ATLAS flavour-tagging algorithms for the LHC Run 2 pp collision dataset

ATLAS Collaboration

doi:10.1140/epjc/s10052-023-11699-1

ATLAS flavour-tagging algorithms for the LHC Run 2 pp collision dataset

ATLAS Collaboration

Institute of Applied Physics
Mohammed VI Polytechnic University
University of California at Berkeley
Faculty of Physics
University of Bucharest
iThemba Labs
Department of Physics
University of South Africa
University of Zululand
Cadi Ayyad University
New York University Abu Dhabi
The University of Georgia, Tbilisi
CERN
Aix-Marseille Université
University of Oklahoma
University of Massachusetts
University of Göttingen
United States Department of Energy
Mohammed V University in Rabat
Tel Aviv University
Technion-Israel Institute of Technology
New York University
Pontificia Universidad Católica de Chile
National Institute for Nuclear Physics
Abdus Salam International Centre for Theoretical Physics
King's College London
Université Savoie Mont Blanc
AGH University of Science and Technology
University of Toronto
Brandeis University
Northern Illinois University
Istanbul University
University of Geneva
Rutherford Appleton Laboratory
University of California at Santa Cruz
Institute for High Energy Physics
University of Pavia
Johannes Gutenberg University Mainz
Alexandru Ioan Cuza University of Iaşi
University of Granada
Azerbaijan National Academy of Sciences
McGill University
Royal Holloway University of London
German Electron Synchrotron
University of Rome Tor Vergata
University of Hassan II Casablanca
Weizmann Institute of Science
Lund University
Columbia University
University of Victoria BC
University of Edinburgh
University of the Witwatersrand
Horia Hulubei National Institute of Physics and Nuclear Engineering
National Technical University of Athens
University of Amsterdam
Czech Technical University in Prague
Academia Sinica - Institute of Physics
Université Paris-Saclay
University of Sussex
Universidad Técnica Federico Santa Maria
University of Birmingham
University of Naples Federico II
Universidad Nacional de La Plata
University of Washington
Universidad Autónoma de Madrid
University of Manchester
Universidade Federal do Rio de Janeiro
University of Adelaide
Ludwig Maximilian University of Munich
University of Michigan, Ann Arbor
Laboratório de Instrumentação e Física Experimental de Partículas
University of Valencia
University of Oslo
University of Sheffield
University of Texas at Austin
Stockholm University
Oskar Klein Centre
University of Milan
National and Kapodistrian University of Athens
Lawrence Livermore National Laboratory
Oklahoma State University
Lawrence Berkeley National Laboratory
High Energy Accelerator Research Organization, Tsukuba
The University of Tokyo
Humboldt University of Berlin
Universidade Federal de Juiz de Fora
Duke University
University of Liverpool
University of Montreal
University of Freiburg
University of Rome La Sapienza
Nagoya University
Ochanomizu University
Harvard University
Mohamed I University
Comenius University
University of Cape Town
University of Illinois
Shandong University
University of Wuppertal
Nanjing University
TRIUMF
Aristotle University of Thessaloniki
University of Thessaly
Carleton University
Yale University
University of Belgrade
University of Texas at Arlington
University of Sydney
Charles University
Heidelberg University
University of Cambridge
Cracow
University of Pittsburgh
University of Bonn
University of Melbourne
University of Genoa
University College London
Max Planck Institute for Physics (Werner Heisenberg Institute)
SLAC National Accelerator Laboratory
Palacký University Olomouc
University of Science and Technology of China
University of Oxford
CAS - Institute of High Energy Physics
Lancaster University
TU Dortmund University
Roma Tre University
An-Najah National University
University of Glasgow
University of Siegen
Bogazici University
Sorbonne Université
Tufts University
University of Bern
University of Fribourg
University of Warwick
Istinye University
Stony Brook University
Universidade do Estado do Rio de Janeiro
United Arab Emirates University
Uppsala University
University of Arizona
CNRS
Technische Universität Dresden
Queen Mary University of London
University of Würzburg
University of Colorado Boulder
University of Oregon
Gaziantep University
University of Calabria
University of Wisconsin-Madison
University of Louisville
Université Clermont Auvergne
Ohio State University
Shanghai Jiao Tong University
Slovak Academy of Sciences
University of Bergen
Simon Fraser University
Boston University
Michigan State University
Justus Liebig University Giessen
University of Chinese Academy of Sciences
Ankara University
Indiana University Bloomington
University of Pisa
University of Copenhagen
University of Iowa
Westmont College
Radboud University Nijmegen
University of Bologna
Autonomous University of Barcelona
University of Minho
University of Salento
Tbilisi State University
Argonne National Laboratory
Tsinghua University
The Collaborative Innovation Center of Quantum Matter (CICQM)
Chinese University of Hong Kong
National Tsing Hua University
Czech Academy of Sciences
University of Ljubljana
Ben-Gurion University of the Negev
University of Udine
Université Grenoble Alpes
University of Lisbon
University of Johannesburg
University of Naples Parthenope
University of British Columbia
Institute of Particle Physics
INFN-TIFPA
University of Trento
Fondazione Bruno Kessler
University of California at Irvine
University of Pennsylvania School of Arts and Sciences
Universidad de Buenos Aires
York University
Southern Methodist University
Millennium Institute for Subatomic physics at high energy frontier (SAPHIR)
Universidade de São Paulo
Ibn Tofail University
RWTH Aachen University
Demokritos National Centre for Scientific Research
Louisiana Tech University
University of Coimbra
City University of New York
National Institute of Physics, College of Science, University of the Philippines, Diliman
University of the Aegean
The University of Chicago
Stanford University
University Politehnica of Bucharest
Jagiellonian University in Kraków
University of Alberta
Enrico Fermi Center
West University of Timisoara
The California State University
California State University East Bay
ICREA
University of New Mexico
University of Tsukuba
Shinshu University
Tokyo Institute of Technology
Iowa State University
Technical University of Munich
Kobe University
Osaka University
The University of Hong Kong
Yeditepe University
Waseda University
University of Texas at Dallas
Georgian National Academy of Sciences
Ilia State University
Universidad de Tarapacá
Center for Interdisciplinary Research and Innovation (CIRI-AUTH)
Kyushu University
University of Innsbruck
Kyoto University
Universidad Andrés Bello
Hellenic Open University
KTH Royal Institute of Technology
Peking University
Hong Kong University of Science and Technology
IMB-CNM. CSIC
California State University Sacramento
Universidad Antonio Nariño
Transilvania University of Brasov
National Institute for Research and Development of Isotopic and Molecular Technologies
Universidad Nacional de Colombia
Bulgarian Academy of Sciences
Washington College
University of Sharjah
TOBB University of Economics and Technology
University of Hamburg
Kyoto University of Education
Mongolian Academy of Sciences
Universidad de La Serena

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

152 Citations (Scopus)

Abstract

The flavour-tagging algorithms developed by the ATLAS Collaboration and used to analyse its dataset of s=13 TeV pp collisions from Run 2 of the Large Hadron Collider are presented. These new tagging algorithms are based on recurrent and deep neural networks, and their performance is evaluated in simulated collision events. These developments yield considerable improvements over previous jet-flavour identification strategies. At the 77% b-jet identification efficiency operating point, light-jet (charm-jet) rejection factors of 170 (5) are achieved in a sample of simulated Standard Model tt¯ events; similarly, at a c-jet identification efficiency of 30%, a light-jet (b-jet) rejection factor of 70 (9) is obtained.

Original language	English
Article number	681
Journal	European Physical Journal C
Volume	83
Issue number	7
DOIs	https://doi.org/10.1140/epjc/s10052-023-11699-1
Publication status	Published - Jul 2023

ASJC Scopus subject areas

Engineering (miscellaneous)
Physics and Astronomy (miscellaneous)

Access to Document

10.1140/epjc/s10052-023-11699-1

Cite this

@article{53829e0f6e6f4d3fa59e045afc5de4c1,

title = "ATLAS flavour-tagging algorithms for the LHC Run 2 pp collision dataset",

abstract = "The flavour-tagging algorithms developed by the ATLAS Collaboration and used to analyse its dataset of s=13 TeV pp collisions from Run 2 of the Large Hadron Collider are presented. These new tagging algorithms are based on recurrent and deep neural networks, and their performance is evaluated in simulated collision events. These developments yield considerable improvements over previous jet-flavour identification strategies. At the 77\% b-jet identification efficiency operating point, light-jet (charm-jet) rejection factors of 170 (5) are achieved in a sample of simulated Standard Model tt¯ events; similarly, at a c-jet identification efficiency of 30\%, a light-jet (b-jet) rejection factor of 70 (9) is obtained.",

author = "\{ATLAS Collaboration\} and G. Aad and B. Abbott and Abbott, \{D. C.\} and K. Abeling and Abidi, \{S. H.\} and A. Aboulhorma and H. Abramowicz and H. Abreu and Y. Abulaiti and \{Abusleme Hoffman\}, \{A. C.\} and Acharya, \{B. S.\} and \{Adam Bourdarios\}, C. and L. Adamczyk and L. Adamek and Addepalli, \{S. V.\} and J. Adelman and A. Adiguzel and S. Adorni and T. Adye and Affolder, \{A. A.\} and Y. Afik and Agaras, \{M. N.\} and J. Agarwala and A. Aggarwal and C. Agheorghiesei and Aguilar-Saavedra, \{J. A.\} and A. Ahmad and F. Ahmadov and Ahmed, \{W. S.\} and S. Ahuja and X. Ai and G. Aielli and \{Ait Tamlihat\}, M. and B. Aitbenchikh and I. Aizenberg and M. Akbiyik and {\AA}kesson, \{T. P.A.\} and Akimov, \{A. V.\} and \{Al Khoury\}, K. and Alberghi, \{G. L.\} and J. Albert and P. Albicocco and S. Alderweireldt and M. Aleksa and Aleksandrov, \{I. N.\} and M. Bhamjee and Connell, \{S. H.\} and Gololo, \{M. G.D.\} and N. Govender and L. Truong",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = jul,

doi = "10.1140/epjc/s10052-023-11699-1",

language = "English",

volume = "83",

journal = "European Physical Journal C",

issn = "1434-6044",

publisher = "Springer Nature",

number = "7",

}

TY - JOUR

T1 - ATLAS flavour-tagging algorithms for the LHC Run 2 pp collision dataset

AU - ATLAS Collaboration

AU - Aad, G.

AU - Abbott, B.

AU - Abbott, D. C.

AU - Abeling, K.

AU - Abidi, S. H.

AU - Aboulhorma, A.

AU - Abramowicz, H.

AU - Abreu, H.

AU - Abulaiti, Y.

AU - Abusleme Hoffman, A. C.

AU - Acharya, B. S.

AU - Adam Bourdarios, C.

AU - Adamczyk, L.

AU - Adamek, L.

AU - Addepalli, S. V.

AU - Adelman, J.

AU - Adiguzel, A.

AU - Adorni, S.

AU - Adye, T.

AU - Affolder, A. A.

AU - Afik, Y.

AU - Agaras, M. N.

AU - Agarwala, J.

AU - Aggarwal, A.

AU - Agheorghiesei, C.

AU - Aguilar-Saavedra, J. A.

AU - Ahmad, A.

AU - Ahmadov, F.

AU - Ahmed, W. S.

AU - Ahuja, S.

AU - Ai, X.

AU - Aielli, G.

AU - Ait Tamlihat, M.

AU - Aitbenchikh, B.

AU - Aizenberg, I.

AU - Akbiyik, M.

AU - Åkesson, T. P.A.

AU - Akimov, A. V.

AU - Al Khoury, K.

AU - Alberghi, G. L.

AU - Albert, J.

AU - Albicocco, P.

AU - Alderweireldt, S.

AU - Aleksa, M.

AU - Aleksandrov, I. N.

AU - Bhamjee, M.

AU - Connell, S. H.

AU - Gololo, M. G.D.

AU - Govender, N.

AU - Truong, L.

PY - 2023/7

Y1 - 2023/7

N2 - The flavour-tagging algorithms developed by the ATLAS Collaboration and used to analyse its dataset of s=13 TeV pp collisions from Run 2 of the Large Hadron Collider are presented. These new tagging algorithms are based on recurrent and deep neural networks, and their performance is evaluated in simulated collision events. These developments yield considerable improvements over previous jet-flavour identification strategies. At the 77% b-jet identification efficiency operating point, light-jet (charm-jet) rejection factors of 170 (5) are achieved in a sample of simulated Standard Model tt¯ events; similarly, at a c-jet identification efficiency of 30%, a light-jet (b-jet) rejection factor of 70 (9) is obtained.

AB - The flavour-tagging algorithms developed by the ATLAS Collaboration and used to analyse its dataset of s=13 TeV pp collisions from Run 2 of the Large Hadron Collider are presented. These new tagging algorithms are based on recurrent and deep neural networks, and their performance is evaluated in simulated collision events. These developments yield considerable improvements over previous jet-flavour identification strategies. At the 77% b-jet identification efficiency operating point, light-jet (charm-jet) rejection factors of 170 (5) are achieved in a sample of simulated Standard Model tt¯ events; similarly, at a c-jet identification efficiency of 30%, a light-jet (b-jet) rejection factor of 70 (9) is obtained.

UR - https://www.scopus.com/pages/publications/85167625195

U2 - 10.1140/epjc/s10052-023-11699-1

DO - 10.1140/epjc/s10052-023-11699-1

M3 - Article

AN - SCOPUS:85167625195

SN - 1434-6044

VL - 83

JO - European Physical Journal C

JF - European Physical Journal C

IS - 7

M1 - 681

ER -

ATLAS flavour-tagging algorithms for the LHC Run 2 pp collision dataset

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this