SciPost Phys. 19, 155 (2025) ·
published 16 December 2025
|
· pdf
The ATLAS experiment at the Large Hadron Collider explores the use of modern neural networks for a multi-dimensional calibration of its calorimeter signal defined by clusters of topologically connected cells (topo-clusters). The Bayesian neural network (BNN) approach not only yields a continuous and smooth calibration function that improves performance relative to the standard calibration but also provides uncertainties on the calibrated energies for each topo-cluster. The results obtained by using a trained BNN are compared to the standard local hadronic calibration and to a calibration provided by training a deep neural network. The uncertainties predicted by the BNN are interpreted in the context of a fractional contribution to the systematic uncertainties of the trained calibration. They are also compared to uncertainty predictions obtained from an alternative estimator employing repulsive ensembles.
SciPost Phys. Proc. 8, 171 (2022) ·
published 14 July 2022
|
· pdf
The Tile Calorimeter (TileCal) is a sampling calorimeter that forms the central region of the hadronic calorimeter of the ATLAS experiment. This sub-detector is to undergo its Phase-II upgrade during long-shutdown 3, in the years from 2025 to mid 2027, in preparation for the start of operation of the High Luminosity Large Hadron Collider (HL-LHC) in 2027. In this proceeding, an overview of the TileCal HL-LHC on-detector electronics upgrade is provided. The detectors Run-II performance in the cases of EM scale calibration, calorimeter response, cell energy distribution and noise as well as a portion of the 2015-2018 Test-beam campaigns results are examined.
