Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network

Summary, in English

The energy and mass measurements of jets are crucial tasks for the Large Hadron Collider experiments. This paper presents a new calibration method to simultaneously calibrate these quantities for large-radius jets measured with the ATLAS detector using a deep neural network (DNN). To address the specificities of the calibration problem, special loss functions and training procedures are employed, and a complex network architecture, which includes feature annotation and residual connection layers, is used. The DNN-based calibration is compared to the standard numerical approach in an extensive series of tests. The DNN approach is found to perform significantly better in almost all of the tests and over most of the relevant kinematic phase space. In particular, it consistently improves the energy and mass resolutions, with a 30% better energy resolution obtained for transverse momenta pT > 500 GeV. © 2024 The Author(s). Published by IOP Publishing Ltd.

• Author: G. Aad; T.P.A. Åkesson; C. Doglioni; P.A. Ekman; V. Hedberg; H. Herde; B. Konya; E. Lytken; R. Poettgen; N.D. Simpson; O. Smirnova; E.J. Wallin; L. Zwalinski
• Department/s: Particle and nuclear physics; eSSENCE: The e-Science Collaboration; Department of Physics
• Publishing year: 2024
• Language: English
• Publication/Series: Machine Learning: Science and Technology
• Volume: 5
• Issue: 3
• Links: http://dx.doi.org/10.1088/2632-2153/ad611e
• Document type: Journal article
• Publisher: IOP Publishing
• Topic: Subatomic Physics
• Keywords: ATLAS; calibrations; CERN jets; detector; Colliding beam accelerators; Deep neural networks; Hadrons; Jet aircraft; Jets; Kinematics; Linear accelerators; Photons; ATLAS detectors; CERN jet; Energy; Energy calibration; Energy resolutions; Mass calibrations; Mass measurements; Measurements of; Neural-networks; Phase space methods
• Status: Published
• ISBN/ISSN/Other: ISSN: 2632-2153