Contributor info: Prof. Cunfeng Feng

ATLAS Collaboration

SciPost Phys. 19, 155 (2025) · published 16 December 2025 | Toggle abstract · 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.

Xiaoting Feng, Hengying Zhang, Cunfeng Feng, Lingling Ma on behalf of the LHAASO Collaboration

SciPost Phys. Proc. 13, 017 (2023) · published 28 September 2023 | Toggle abstract · pdf

LHAASO KM2A consists of 5915 scintillation detectors and 1188 muon detectors, and the muon detectors cover 4% area of the whole array with 30 m interdetector spacing. The muon number in air shower events, with very high energy, is investigated with the data recorded by muon detector of the 3/4 LHAASO array in 2021. The attenuation length of muon number in the air shower is measured by fitting the muon number with constant flux in various zenith angles, based on the constant intensity cut method. The variation of the attenuation length as shower energy from hundreds TeV to tens PeV is presented. The results of simulation also is presented for comparing.