Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 91: Methods in Particle Physics V

T 91.3: Vortrag

Freitag, 20. März 2026, 09:30–09:45, KH 00.020

Calibration of calorimeter signals in theATLAS experiment using an uncertainty-awareneural network — •Isabel Sainz Saenz-Diez — Kirchhoff Institute for Physics, Heidelberg University

The measurement of energy deposits in the calorimeters is a key aspect of particle reconstruction. In the case of the ATLAS experiment at the Large Hadron Collider (LHC), the calorimeter signals are reconstructed as clusters of topologically connected cells (topo-clusters) and need to be calibrated for energy losses that take part in hadronic showers and do not leave energy in the calorimeter cells. Machine Learning (ML) methods have been proposed in order to perform the hadronic calibration of the clusters. The talk will present the current status of the implementation and performance of a Deep Neural Network (DNN) which predicts both the energy of the clusters and its uncertainty. The impact of this new calibration in jet reconstruction and its outperformance with respect to the current calibration is discussed and both results at cluster-level and jet-level will be presented.