greater than 97% accuracy across different classes of physics events, significantly better than other machine learning approaches.},
doi = {10.1109/ICMLA.2016.0160},
journal = {2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)},
number = ,
volume = ,
place = {United States},
year = {Thu Feb 02 00:00:00 EST 2017},
month = {Thu Feb 02 00:00:00 EST 2017}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share: