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

Racah, Evan; Ko, Seyoon; Sadowski, Peter; Bhimji, Wahid; Tull, Craig; Oh, Sang-Yun; Baldi, Pierre; Prabhat, .

doi:10.1109/ICMLA.2016.0160

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:

Racah, Evan ^[1]; Ko, Seyoon ^[2]; Sadowski, Peter ^[3]; Bhimji, Wahid ^[1]; Tull, Craig ^[1]; Oh, Sang-Yun ^[1]; Baldi, Pierre ^[3]; Prabhat, . ^[1]

Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Seoul National Univ. (Korea, Republic of)
Univ. of California, Irvine, CA (United States)

Publication Date:: Thu Feb 02 00:00:00 EST 2017

Research Org.:: Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

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

OSTI Identifier:: 1379700

Grant/Contract Number:: AC02-05CH11231

Resource Type:: 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.

Copy to clipboard


                    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.  https://doi.org/10.1109/ICMLA.2016.0160

Copy to clipboard


                    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.  https://doi.org/10.1109/ICMLA.2016.0160.  https://www.osti.gov/servlets/purl/1379700.

Copy to clipboard


                    
@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}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/ICMLA.2016.0160

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Works referencing / citing this record:

Machine learning at the energy and intensity frontiers of particle physics
journal, August 2018

Radovic, Alexander; Williams, Mike; Rousseau, David
Nature, Vol. 560, Issue 7716
DOI: 10.1038/s41586-018-0361-2

Similar Records in DOE PAGES and OSTI.GOV collections:

Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment

Journal Article Perdue, G. N. ; Ghosh, A. ; Wospakrik, M. ; ... - Journal of Instrumentation

We present a simulation-based study using deep convolutional neural networks (DCNNs) to identify neutrino interaction vertices in the MINERvA passive targets region, and illustrate the application of domain adversarial neural networks (DANNs) in this context. DANNs are designed to be trained in one domain (simulated data) but tested in a second domain (physics data) and utilize unlabeled data from the second domain so that during training only features which are unable to discriminate between the domains are promoted. MINERvA is a neutrino-nucleus scattering experiment using the NuMI beamline at Fermilab. A-dependent cross sections are an important part of the physicsmore »« less
Cited by 8
https://doi.org/10.1088/1748-0221/13/11/P11020

Full Text Available
Novel usage of deep learning and high-performance computing in long-baseline neutrino oscillation experiments

Conference Alonso Monsalve, Saúl ; Rodriguez, Manuel J. - EPJ Web Conf.

Mención Internacional en el título de doctorDeep-learning methods are playing a crucial role in numerous scientific and industrialapplications. Over the past two decades, these techniques have helped in the collection,reconstruction, and analysis of large data samples in particle physics experiments. Themain topic of this PhD research is the study of deep-learning techniques in long-baselineneutrino oscillation experiments. Neutrinos are mysterious light elementary particles,and their investigation is essential to shed light on some of the remaining open questionsin physics. The work presented here describes an algorithm based on a convolutionalneural network developed to provide highly accurate and efficient selections of electronneutrino andmore »« less
https://doi.org/10.1051/epjconf/202024501030

Full Text Available
Neutrino interaction classification with a convolutional neural network in the DUNE far detector

Journal Article Abi, B. ; Acciarri, R. ; Acero, M. A. ; ... - Physical Review. D.

The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on a convolutional neural network has been developed to provide highly efficient and pure selections of electron neutrino and muon neutrino charged-current interactions. The electron neutrino (antineutrino) selection efficiency peaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between 2-5 GeV. The muon neutrino (antineutrino) event selection is found to have a maximum efficiency of 96% (97%) and exceeds 90% (95%) efficiency for reconstructed neutrinomore »« less
https://doi.org/10.1103/PhysRevD.102.092003
Final Phase I Technical Report - Deep Learning Enabled FAIR Data Management for Center for Functional Nanomaterials

Technical Report Sun, Yu

Modern materials science experiments are pushing towards several frontiers: 1) faster data collection rates, for example the Center for Functional Nanomaterials (CFN) and National Synchrotron Light Source II (NSLS-II) at BNL alone generates data in the range of 500TB/week, 2) larger arrays of detectors with higher pixel counts, 3) multi-modal measurement of elemental, structural, chemical, and physical properties at different lengths and scales of material system, and 4) sophisticated reconstruction of the shape, density, and strain field inside a crystal. These trends, once combined, highlight an enormous challenge concerning the scale of data analytics. It is clear that modern scientificmore »« less
Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

Journal Article Churchill, R. M. ; Tobias, B. ; Zhu, Y. - Physics of Plasmas

In this paper, we discuss recent advances in deep convolutional neural networks (CNNs) for sequence learning, which allow identifying longrange, multi-scale phenomena in long sequences, such as those found in fusion plasmas. We point out several benefits of these deep CNN architectures, such as not requiring experts such as physicists to hand-craft input data features, the ability to capture longer range dependencies compared to the more common sequence neural networks (recurrent neural networks like long short-term memory networks), and the comparative computational efficiency. We apply this neural network architecture to the popular problem of disruption prediction in fusion energy tokamaks,more »« less
Cited by 28
https://doi.org/10.1063/1.5144458

Full Text Available

Similar Records

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

Abstract

Citation Formats

Machine learning at the energy and intensity frontiers of particle physics journal, August 2018

Machine learning at the energy and intensity frontiers of particle physics
journal, August 2018