DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: End-to-End Physics Event Classification with CMS Open Data: Applying Image-Based Deep Learning to Detector Data for the Direct Classification of Collision Events at the LHC

Abstract

This paper describes the construction of novel end-to-end image-based classifiers that directly leverage low-level simulated detector data to discriminate signal and background processes in pp collision events at the Large Hadron Collider at CERN. To better understand what end-to-end classifiers are capable of learning from the data and to address a number of associated challenges, we distinguish the decay of the standard model Higgs boson into two photons from its leading background sources using high-fidelity simulated CMS Open Data. We demonstrate the ability of end-to-end classifiers to learn from the angular distribution of the photons recorded as electromagnetic showers, their intrinsic shapes, and the energy of their constituent hits, even when the underlying particles are not fully resolved, delivering a clear advantage in such cases over purely kinematics-based classifiers.

Authors:
ORCiD logo [1];  [1];  [2];  [1]
  1. Carnegie Mellon Univ., Pittsburgh, PA (United States)
  2. Univ. of Florida, Gainesville, FL (United States)
Publication Date:
Research Org.:
Carnegie Mellon Univ., Pittsburgh, PA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), High Energy Physics (HEP)
OSTI Identifier:
1755518
Grant/Contract Number:  
SC0010118
Resource Type:
Accepted Manuscript
Journal Name:
Computing and Software for Big Science
Additional Journal Information:
Journal Volume: 4; Journal Issue: 1; Journal ID: ISSN 2510-2036
Publisher:
Springer
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; end-to-end; detector images; machine learning; deep learning; CNN; Resnet; photon ID; event classification; mass sculpting; LHC; CMS; open data; higgs boson

Citation Formats

Andrews, M., Paulini, M., Gleyzer, S., and Poczos, B. End-to-End Physics Event Classification with CMS Open Data: Applying Image-Based Deep Learning to Detector Data for the Direct Classification of Collision Events at the LHC. United States: N. p., 2020. Web. doi:10.1007/s41781-020-00038-8.
Andrews, M., Paulini, M., Gleyzer, S., & Poczos, B. End-to-End Physics Event Classification with CMS Open Data: Applying Image-Based Deep Learning to Detector Data for the Direct Classification of Collision Events at the LHC. United States. https://doi.org/10.1007/s41781-020-00038-8
Andrews, M., Paulini, M., Gleyzer, S., and Poczos, B. Wed . "End-to-End Physics Event Classification with CMS Open Data: Applying Image-Based Deep Learning to Detector Data for the Direct Classification of Collision Events at the LHC". United States. https://doi.org/10.1007/s41781-020-00038-8. https://www.osti.gov/servlets/purl/1755518.
@article{osti_1755518,
title = {End-to-End Physics Event Classification with CMS Open Data: Applying Image-Based Deep Learning to Detector Data for the Direct Classification of Collision Events at the LHC},
author = {Andrews, M. and Paulini, M. and Gleyzer, S. and Poczos, B.},
abstractNote = {This paper describes the construction of novel end-to-end image-based classifiers that directly leverage low-level simulated detector data to discriminate signal and background processes in pp collision events at the Large Hadron Collider at CERN. To better understand what end-to-end classifiers are capable of learning from the data and to address a number of associated challenges, we distinguish the decay of the standard model Higgs boson into two photons from its leading background sources using high-fidelity simulated CMS Open Data. We demonstrate the ability of end-to-end classifiers to learn from the angular distribution of the photons recorded as electromagnetic showers, their intrinsic shapes, and the energy of their constituent hits, even when the underlying particles are not fully resolved, delivering a clear advantage in such cases over purely kinematics-based classifiers.},
doi = {10.1007/s41781-020-00038-8},
journal = {Computing and Software for Big Science},
number = 1,
volume = 4,
place = {United States},
year = {Wed Mar 11 00:00:00 EDT 2020},
month = {Wed Mar 11 00:00:00 EDT 2020}
}

Works referenced in this record:

Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC
journal, September 2018


/GluGluHToGG_M-125_8TeV-pythia6/Summer12_DR53X-PU_RD1_START53_V7N-v2/AODSIM
dataset, January 2017


Observation of the diphoton decay of the Higgs boson and measurement of its properties
journal, October 2014


DELPHES 3: a modular framework for fast simulation of a generic collider experiment
journal, February 2014

  • de Favereau, J.; Delaere, C.; Demin, P.
  • Journal of High Energy Physics, Vol. 2014, Issue 2
  • DOI: 10.1007/JHEP02(2014)057

PYTHIA 6.4 physics and manual
journal, May 2006


Jet tagging via particle clouds
journal, March 2020


Jet-images — deep learning edition
journal, July 2016

  • de Oliveira, Luke; Kagan, Michael; Mackey, Lester
  • Journal of High Energy Physics, Vol. 2016, Issue 7
  • DOI: 10.1007/JHEP07(2016)069

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

  • Kasieczka, Gregor; Plehn, Tilman; Russell, Michael
  • Journal of High Energy Physics, Vol. 2017, Issue 5
  • DOI: 10.1007/JHEP05(2017)006

New approaches for boosting to uniformity
journal, March 2015


Deep Residual Learning for Image Recognition
conference, June 2016

  • He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • DOI: 10.1109/CVPR.2016.90

CMS Simulation Software
journal, December 2012


End-to-End Event Classification of High-Energy Physics Data
journal, September 2018


Pileup subtraction using jet areas
journal, January 2008


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

  • Baldi, P.; Sadowski, P.; Whiteson, D.
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms5308

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

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

  • Louppe, Gilles; Cho, Kyunghyun; Becot, Cyril
  • Journal of High Energy Physics, Vol. 2019, Issue 1
  • DOI: 10.1007/JHEP01(2019)057

Description and performance of track and primary-vertex reconstruction with the CMS tracker
journal, October 2014


The CMS experiment at the CERN LHC
journal, August 2008


Particle-flow reconstruction and global event description with the CMS detector
journal, October 2017


Higgs boson decays to CP -odd scalars at the Fermilab Tevatron and beyond
journal, February 2001

  • Dobrescu, Bogdan A.; Landsberg, Greg; Matchev, Konstantin T.
  • Physical Review D, Vol. 63, Issue 7
  • DOI: 10.1103/PhysRevD.63.075003