Deeply Learning Deep Inelastic Scattering Kinematics

Abstract

We study the use of deep learning techniques to reconstruct the kinematics of the neutral current deep inelastic scattering (DIS) process in electron-proton collisions. In particular, we use simulated data from the ZEUS experiment at the HERA accelerator facility, and train deep neural networks to reconstruct the kinematic variables $Q^2$ and $x$. Our approach is based on the information used in the classical construction methods, the measurements of the scattered lepton, and the hadronic final state in the detector, but is enhanced through correlations and patterns revealed with the simulated data sets. We show that, with the appropriate selection of a training set, the neural networks sufficiently surpass all classical reconstruction methods on most of the kinematic range considered. Rapid access to large samples of simulated data and the ability of neural networks to effectively extract information from large data sets, both suggest that deep learning techniques to reconstruct DIS kinematics can serve as a rigorous method to combine and outperform the classical reconstruction methods.

arXiv comment16 pages, 8 figures. v3 journal version

References in corpus (21)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• An Introduction to PYTHIA 8.2
• MadGraph 5 : Going Beyond
• Global QCD Analysis of Parton Structure of the Nucleon: CTEQ5 Parton Distributions
• Scattering Amplitudes with Open Loops
• Herwig 7.0 / Herwig++ 3.0 Release Note
• Event Generation with Sherpa 2.2
• WHIZARD: Simulating Multi-Particle Processes at LHC and ILC
• LEPTO 6.5 - A Monte Carlo Generator for Deep Inelastic Lepton-Nucleon Scattering
• The CCFM Monte Carlo generator CASCADE 2.2.0
• HECTOR 1.00 - A program for the calculation of QED, QCD and electroweak corrections to ep and lN deep inelastic neutral and charged current scattering
• Neural Network based Electron Identification in the ZEUS Calorimeter
• On the Kinematic Reconstruction of Deep Inelastic Scattering at HERA: the $\Sigma$ Method
• NNLO QCD corrections to jet production in deep inelastic scattering
• Inclusive-jet and dijet cross sections in deep inelastic scattering at HERA
• Jet-radius dependence of inclusive-jet cross sections in deep inelastic scattering at HERA
• Measurement of High-Q^2 Neutral-Current e^+p Deep Inelastic Scattering Cross-Sections at HERA
• Inclusive-jet cross sections in NC DIS at HERA and a comparison of the kT, anti-kT and SIScone jet algorithms
• A new approach to semi-inclusive deep-inelastic scattering with QED and QCD factorization
• The BlackHat Library for One-Loop Amplitudes

Cited by in corpus (7)

• Machine Learning in Nuclear Physics
• The Present and Future of QCD
• Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
• Machine learning-based jet and event classification at the Electron-Ion Collider with applications to hadron structure and spin physics
• Neutrino-tagged jets at the Electron-Ion Collider
• Unifying Simulation and Inference with Normalizing Flows
• Kinematic fitting of Neutral current events in deep inelastic ep collisions