Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques


Sirunyan A. M., Tumasyan A., Adam W., Ambrogi F., Bergauer T., Brandstetter J., ...More

JOURNAL OF INSTRUMENTATION, vol.15, no.6, 2020 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 15 Issue: 6
  • Publication Date: 2020
  • Doi Number: 10.1088/1748-0221/15/06/p06005
  • Journal Name: JOURNAL OF INSTRUMENTATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, Index Islamicus, INSPEC
  • Çukurova University Affiliated: Yes

Abstract

Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at root S = 13 TeV, corresponding to an integrated luminosity of 35.9 fb(-1). Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.