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, 126 (2022) ·
published 13 July 2022
|
· pdf
The ATLAS experiment at CERN’s Large Hadron Collider (LHC) will be upgraded in two stages to prepare first for the Run 3 data-taking campaign, during which the integrated luminosity will roughly double, and then for the High-Luminosity LHC program with an ultimate integrated luminosity of up to 4 ab-1. These upgrades and high-statistics datasets will allow ATLAS to perform searches and precision measurements to constrain the Standard Model in yet-unexplored phase spaces and in the Higgs sector. This contribution summarizes the ATLAS detector upgrades and selected physics prospects for Run 3 and the HL-LHC.
