Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: End-to-end jet classification of quarks and gluons with the CMS Open Data

Journal Article · · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment
 [1];  [1];  [2];  [3];  [4];  [3];  [1];  [1];  [3]
  1. Carnegie Mellon Univ., Pittsburgh, PA (United States)
  2. Carnegie Mellon Univ., Pittsburgh, PA (United States); European Organization for Nuclear Research (CERN), Geneva (Switzerland)
  3. Brown Univ., Providence, RI (United States)
  4. Univ. of Alabama, Tuscaloosa, AL (United States)
+ Show Author Affiliations

We describe the construction of novel end-to-end jet image classifiers to discriminate quark- versus gluon-initiated jets using the simulated CMS Open Data. These multi-detector images correspond to true maps of the low-level energy deposits in the detector, giving the classifiers direct access to the maximum recorded event information about the jet, differing fundamentally from conventional jet images constructed from reconstructed particle-level information. Using this approach, we achieve classification performance competitive with current state-of-the-art jet classifiers that are dominated by particle-based algorithms. We find the performance to be driven by the availability of precise spatial information, highlighting the importance of high-fidelity detector images. We then illustrate how end-to-end jet classification techniques can be incorporated into event classification workflows using Quantum Chromodynamics di-quark versus di-gluon events. We conclude with the end-to-end event classification of full detector images, which we find to be robust against the effects of underlying event and pileup outside the jet regions-of-interest.

Research Organization:
Carnegie Mellon Univ., Pittsburgh, PA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP); European Commission (EC)
Grant/Contract Number:
SC0010118; 765710
OSTI ID:
1638100
Alternate ID(s):
OSTI ID: 1684625; OSTI ID: 1755516; OSTI ID: 1837677
Journal Information:
Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 977; ISSN 0168-9002
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (28)

The anti- k t jet clustering algorithm journal April 2008
Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC journal September 2018
Study of jet shapes in inclusive jet production in p p collisions at s = 7     TeV using the ATLAS detector journal March 2011
Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber journal May 2019
Energy flow networks: deep sets for particle jets journal January 2019
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 journal March 2020
PYTHIA 6.4 physics and manual journal May 2006
Boosted objects: a probe of beyond the standard model physics journal June 2011
The Machine Learning landscape of top taggers journal January 2019
Jet-images — deep learning edition journal July 2016
Deep-learning top taggers or the end of QCD? journal May 2017
Deep learning in color: towards automated quark/gluon jet discrimination journal January 2017
Quark-gluon tagging: Machine learning vs detector journal January 2019
A convolutional neural network neutrino event classifier journal September 2016
ImageNet classification with deep convolutional neural networks journal May 2017
Identification of boosted Higgs bosons decaying into b-quark pairs with the ATLAS detector at 13 $$\text {TeV}$$TeV journal October 2019
Jet substructure at the Large Hadron Collider journal December 2019
Review of Particle Physics journal August 2018
Jet substructure studies with CMS open data journal October 2017
Jet flavor classification in high-energy physics with deep neural networks journal December 2016
Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning journal November 2019
End-to-End Event Classification of High-Energy Physics Data journal September 2018
Jet reconstruction and performance using particle flow with the ATLAS Detector journal July 2017
Geant4—a simulation toolkit
  • 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
journal July 2003
Shape, transverse size, and charged-hadron multiplicity of jets in pp collisions at $ \sqrt{s}=7\;TeV $ journal June 2012
QCD-aware recursive neural networks for jet physics journal January 2019
Quark and Gluon Tagging at the LHC journal October 2011
Particle-flow reconstruction and global event description with the CMS detector journal October 2017

Figures / Tables (12)

Table 1(p. 2)table Table 1
Table 2(p. 3)table Table 2
Table 3(p. 3)table Table 3
Fig. 1(p. 4)figure Fig. 1
Fig. 2(p. 5)figure Fig. 2
Fig. 3(p. 5)figure Fig. 3
Table 4(p. 5)table Table 4
Fig. 4(p. 6)figure Fig. 4
Fig. 5(p. 6)figure Fig. 5
Table 5(p. 6)table Table 5
Table 6(p. 6)table Table 6
Table 7(p. 7)table Table 7

Similar Records

Related Subjects

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
Machine learning
jet images
end-to-end
CMS Open Data
convolutional neural network
LHC
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS