Publication
Title
Reconstruction of decays to merged photons using end-to-end deep learning with domain continuation in the CMS detector
Author
Institution/Organisation
CMS Collaboration
Abstract
A novel technique based on machine learning is introduced to reconstruct the decays of highly Lorentz boosted particles. Using an end-to-end deep learning strategy, the technique bypasses existing rule-based particle reconstruction methods typically used in high energy physics analyses. It uses minimally processed detector data as input and directly outputs particle properties of interest. The new technique is demonstrated for the reconstruction of the invariant mass of particles decaying in the CMS detector. The decay of a hypothetical scalar particle A into two photons, A gamma gamma, is chosen as a benchmark decay. Lorentz boosts gamma L 1/4 60-600 are considered, ranging from regimes where both photons are resolved to those where the photons are closely merged as one object. A training method using domain continuation is introduced, enabling the invariant mass reconstruction of unresolved photon pairs in a novel way. The new technique is validated using pi 0 gamma gamma decays in LHC collision data.
Language
English
Source (journal)
Physical review D / American Physical Society. - Ridge, N.Y., 2016, currens
Publication
Ridge, N.Y. : American Physical Society , 2023
ISSN
2470-0029
DOI
10.1103/PHYSREVD.108.052002
Volume/pages
108 :5 (2023) , p. 1-34
Article Reference
052002
ISI
001091059400002
Full text (Publisher's DOI)
Full text (open access)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identifier
Creation 01.02.2024
Last edited 07.02.2024
To cite this reference