Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network
Aad, G. ; Åkesson, T.P.A. LU
; Doglioni, C.
LU
; Ekman, P.A.
LU
; Hedberg, V.
LU
; Herde, H.
LU
; Konya, B.
LU
; Lytken, E.
LU
; Poettgen, R.
LU
and Simpson, N.D.
LU
, et al.
(2024)
In Machine Learning: Science and Technology
5(3).
- Abstract
- 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... (More)
- 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. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/ce591da0-e81e-4223-8f44-e71d43e39f7e
- author
- Aad, G.
; Åkesson, T.P.A.
LU
; Doglioni, C.
LU
; Ekman, P.A.
LU
; Hedberg, V.
LU
; Herde, H.
LU
; Konya, B.
LU
; Lytken, E.
LU
; Poettgen, R.
LU
and Simpson, N.D.
LU
, et al. (More)
- Aad, G.
; Åkesson, T.P.A.
LU
; Doglioni, C.
LU
; Ekman, P.A.
LU
; Hedberg, V.
LU
; Herde, H.
LU
; Konya, B.
LU
; Lytken, E.
LU
; Poettgen, R.
LU
; Simpson, N.D.
LU
; Smirnova, O.
LU
; Wallin, E.J.
LU
and Zwalinski, L.
(Less)
- author collaboration
- organization
- publishing date
- 2024
- type
- Contribution to journal
- publication status
- published
- subject
- 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
- in
- Machine Learning: Science and Technology
- volume
- 5
- issue
- 3
- article number
- 035051
- publisher
- IOP Publishing
- external identifiers
-
- scopus:85203423356
- ISSN
- 2632-2153
- DOI
- 10.1088/2632-2153/ad611e
- language
- English
- LU publication?
- yes
- id
- ce591da0-e81e-4223-8f44-e71d43e39f7e
- date added to LUP
- 2024-10-11 11:51:34
- date last changed
- 2025-04-04 15:06:52
@article{ce591da0-e81e-4223-8f44-e71d43e39f7e,
abstract = {{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 = {{Aad, G. and Åkesson, T.P.A. and Doglioni, C. and Ekman, P.A. and Hedberg, V. and Herde, H. and Konya, B. and Lytken, E. and Poettgen, R. and Simpson, N.D. and Smirnova, O. and Wallin, E.J. and Zwalinski, L.}},
issn = {{2632-2153}},
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}},
language = {{eng}},
number = {{3}},
publisher = {{IOP Publishing}},
series = {{Machine Learning: Science and Technology}},
title = {{Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network}},
url = {{http://dx.doi.org/10.1088/2632-2153/ad611e}},
doi = {{10.1088/2632-2153/ad611e}},
volume = {{5}},
year = {{2024}},
}