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

Title: Calorimetry with deep learning: particle simulation and reconstruction for collider physics

Abstract

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

Authors:
 [1];  [2];  [3];  [4];  [5];  [6];  [4];  [7];  [8];  [2];  [4];  [9];  [2];  [9];  [4]; ORCiD logo [4]
  1. Univ. of Chicago, IL (United States)
  2. European Organization for Nuclear Research (CERN), Geneva (Switzerland)
  3. Univ. of Texas, Arlington, TX (United States)
  4. Univ. of Illinois at Urbana-Champaign, IL (United States)
  5. European Organization for Nuclear Research (CERN), Geneva (Switzerland); Univ. of Engineering and Technology (UET), Peshawar (Pakistan)
  6. Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
  7. Univ. of California, San Diego, CA (United States)
  8. Univ. of Helsinki (Finland)
  9. California Inst. of Technology (CalTech), Pasadena, CA (United States)
Publication Date:
Research Org.:
Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), High Energy Physics (HEP); European Research Council (ERC); National Science Foundation (NSF); State of Illinois; NVIDIA; SuperMicro; Kavli Foundation
OSTI Identifier:
1648563
Report Number(s):
FERMILAB-PUB-20-448-CMS; arXiv:1912.06794
Journal ID: ISSN 1434-6044; oai:inspirehep.net:1770936
Grant/Contract Number:  
AC02-07CH11359; SC0011925; 772369; 083650; OCI-0725070; ACI-1238993
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
European Physical Journal. C, Particles and Fields
Additional Journal Information:
Journal Volume: 80; Journal Issue: 7; Journal ID: ISSN 1434-6044
Publisher:
Springer
Country of Publication:
United States
Language:
English
Subject:
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY; 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats

Belayneh, Dawit, Carminati, Federico, Farbin, Amir, Hooberman, Benjamin, Khattak, Gulrukh, Liu, Miaoyuan, Liu, Junze, Olivito, Dominick, Barin Pacela, Vitória, Pierini, Maurizio, Schwing, Alexander, Spiropulu, Maria, Vallecorsa, Sofia, Vlimant, Jean-Roch, Wei, Wei, and Zhang, Matt. Calorimetry with deep learning: particle simulation and reconstruction for collider physics. United States: N. p., 2020. Web. doi:10.1140/epjc/s10052-020-8251-9.
Belayneh, Dawit, Carminati, Federico, Farbin, Amir, Hooberman, Benjamin, Khattak, Gulrukh, Liu, Miaoyuan, Liu, Junze, Olivito, Dominick, Barin Pacela, Vitória, Pierini, Maurizio, Schwing, Alexander, Spiropulu, Maria, Vallecorsa, Sofia, Vlimant, Jean-Roch, Wei, Wei, & Zhang, Matt. Calorimetry with deep learning: particle simulation and reconstruction for collider physics. United States. https://doi.org/10.1140/epjc/s10052-020-8251-9
Belayneh, Dawit, Carminati, Federico, Farbin, Amir, Hooberman, Benjamin, Khattak, Gulrukh, Liu, Miaoyuan, Liu, Junze, Olivito, Dominick, Barin Pacela, Vitória, Pierini, Maurizio, Schwing, Alexander, Spiropulu, Maria, Vallecorsa, Sofia, Vlimant, Jean-Roch, Wei, Wei, and Zhang, Matt. 2020. "Calorimetry with deep learning: particle simulation and reconstruction for collider physics". United States. https://doi.org/10.1140/epjc/s10052-020-8251-9. https://www.osti.gov/servlets/purl/1648563.
@article{osti_1648563,
title = {Calorimetry with deep learning: particle simulation and reconstruction for collider physics},
author = {Belayneh, Dawit and Carminati, Federico and Farbin, Amir and Hooberman, Benjamin and Khattak, Gulrukh and Liu, Miaoyuan and Liu, Junze and Olivito, Dominick and Barin Pacela, Vitória and Pierini, Maurizio and Schwing, Alexander and Spiropulu, Maria and Vallecorsa, Sofia and Vlimant, Jean-Roch and Wei, Wei and Zhang, Matt},
abstractNote = {Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.},
doi = {10.1140/epjc/s10052-020-8251-9},
url = {https://www.osti.gov/biblio/1648563}, journal = {European Physical Journal. C, Particles and Fields},
issn = {1434-6044},
number = 7,
volume = 80,
place = {United States},
year = {2020},
month = {7}
}

Works referenced in this record:

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


Track finding with neural networks
journal, July 1989


Classification of the hadronic decays of the Z0 into b and c quark pairs using a neural network
journal, December 1992


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


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


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


Weakly Supervised Classification For High Energy Physics
journal, September 2018


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


QCD-aware recursive neural networks for jet physics
journal, January 2019


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


The ATLAS Experiment at the CERN Large Hadron Collider
journal, August 2008


The CMS experiment at the CERN LHC
journal, August 2008


Physics and Detectors at CLIC: CLIC Conceptual Design Report
null, January 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
  • https://doi.org/10.1016/S0168-9002(03)01368-8

The ATLAS Fast Monte Carlo Production Chain Project
journal, December 2015


Jet-images — deep learning edition
journal, July 2016


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


CaloGAN: Simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks
journal, January 2018


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


Electromagnetic showers beyond shower shapes
journal, January 2020

  • de Oliveira, Luke; Nachman, Benjamin; Paganini, Michela
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 951
  • https://doi.org/10.1016/j.nima.2019.162879

Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
journal, September 2018


Going deeper with convolutions
conference, June 2015