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.
Federico Meloni on behalf of the LUXE collaboration
SciPost Phys. Proc. 12, 037 (2023) ·
published 4 July 2023
|
· pdf
The proposed LUXE experiment (LASER Und XFEL Experiment) at DESY, Hamburg, aims to probe QED in its non-perturbative regime. In order to do this, LUXE will study the interactions between 16.5 GeV electrons from the European XFEL and high-intensity laser pulses. This experiment also provides a unique opportunity to probe physics beyond the Standard Model: exploiting the large photon flux generated at LUXE, it is possible to design a dedicated detector to probe axion-like-particles up to a mass of 350 MeV and with photon coupling of $3 \cdot 10^{-6}$ GeV$^{-1}$. This reach is comparable to the projected sensitivity of experiments like FASER2 at the HL-LHC and NA62 operating in dump mode.