A Deep Neural Network for Simultaneous Estimation of b Jet Energy and Resolution

CMS Collaboration

doi:10.1007/s41781-020-00041-z

A Deep Neural Network for Simultaneous Estimation of b Jet Energy and Resolution

CMS Collaboration

Física

CERN
A. Alikhanian Yerevan Institute of Physics
Institut für Hochenergiephysik der OeAW
Belarusian State University
University of Antwerp
Vrije Universiteit Brussel
Université Libre de Bruxelles
Ghent University
Université catholique de Louvain
Centro Brasileiro de Pesquisas Fisicas
Universidade do Estado do Rio de Janeiro
Universidade Estadual Paulista Júlio de Mesquita Filho
Bulgarian Academy of Sciences
University of Sofia
Beihang University
Tsinghua University
Institute of High Energy Physics Chinese Academy of Science
Peking University
Zhejiang University
Universidad de los Andes Colombia
Universidad de Antioquia
University of Split
Faculty of Science, University of Split
Institute Rudjer Boskovic
University of Cyprus
Charles University
Escuela Politecnica Nacional
Egyptian Network of High Energy Physics
National Institute of Chemical Physics and Biophysics, Tallinn
University of Helsinki
Helsinki Institute of Physics
Lappeenranta University of Technology
Université Paris-Saclay
Laboratoire Leprince-Ringuet
Institut Pluridisciplinaire Hubert Curien
IN2P3-CNRS
Universite Claude Bernard Lyon 1
Georgian Technical University
Tbilisi State University
RWTH Aachen University
Deutsches Elektronen-Synchrotron (DESY)
University of Hamburg
Karlsruhe Institute of Technology
NCSR Demokritos
National and Kapodistrian University of Athens
National Technical University of Athens
University of Ioannina
Eötvös Loránd University
KFKI Research Institute for Particle and Nuclear Physics
Institute for Nuclear Research
University of Debrecen
Eszterhazy Karoly University
Indian Institute of Science
National Institute of Science Education and Research
Panjab University
University of Delhi
Saha Institute of Nuclear Physics
Indian Institute of Technology Madras
Bhabha Atomic Research Centre
Tata Institute of Fundamental Research, Mumbai
Indian Institute of Science Education and Research Pune
Institute for Research for Fundamental Sciences
University College Dublin
Université di Bari
University of Bologna
University of Catania
University of Florence
National Institute for Nuclear Physics
University of Genoa
Université di Milano-Bicocca
University of Naples Federico II
University of Padua
Université di Pavia
Université di Perugia
University of Pisa
Université di Roma La Sapienza
Université di Torino
Université di Trieste
Kyungpook National University
Chonnam National University
Hanyang University
Korea University
Kyung Hee University
Sejong University
Seoul National University
University of Seoul
Sungkyunkwan University
Riga Technical University
Vilnius University
Universiti Malaya
Universidad de Sonora
Centro de Investigacion y de Estudios Avanzados del Instituto Politécnico Nacional
Universidad Iberoamericana (UIA)
Benemerita Universidad Autonoma de Puebla
Universidad Autónoma de San Luis Potosí
University of Montenegro
University of Auckland
University of Canterbury
Quaid-I-Azam University
AGH University of Krakow
National Centre for Nuclear Research
University of Warsaw
Laboratório de Instrumentação e Fisica Experimental de Partículas
Joint Institute for Nuclear Research, Dubna
Petersburg Nuclear Physics Institute (PNPI)
RAS - Institute for Nuclear Research
Institute for Theoretical and Experimental Physics
Moscow Institute of Physics and Technology
National Research Nuclear University ‘Moscow Engineering Physics Institute’ (MEPhI)
RAS - P.N. Lebedev Physics Institute
Lomonosov Moscow State University
Rutherford Appleton Laboratory
Novosibirsk State University
Institute for High Energy Physics
National Research Tomsk Polytechnic University
Tomsk State University
University of Belgrade
CIEMAT
Universidad Autónoma de Madrid
University of Oviedo
CSIC-Universidad de Cantabria
University of Colombo
University of Ruhuna
Paul Scherrer Institut
ETH Zurich
University of Zurich
National Central University
National Taiwan University
Chulalongkorn University
Cukurova University
Middle East Technical University (METU)
Bogazici University
Istanbul Technical University
Istanbul University
Institute for Scintillation Materials of National Academy of Science of Ukraine
NASU - Kharkov Institute of Physics and Technology
University of Bristol
Imperial College London
Brunel University London
Baylor University
Catholic University of America
University of Alabama
Boston University
Brown University
University of California, Davis
University of California at Los Angeles
University of California at Riverside
University of California at San Diego
University of California at Santa Barbara
California Institute of Technology
Carnegie Mellon University
University of Colorado at Boulder
Cornell University
Fermi National Accelerator Laboratory
University of Florida
Florida International University
Florida State University
Florida Institute of Technology
University of Illinois at Chicago
University of Iowa
Johns Hopkins University
University of Kansas
Kansas State University
Lawrence Livermore National Laboratory
University of Maryland, College Park
Massachusetts Institute of Technology
University of Minnesota-Twin Cities
University of Mississippi
University of Nebraska-Lincoln
State University of New York at Buffalo
Northeastern University
Northwestern University
University of Notre Dame
Ohio State University
Princeton University
University of Puerto Rico
Purdue University
Purdue University Calumet
Rice University
University of Rochester
Rutgers University–New Brunswick
University of Tennessee
Texas AandM University
Texas Tech University
Vanderbilt University
University of Virginia
Wayne State University
University of Wisconsin-Madison

Research output: Contribution to journal › Article › peer-review

36 Scopus citations

Abstract

We describe a method to obtain point and dispersion estimates for the energies of jets arising from b quarks produced in proton–proton collisions at an energy of s=13TeV at the CERN LHC. The algorithm is trained on a large sample of simulated b jets and validated on data recorded by the CMS detector in 2017 corresponding to an integrated luminosity of 41 fb-1. A multivariate regression algorithm based on a deep feed-forward neural network employs jet composition and shape information, and the properties of reconstructed secondary vertices associated with the jet. The results of the algorithm are used to improve the sensitivity of analyses that make use of b jets in the final state, such as the observation of Higgs boson decay to b b ¯.

Original language	English
Article number	10
Journal	Computing and Software for Big Science
Volume	4
Issue number	1
DOIs	https://doi.org/10.1007/s41781-020-00041-z
State	Published - Dec 2020

Keywords

CMS
Deep learning
Higgs boson
Jet energy
Jet resolution
b jets

Access to Document

10.1007/s41781-020-00041-z

Cite this

@article{e52fd1f9ba6642f8acf109db7ca131ea,

title = "A Deep Neural Network for Simultaneous Estimation of b Jet Energy and Resolution",

abstract = "We describe a method to obtain point and dispersion estimates for the energies of jets arising from b quarks produced in proton–proton collisions at an energy of s=13TeV at the CERN LHC. The algorithm is trained on a large sample of simulated b jets and validated on data recorded by the CMS detector in 2017 corresponding to an integrated luminosity of 41 fb-1. A multivariate regression algorithm based on a deep feed-forward neural network employs jet composition and shape information, and the properties of reconstructed secondary vertices associated with the jet. The results of the algorithm are used to improve the sensitivity of analyses that make use of b jets in the final state, such as the observation of Higgs boson decay to b b ¯.",

keywords = "CMS, Deep learning, Higgs boson, Jet energy, Jet resolution, b jets",

author = "\{CMS Collaboration\} and Sirunyan, \{A. M.\} and A. Tumasyan and W. Adam and F. Ambrogi and T. Bergauer and M. Dragicevic and J. Er{\"o} and Valle, \{A. Escalante Del\} and M. Flechl and R. Fr{\"u}hwirth and M. Jeitler and N. Krammer and I. Kr{\"a}tschmer and D. Liko and T. Madlener and I. Mikulec and N. Rad and J. Schieck and R. Sch{\"o}fbeck and M. Spanring and D. Spitzbart and W. Waltenberger and Wulz, \{C. E.\} and M. Zarucki and V. Drugakov and V. Mossolov and Gonzalez, \{J. Suarez\} and Darwish, \{M. R.\} and \{De Wolf\}, \{E. A.\} and Croce, \{D. Di\} and X. Janssen and A. Lelek and M. Pieters and Sfar, \{H. Rejeb\} and Haevermaet, \{H. Van\} and Mechelen, \{P. Van\} and Putte, \{S. Van\} and Remortel, \{N. Van\} and F. Blekman and Bols, \{E. S.\} and Chhibra, \{S. S.\} and J. D{\textquoteright}Hondt and \{De Clercq\}, J. and D. Lontkovskyi and S. Lowette and I. Marchesini and S. Moortgat and Q. Python and K. Skovpen and Jarrin, \{E. Carrera\}",

note = "Publisher Copyright: {\textcopyright} 2020, The Author(s).",

year = "2020",

month = dec,

doi = "10.1007/s41781-020-00041-z",

language = "Ingl{\'e}s",

volume = "4",

journal = "Computing and Software for Big Science",

issn = "2510-2044",

publisher = "Springer Nature",

number = "1",

}

TY - JOUR

T1 - A Deep Neural Network for Simultaneous Estimation of b Jet Energy and Resolution

AU - CMS Collaboration

AU - Sirunyan, A. M.

AU - Tumasyan, A.

AU - Adam, W.

AU - Ambrogi, F.

AU - Bergauer, T.

AU - Dragicevic, M.

AU - Erö, J.

AU - Valle, A. Escalante Del

AU - Flechl, M.

AU - Frühwirth, R.

AU - Jeitler, M.

AU - Krammer, N.

AU - Krätschmer, I.

AU - Liko, D.

AU - Madlener, T.

AU - Mikulec, I.

AU - Rad, N.

AU - Schieck, J.

AU - Schöfbeck, R.

AU - Spanring, M.

AU - Spitzbart, D.

AU - Waltenberger, W.

AU - Wulz, C. E.

AU - Zarucki, M.

AU - Drugakov, V.

AU - Mossolov, V.

AU - Gonzalez, J. Suarez

AU - Darwish, M. R.

AU - De Wolf, E. A.

AU - Croce, D. Di

AU - Janssen, X.

AU - Lelek, A.

AU - Pieters, M.

AU - Sfar, H. Rejeb

AU - Haevermaet, H. Van

AU - Mechelen, P. Van

AU - Putte, S. Van

AU - Remortel, N. Van

AU - Blekman, F.

AU - Bols, E. S.

AU - Chhibra, S. S.

AU - D’Hondt, J.

AU - De Clercq, J.

AU - Lontkovskyi, D.

AU - Lowette, S.

AU - Marchesini, I.

AU - Moortgat, S.

AU - Python, Q.

AU - Skovpen, K.

AU - Jarrin, E. Carrera

PY - 2020/12

Y1 - 2020/12

N2 - We describe a method to obtain point and dispersion estimates for the energies of jets arising from b quarks produced in proton–proton collisions at an energy of s=13TeV at the CERN LHC. The algorithm is trained on a large sample of simulated b jets and validated on data recorded by the CMS detector in 2017 corresponding to an integrated luminosity of 41 fb-1. A multivariate regression algorithm based on a deep feed-forward neural network employs jet composition and shape information, and the properties of reconstructed secondary vertices associated with the jet. The results of the algorithm are used to improve the sensitivity of analyses that make use of b jets in the final state, such as the observation of Higgs boson decay to b b ¯.

AB - We describe a method to obtain point and dispersion estimates for the energies of jets arising from b quarks produced in proton–proton collisions at an energy of s=13TeV at the CERN LHC. The algorithm is trained on a large sample of simulated b jets and validated on data recorded by the CMS detector in 2017 corresponding to an integrated luminosity of 41 fb-1. A multivariate regression algorithm based on a deep feed-forward neural network employs jet composition and shape information, and the properties of reconstructed secondary vertices associated with the jet. The results of the algorithm are used to improve the sensitivity of analyses that make use of b jets in the final state, such as the observation of Higgs boson decay to b b ¯.

KW - CMS

KW - Deep learning

KW - Higgs boson

KW - Jet energy

KW - Jet resolution

KW - b jets

UR - https://www.scopus.com/pages/publications/85097776096

U2 - 10.1007/s41781-020-00041-z

DO - 10.1007/s41781-020-00041-z

M3 - Artículo

AN - SCOPUS:85097776096

SN - 2510-2044

VL - 4

JO - Computing and Software for Big Science

JF - Computing and Software for Big Science

IS - 1

M1 - 10

ER -

A Deep Neural Network for Simultaneous Estimation of b Jet Energy and Resolution

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this