Machine Learning at the Belle II Experiment

The Full Event Interpretation and Its Validation on Belle Data

  • Thomas Keck

Part of the Springer Theses book series (Springer Theses)

Table of contents

  1. Front Matter
    Pages i-xi
  2. Thomas Keck
    Pages 1-1
  3. Thomas Keck
    Pages 3-21
  4. Thomas Keck
    Pages 23-62
  5. Thomas Keck
    Pages 63-100
  6. Thomas Keck
    Pages 101-153
  7. Thomas Keck
    Pages 155-155
  8. Back Matter
    Pages 157-174

About this book


This book explores how machine learning can be used to improve the efficiency of expensive fundamental science experiments.

The first part introduces the Belle and Belle II experiments, providing a detailed description of the Belle to Belle II data conversion tool, currently used by many analysts. 

The second part covers machine learning in high-energy physics, discussing the Belle II machine learning infrastructure and selected algorithms in detail. Furthermore, it examines several machine learning techniques that can be used to control and reduce systematic uncertainties. 

The third part investigates the important exclusive B tagging technique, unique to physics experiments operating at the Υ resonances, and studies in-depth the novel Full Event Interpretation algorithm, which doubles the maximum tag-side efficiency of its predecessor. 

The fourth part presents a complete measurement of the branching fraction of the rare leptonic B decay “B→tau nu”, which is used to validate the algorithms discussed in previous parts.


Machine Learning at Belle II Full Event Interpretation Exclusive Tagging Hadronic Tagging Semileptonic Tagging Belle to Belle II Data Conversion Belle II B to tau nu FastBDT FastFit

Authors and affiliations

  • Thomas Keck
    • 1
  1. 1.Institute of Experimental Particle PhysicsKarlsruhe Institute of TechnologyKarlsruheGermany

Bibliographic information

  • DOI
  • Copyright Information Springer Nature Switzerland AG 2018
  • Publisher Name Springer, Cham
  • eBook Packages Physics and Astronomy
  • Print ISBN 978-3-319-98248-9
  • Online ISBN 978-3-319-98249-6
  • Series Print ISSN 2190-5053
  • Series Online ISSN 2190-5061
  • Buy this book on publisher's site