Precision calibration of calorimeter signals in the ATLAS experiment using an uncertainty-aware neural network

TL;DR

This paper presents a Bayesian neural network approach for calibrating calorimeter signals in the ATLAS experiment, offering improved accuracy and uncertainty estimation over traditional methods.

Contribution

It introduces a Bayesian neural network for multi-dimensional calorimeter calibration that provides both improved performance and uncertainty quantification.

Findings

BNN calibration outperforms standard local hadronic calibration.

BNN provides meaningful uncertainty estimates for each calibrated cluster.

Uncertainty predictions align with systematic uncertainty contributions.

Abstract

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.