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. 10, 034 (2022) ·
published 11 August 2022
|
· pdf
The latest measurements of collective behaviour in a variety of collision systems with the ATLAS detector at the LHC, including pp collisions at 13 TeV, Xe+Xe collisions at 5.44 TeV, and Pb+Pb collisions at 5.02 TeV, are presented. They include vn-[pT] correlations, which carry important information about the initial-state geometry of the quark-gluon plasma and can shed light on any quadrupole deformation in the Xe nucleus, and measurements of flow decorrelations differential in rapidity, which probe the longitudinal structure of the colliding system. These measurements furthermore provide stringent tests of the theoretical understanding of the initial state in heavy ion collisions.
