skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine learning techniques in searches for$$t\bar{t}$$h in the h → $$b\bar{b}$$ decay channel

Abstract

Study of the production of pairs of top quarks in association with a Higgs boson is one of the primary goals of the Large Hadron Collider over the next decade, as measurements of this process may help us to understand whether the uniquely large mass of the top quark plays a special role in electroweak symmetry breaking. Higgs bosons decay predominantly to b$$\bar{_b}$$, yielding signatures for the signal that are similar to t$$\bar{_t}$$ + jets with heavy flavor. Though particularly challenging to study due to the similar kinematics between signal and background events, such final states (t$$\bar{_t}$$b$$\bar{b}$$) are an important channel for studying the top quark Yukawa coupling. This paper presents a systematic study of machine learning (ML) methods for detecting t$$\bar{_t}$$h in the h → b$$\bar{b}$$ decay channel. Among the seven ML methods tested, we show that neural network models outperform alternative methods. In addition, two neural models used in this paper outperform NeuroBayes, one of the standard algorithms used in current particle physics experiments. We further study the effectiveness of ML algorithms by investigating the impact of feature set and data size, as well as the depth of the networks for neural models. We demonstrate that an extended feature set leads to improvement of performance over basic features. Furthermore, the availability of large samples for training is found to be important for improving the performance of the techniques. For the features and the data set studied here, neural networks of more layers deliver comparable performance to their simpler counterparts.

Authors:
 [1];  [1];  [2];  [2];  [1];  [2];  [1]
  1. Northern Illinois Univ., DeKalb, IL (United States)
  2. Argonne National Lab. (ANL), Lemont, IL (United States)
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
National Science Foundation (NSF); USDOE Office of Science (SC)
OSTI Identifier:
1373727
Grant/Contract Number:  
AC02-06CH11357
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Instrumentation
Additional Journal Information:
Journal Volume: 12; Journal Issue: 04; Journal ID: ISSN 1748-0221
Publisher:
Institute of Physics (IOP)
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; 46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY; Analysis and statistical methods; Data processing methods

Citation Formats

Santos, Robert, Nguyen, M., Webster, Jordan, Ryu, Soo, Adelman, Jahred, Chekanov, Sergei, and Zhou, Jie. Machine learning techniques in searches for$t\bar{t}$h in the h → $b\bar{b}$ decay channel. United States: N. p., 2017. Web. https://doi.org/10.1088/1748-0221/12/04/P04014.
Santos, Robert, Nguyen, M., Webster, Jordan, Ryu, Soo, Adelman, Jahred, Chekanov, Sergei, & Zhou, Jie. Machine learning techniques in searches for$t\bar{t}$h in the h → $b\bar{b}$ decay channel. United States. https://doi.org/10.1088/1748-0221/12/04/P04014
Santos, Robert, Nguyen, M., Webster, Jordan, Ryu, Soo, Adelman, Jahred, Chekanov, Sergei, and Zhou, Jie. Mon . "Machine learning techniques in searches for$t\bar{t}$h in the h → $b\bar{b}$ decay channel". United States. https://doi.org/10.1088/1748-0221/12/04/P04014. https://www.osti.gov/servlets/purl/1373727.
@article{osti_1373727,
title = {Machine learning techniques in searches for$t\bar{t}$h in the h → $b\bar{b}$ decay channel},
author = {Santos, Robert and Nguyen, M. and Webster, Jordan and Ryu, Soo and Adelman, Jahred and Chekanov, Sergei and Zhou, Jie},
abstractNote = {Study of the production of pairs of top quarks in association with a Higgs boson is one of the primary goals of the Large Hadron Collider over the next decade, as measurements of this process may help us to understand whether the uniquely large mass of the top quark plays a special role in electroweak symmetry breaking. Higgs bosons decay predominantly to b$\bar{_b}$, yielding signatures for the signal that are similar to t$\bar{_t}$ + jets with heavy flavor. Though particularly challenging to study due to the similar kinematics between signal and background events, such final states (t$\bar{_t}$b$\bar{b}$) are an important channel for studying the top quark Yukawa coupling. This paper presents a systematic study of machine learning (ML) methods for detecting t$\bar{_t}$h in the h → b$\bar{b}$ decay channel. Among the seven ML methods tested, we show that neural network models outperform alternative methods. In addition, two neural models used in this paper outperform NeuroBayes, one of the standard algorithms used in current particle physics experiments. We further study the effectiveness of ML algorithms by investigating the impact of feature set and data size, as well as the depth of the networks for neural models. We demonstrate that an extended feature set leads to improvement of performance over basic features. Furthermore, the availability of large samples for training is found to be important for improving the performance of the techniques. For the features and the data set studied here, neural networks of more layers deliver comparable performance to their simpler counterparts.},
doi = {10.1088/1748-0221/12/04/P04014},
journal = {Journal of Instrumentation},
number = 04,
volume = 12,
place = {United States},
year = {2017},
month = {4}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 1 work
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Comparative study of various algorithms for the merging of parton showers and matrix elements in hadronic collisions
journal, December 2007


Measurement of event shapes at large momentum transfer with the ATLAS detector in pp collisions at $\sqrt{\mathbf{s}}=7\ \mathrm{TeV}$
journal, November 2012


The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
journal, July 2014

  • Alwall, J.; Frederix, R.; Frixione, S.
  • Journal of High Energy Physics, Vol. 2014, Issue 7
  • DOI: 10.1007/JHEP07(2014)079

MadGraph 5: going beyond
journal, June 2011

  • Alwall, Johan; Herquet, Michel; Maltoni, Fabio
  • Journal of High Energy Physics, Vol. 2011, Issue 6
  • DOI: 10.1007/JHEP06(2011)128

A convolutional neural network neutrino event classifier
journal, September 2016


A neural network clustering algorithm for the ATLAS silicon pixel detector
journal, September 2014


Fox-Wolfram moments in Higgs physics
journal, April 2013

  • Bernaciak, Catherine; Buschmann, Malte Seán Andreas; Butter, Anja
  • Physical Review D, Vol. 87, Issue 7
  • DOI: 10.1103/PhysRevD.87.073014

Parton distributions with QED corrections
journal, December 2013


Boosting Higgs pair production in the $$b\bar{b}b\bar{b}$$ b b ¯ b b ¯ final state with multivariate techniques
journal, July 2016


Parameterized neural networks for high-energy physics
journal, April 2016


Herwig++ physics and manual
journal, November 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

Enhanced Higgs Boson to τ + τ Search with Deep Learning
journal, March 2015


Observation of Top Quark Production in p ¯ p Collisions with the Collider Detector at Fermilab
journal, April 1995


Total Top-Quark Pair-Production Cross Section at Hadron Colliders Through O ( α S 4 )
journal, June 2013


Search for the standard model Higgs boson produced in association with a top-quark pair in pp collisions at the LHC
journal, May 2013

  • Chatrchyan, S.; Khachatryan, V.; Sirunyan, A. M.
  • Journal of High Energy Physics, Vol. 2013, Issue 5
  • DOI: 10.1007/JHEP05(2013)145

HepSim: A Repository with Predictions for High-Energy Physics Experiments
journal, January 2015


Search for Z resonances decaying to t t ¯ in dilepton + jets final states in p p collisions at s = 7 TeV
journal, April 2013


Search for a standard model Higgs boson produced in association with a top-quark pair and decaying to bottom quarks using a matrix element method
journal, June 2015


The anti- k t jet clustering algorithm
journal, April 2008


Observation of the Top Quark
journal, April 1995


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

Introduction to HOBIT, a b-jet identification tagger at the CDF experiment optimized for light Higgs boson searches
journal, January 2013

  • Freeman, J.; Junk, T.; Kirby, M.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 697
  • DOI: 10.1016/j.nima.2012.09.021

Jet flavor classification in high-energy physics with deep neural networks
journal, December 2016


The WEKA data mining software: an update
journal, November 2009

  • Hall, Mark; Frank, Eibe; Holmes, Geoffrey
  • ACM SIGKDD Explorations Newsletter, Vol. 11, Issue 1
  • DOI: 10.1145/1656274.1656278

Search for the associated production of the Higgs boson with a top-quark pair
journal, September 2014

  • Khachatryan, V.; Sirunyan, A. M.; Tumasyan, A.
  • Journal of High Energy Physics, Vol. 2014, Issue 9
  • DOI: 10.1007/JHEP09(2014)087

Erratum: Search for the associated production of the Higgs boson with a top-quark pair
journal, October 2014

  • Khachatryan, V.; Sirunyan, A. M.; Tumasyan, A.
  • Journal of High Energy Physics, Vol. 2014, Issue 10
  • DOI: 10.1007/JHEP10(2014)106

LHCb Topological Trigger Reoptimization
journal, December 2015


FastJet user manual: (for version 3.0.2)
journal, March 2012


A neural network z -vertex trigger for Belle II
journal, May 2015


Boosted decision trees as an alternative to artificial neural networks for particle identification
journal, May 2005

  • Roe, Byron P.; Yang, Hai-Jun; Zhu, Ji
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 543, Issue 2-3
  • DOI: 10.1016/j.nima.2004.12.018

PYTHIA 6.4 physics and manual
journal, May 2006


BIOCAT: a pattern recognition platform for customizable biological image classification and annotation
journal, October 2013


    Works referencing / citing this record:

    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

    Energy flow networks: deep sets for particle jets
    journal, January 2019

    • Komiske, Patrick T.; Metodiev, Eric M.; Thaler, Jesse
    • Journal of High Energy Physics, Vol. 2019, Issue 1
    • DOI: 10.1007/jhep01(2019)121