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

Title: Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters

Abstract

Physicists at the Large Hadron Collider (LHC) rely on detailed simulations of particle collisions to build expectations of what experimental data may look like under different theoretical modeling assumptions. Petabytes of simulated data are needed to develop analysis techniques, though they are expensive to generate using existing algorithms and computing resources. The modeling of detectors and the precise description of particle cascades as they interact with the material in the calorimeter are the most computationally demanding steps in the simulation pipeline. We therefore introduce a deep neural network-based generative model to enable high-fidelity, fast, electromagnetic calorimeter simulation. There are still challenges for achieving precision across the entire phase space, but our current solution can reproduce a variety of particle shower properties while achieving speedup factors of up to 100 000×. This opens the door to a new era of fast simulation that could save significant computing time and disk space, while extending the reach of physics searches and precision measurements at the LHC and beyond.

Authors:
; ;
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:
1418184
Alternate Identifier(s):
OSTI ID: 1485074
Grant/Contract Number:  
AC02-05CH11231; FG02-92ER40704
Resource Type:
Published Article
Journal Name:
Physical Review Letters
Additional Journal Information:
Journal Name: Physical Review Letters Journal Volume: 120 Journal Issue: 4; Journal ID: ISSN 0031-9007
Publisher:
American Physical Society
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats

Paganini, Michela, de Oliveira, Luke, and Nachman, Benjamin. Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters. United States: N. p., 2018. Web. doi:10.1103/PhysRevLett.120.042003.
Paganini, Michela, de Oliveira, Luke, & Nachman, Benjamin. Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters. United States. doi:10.1103/PhysRevLett.120.042003.
Paganini, Michela, de Oliveira, Luke, and Nachman, Benjamin. Fri . "Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters". United States. doi:10.1103/PhysRevLett.120.042003.
@article{osti_1418184,
title = {Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters},
author = {Paganini, Michela and de Oliveira, Luke and Nachman, Benjamin},
abstractNote = {Physicists at the Large Hadron Collider (LHC) rely on detailed simulations of particle collisions to build expectations of what experimental data may look like under different theoretical modeling assumptions. Petabytes of simulated data are needed to develop analysis techniques, though they are expensive to generate using existing algorithms and computing resources. The modeling of detectors and the precise description of particle cascades as they interact with the material in the calorimeter are the most computationally demanding steps in the simulation pipeline. We therefore introduce a deep neural network-based generative model to enable high-fidelity, fast, electromagnetic calorimeter simulation. There are still challenges for achieving precision across the entire phase space, but our current solution can reproduce a variety of particle shower properties while achieving speedup factors of up to 100 000×. This opens the door to a new era of fast simulation that could save significant computing time and disk space, while extending the reach of physics searches and precision measurements at the LHC and beyond.},
doi = {10.1103/PhysRevLett.120.042003},
journal = {Physical Review Letters},
number = 4,
volume = 120,
place = {United States},
year = {2018},
month = {1}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
DOI: 10.1103/PhysRevLett.120.042003

Citation Metrics:
Cited by: 13 works
Citation information provided by
Web of Science

Figures / Tables:

FIG. 1 FIG. 1: Average γ GEANT4 shower (top row), and average γ CaloGAN shower (bottom row), with progressive calorimeter depth (from left to right).

Save / Share:

Works referenced in this record:

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

  • Cogan, Josh; Kagan, Michael; Strauss, Emanuel
  • Journal of High Energy Physics, Vol. 2015, Issue 2
  • DOI: 10.1007/JHEP02(2015)118

Fast simulation of electromagnetic showers in the ATLAS calorimeter: Frozen showers
journal, April 2009


Common Accounting System for Monitoring the ATLAS Distributed Computing Resources
journal, June 2014


Reconstruction of three-dimensional porous media using generative adversarial neural networks
journal, October 2017


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

  • de Oliveira, Luke; Paganini, Michela; Nachman, Benjamin
  • Computing and Software for Big Science, Vol. 1, Issue 1
  • DOI: 10.1007/s41781-017-0004-6

The ATLAS Simulation Infrastructure
journal, September 2010


The Fast Simulation of The CMS Experiment
journal, December 2012


Geant4—a simulation toolkit
journal, July 2003

  • Agostinelli, S.; Allison, J.; Amako, K.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 506, Issue 3
  • DOI: 10.1016/S0168-9002(03)01368-8

Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
journal, January 2017

  • Schawinski, Kevin; Zhang, Ce; Zhang, Hantian
  • Monthly Notices of the Royal Astronomical Society: Letters
  • DOI: 10.1093/mnrasl/slx008

Review of Particle Physics
journal, August 2014


Measurement of the Inelastic Proton-Proton Cross Section at s = 13 TeV with the ATLAS Detector at the LHC
journal, October 2016


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


PYTHIA 6.4 physics and manual
journal, May 2006


The fast simulation of electromagnetic and hadronic showers
journal, May 1990

  • Grindhammer, G.; Rudowicz, M.; Peters, S.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 290, Issue 2-3
  • DOI: 10.1016/0168-9002(90)90566-O

Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
journal, September 2012


Topological cell clustering in the ATLAS calorimeters and its performance in LHC Run 1
journal, July 2017


    Works referencing / citing this record:

    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


      Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.