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

Title: Machine learning at the energy and intensity frontiers of particle physics

Abstract

Our knowledge of the fundamental particles of nature and their interactions is summarized by the standard model of particle physics. Advancing our understanding in this field has required experiments that operate at ever higher energies and intensities, which produce extremely large and information-rich data samples. The use of machine-learning techniques is revolutionizing how we interpret these data samples, greatly increasing the discovery potential of present and future experiments. Here we summarize the challenges and opportunities that come with the use of machine learning at the frontiers of particle physics.

Authors:
 [1];  [2];  [3];  [4];  [5];  [6];  [7];  [4];  [8]
  1. College of William and Mary, Williamsburg, VA (United States)
  2. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  3. Univ. Paris-Sud, Orsay (France)
  4. SLAC National Accelerator Lab., Menlo Park, CA (United States)
  5. Univ. di Bologna, Bologna (Italy); INFN Sezione di Bologna, Bologna (Italy)
  6. Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
  7. Univ. of Cincinnati, Cincinnati, OH (United States)
  8. Tufts Univ., Medford, MA (United States)
Publication Date:
Research Org.:
SLAC National Accelerator Lab., Menlo Park, CA (United States); Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), High Energy Physics (HEP)
OSTI Identifier:
1469751
Alternate Identifier(s):
OSTI ID: 1498560
Report Number(s):
FERMILAB-PUB-18-436-ND
Journal ID: ISSN 0028-0836; PII: 361
Grant/Contract Number:  
AC02-76SF00515; AC02-07CH11359
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Nature (London)
Additional Journal Information:
Journal Volume: 560; Journal Issue: 7716; Journal ID: ISSN 0028-0836
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats

Radovic, Alexander, Williams, Mike, Rousseau, David, Kagan, Michael, Bonacorsi, Daniele, Himmel, Alexander, Aurisano, Adam, Terao, Kazuhiro, and Wongjirad, Taritree. Machine learning at the energy and intensity frontiers of particle physics. United States: N. p., 2018. Web. doi:10.1038/s41586-018-0361-2.
Radovic, Alexander, Williams, Mike, Rousseau, David, Kagan, Michael, Bonacorsi, Daniele, Himmel, Alexander, Aurisano, Adam, Terao, Kazuhiro, & Wongjirad, Taritree. Machine learning at the energy and intensity frontiers of particle physics. United States. https://doi.org/10.1038/s41586-018-0361-2
Radovic, Alexander, Williams, Mike, Rousseau, David, Kagan, Michael, Bonacorsi, Daniele, Himmel, Alexander, Aurisano, Adam, Terao, Kazuhiro, and Wongjirad, Taritree. Wed . "Machine learning at the energy and intensity frontiers of particle physics". United States. https://doi.org/10.1038/s41586-018-0361-2. https://www.osti.gov/servlets/purl/1469751.
@article{osti_1469751,
title = {Machine learning at the energy and intensity frontiers of particle physics},
author = {Radovic, Alexander and Williams, Mike and Rousseau, David and Kagan, Michael and Bonacorsi, Daniele and Himmel, Alexander and Aurisano, Adam and Terao, Kazuhiro and Wongjirad, Taritree},
abstractNote = {Our knowledge of the fundamental particles of nature and their interactions is summarized by the standard model of particle physics. Advancing our understanding in this field has required experiments that operate at ever higher energies and intensities, which produce extremely large and information-rich data samples. The use of machine-learning techniques is revolutionizing how we interpret these data samples, greatly increasing the discovery potential of present and future experiments. Here we summarize the challenges and opportunities that come with the use of machine learning at the frontiers of particle physics.},
doi = {10.1038/s41586-018-0361-2},
url = {https://www.osti.gov/biblio/1469751}, journal = {Nature (London)},
issn = {0028-0836},
number = 7716,
volume = 560,
place = {United States},
year = {2018},
month = {8}
}

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

Citation Metrics:
Cited by: 11 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

uBoost: a boosting method for producing uniform selection efficiencies from multivariate classifiers
journal, December 2013


A measurement of the production of D*± mesons on the Z0 resonance
journal, March 1995


Deep learning
journal, May 2015


The use of neural networks in γ-π0 discrimination
journal, June 1993

  • Babbage, Wayne S.; Thompson, Lee F.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 330, Issue 3
  • https://doi.org/10.1016/0168-9002(93)90579-7

Search for the standard model Higgs boson produced in association with a W or a Z boson and decaying to bottom quarks
journal, January 2014


Predicting dataset popularity for the CMS experiment
journal, October 2016


Using LSTM recurrent neural networks for monitoring the LHC superconducting magnets
journal, September 2017

  • Wielgosz, Maciej; Skoczeń, Andrzej; Mertik, Matej
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 867
  • https://doi.org/10.1016/j.nima.2017.06.020

Mastering the game of Go with deep neural networks and tree search
journal, January 2016


Decorrelated jet substructure tagging using adversarial neural networks
journal, October 2017


Jet substructure classification in high-energy physics with deep neural networks
journal, May 2016


Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber
journal, March 2017


Search for Dark Photons Produced in 13 TeV p p Collisions
journal, February 2018


Search for Hidden-Sector Bosons in B 0 K * 0 μ + μ Decays
journal, October 2015


Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
journal, September 2012


Going deeper with convolutions
conference, June 2015


Disk storage management for LHCb based on Data Popularity estimator
journal, December 2015


ImageNet Large Scale Visual Recognition Challenge
journal, April 2015


Backpropagation Applied to Handwritten Zip Code Recognition
journal, December 1989


Higgs search by neural networks at LHC
journal, February 1994


Multivariate Analysis Methods in Particle Physics
journal, November 2011


A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
journal, August 1997


Constraints on Oscillation Parameters from ν e Appearance and ν μ Disappearance in NOvA
journal, June 2017


LHCb detector performance
journal, March 2015


Jet flavor classification in high-energy physics with deep neural networks
journal, December 2016


Efficient antihydrogen detection in antimatter physics by deep learning
journal, September 2017


Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters
journal, January 2018


LHC Machine
journal, August 2008


Using neural networks to identify jets
journal, February 1991


Boosted decision trees as an alternative to artificial neural networks for particle identification
journal, May 2005

  • Roe, Byron P.; Yang, Hai-Jun; Zhu, Ji
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 543, Issue 2-3
  • https://doi.org/10.1016/j.nima.2004.12.018

Search for active-sterile neutrino mixing using neutral-current interactions in NOvA
journal, October 2017


Finding gluon jets with a neural trigger
journal, September 1990


The LHCb trigger and its performance in 2011
journal, April 2013


Monitoring data transfer latency in CMS computing operations
journal, December 2015


Neural networks and cellular automata in experimental high energy physics
journal, June 1988


Learning representations by back-propagating errors
journal, October 1986


GRID Storage Optimization in Transparent and User-Friendly Way for LHCb Datasets
journal, October 2017


Parameterized neural networks for high-energy physics
journal, April 2016


LHCb trigger streams optimization
journal, October 2017


Design and construction of the MicroBooNE detector
journal, February 2017


Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks
conference, December 2016


Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree
journal, February 2013


LHCb Topological Trigger Reoptimization
journal, December 2015


Towards automation of data quality system for CERN CMS experiment
journal, October 2017


Learning to Forget: Continual Prediction with LSTM
journal, October 2000


JETNET 3.0—A versatile artificial neural network package
journal, June 1994


New approaches for boosting to uniformity
journal, March 2015


Background rejection in NEXT using deep neural networks
journal, January 2017


Neural Networks for Modeling and Control of Particle Accelerators
journal, April 2016


Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
journal, September 2017


Searching for exotic particles in high-energy physics with deep learning
journal, July 2014


Measurement of the tau polarisation at the Z resonance
journal, September 1993


Some Effects of Ionizing Radiation on the Formation of Bubbles in Liquids
journal, August 1952


Pattern recognition in high energy physics with artificial neural networks — JETNET 2.0
journal, May 1992


Parton shower uncertainties in jet substructure analyses with deep neural networks
journal, January 2017


ATLAS pixel detector electronics and sensors
journal, July 2008


Evidence for the Higgs-boson Yukawa coupling to tau leptons with the ATLAS detector
journal, April 2015


Jet-images — deep learning edition
journal, July 2016


A convolutional neural network neutrino event classifier
journal, September 2016


Jet-images: computer vision inspired techniques for jet tagging
journal, February 2015


Deep learning in color: towards automated quark/gluon jet discrimination
journal, January 2017


Deep-learning top taggers or the end of QCD?
journal, May 2017


Electron efficiency measurements with the ATLAS detector using 2012 LHC proton–proton collision data
journal, March 2017


Evidence for the 125 GeV Higgs boson decaying to a pair of τ leptons
journal, May 2014


Weakly supervised classification in high energy physics
journal, May 2017


Search for Dark Photons Produced in 13 TeV $pp$ Collisions
text, January 2018


    Works referencing / citing this record:

    A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
    journal, August 1997


    Measurement of the tau polarisation at the Z resonance
    journal, September 1993


    A measurement of the production of D*± mesons on the Z0 resonance
    journal, March 1995


    ImageNet Large Scale Visual Recognition Challenge
    journal, April 2015


    Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
    journal, September 2017


    Neural networks and cellular automata in experimental high energy physics
    journal, June 1988


    Pattern recognition in high energy physics with artificial neural networks — JETNET 2.0
    journal, May 1992


    JETNET 3.0—A versatile artificial neural network package
    journal, June 1994


    The use of neural networks in γ-π0 discrimination
    journal, June 1993

    • Babbage, Wayne S.; Thompson, Lee F.
    • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 330, Issue 3
    • https://doi.org/10.1016/0168-9002(93)90579-7

    Higgs search by neural networks at LHC
    journal, February 1994


    Using neural networks to identify jets
    journal, February 1991


    Boosted decision trees as an alternative to artificial neural networks for particle identification
    journal, May 2005

    • Roe, Byron P.; Yang, Hai-Jun; Zhu, Ji
    • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 543, Issue 2-3
    • https://doi.org/10.1016/j.nima.2004.12.018

    Using LSTM recurrent neural networks for monitoring the LHC superconducting magnets
    journal, September 2017

    • Wielgosz, Maciej; Skoczeń, Andrzej; Mertik, Matej
    • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 867
    • https://doi.org/10.1016/j.nima.2017.06.020

    Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
    journal, September 2012


    Learning representations by back-propagating errors
    journal, October 1986


    Deep learning
    journal, May 2015


    Mastering the game of Go with deep neural networks and tree search
    journal, January 2016


    Searching for exotic particles in high-energy physics with deep learning
    journal, July 2014


    Monitoring data transfer latency in CMS computing operations
    journal, December 2015


    Disk storage management for LHCb based on Data Popularity estimator
    journal, December 2015


    LHCb Topological Trigger Reoptimization
    journal, December 2015


    Predicting dataset popularity for the CMS experiment
    journal, October 2016


    GRID Storage Optimization in Transparent and User-Friendly Way for LHCb Datasets
    journal, October 2017


    LHCb trigger streams optimization
    journal, October 2017


    Towards automation of data quality system for CERN CMS experiment
    journal, October 2017


    New approaches for boosting to uniformity
    journal, March 2015


    Background rejection in NEXT using deep neural networks
    journal, January 2017


    Design and construction of the MicroBooNE detector
    journal, February 2017


    Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber
    journal, March 2017


    LHC Machine
    journal, August 2008


    Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree
    journal, February 2013


    The LHCb trigger and its performance in 2011
    journal, April 2013


    uBoost: a boosting method for producing uniform selection efficiencies from multivariate classifiers
    journal, December 2013


    Efficient antihydrogen detection in antimatter physics by deep learning
    journal, September 2017


    Some Effects of Ionizing Radiation on the Formation of Bubbles in Liquids
    journal, August 1952


    Search for the standard model Higgs boson produced in association with a W or a Z boson and decaying to bottom quarks
    journal, January 2014


    Jet substructure classification in high-energy physics with deep neural networks
    journal, May 2016


    Jet flavor classification in high-energy physics with deep neural networks
    journal, December 2016


    Parton shower uncertainties in jet substructure analyses with deep neural networks
    journal, January 2017


    Search for active-sterile neutrino mixing using neutral-current interactions in NOvA
    journal, October 2017


    Decorrelated jet substructure tagging using adversarial neural networks
    journal, October 2017


    Search for Hidden-Sector Bosons in B 0 K * 0 μ + μ Decays
    journal, October 2015


    Constraints on Oscillation Parameters from ν e Appearance and ν μ Disappearance in NOvA
    journal, June 2017


    Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters
    journal, January 2018


    Search for Dark Photons Produced in 13 TeV p p Collisions
    journal, February 2018


    Finding gluon jets with a neural trigger
    journal, September 1990


    Going deeper with convolutions
    conference, June 2015


    Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks
    conference, December 2016


    Neural Networks for Modeling and Control of Particle Accelerators
    journal, April 2016


    Parameterized neural networks for high-energy physics
    journal, April 2016


    Multivariate Analysis Methods in Particle Physics
    journal, November 2011


    Learning to Forget: Continual Prediction with LSTM
    journal, October 2000


    Backpropagation Applied to Handwritten Zip Code Recognition
    journal, December 1989


    Learning representations of irregular particle-detector geometry with distance-weighted graph networks
    journal, July 2019


    Learning representations of irregular particle-detector geometry with distance-weighted graph networks
    journal, July 2019


    Energy flow networks: deep sets for particle jets
    journal, January 2019


    Calculating pull for non-singlet jets
    journal, December 2019


    FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing
    journal, October 2019


    Topology Classification with Deep Learning to Improve Real-Time Event Selection at the LHC
    journal, August 2019


    Quantum optical neural networks
    journal, July 2019


    Applications, promises, and pitfalls of deep learning for fluorescence image reconstruction
    journal, July 2019


    Machine learning workflows to estimate class probabilities for precision cancer diagnostics on DNA methylation microarray data
    journal, January 2020


    Deep Neural Network Inverse Design of Integrated Photonic Power Splitters
    journal, February 2019


    The inverse design of structural color using machine learning
    journal, January 2019


    Deep learning for mining protein data
    journal, December 2019


    Regressive and generative neural networks for scalar field theory
    journal, July 2019


    Context-enriched identification of particles with a convolutional network for neutrino events
    journal, October 2019


    Machine learning and the physical sciences
    journal, December 2019


    Neural hierarchical models of ecological populations
    journal, April 2020


    Pileup mitigation at the Large Hadron Collider with graph neural networks
    journal, July 2019


    Machine and deep learning applications in particle physics
    journal, December 2019