26th Australian Institute of Physics Congress and the Australian and New Zealand Conference on Optics and Photonics

Graph Neural Networks for Calorimeter-Based Cluster Calibration at the ATLAS Experiment

Not scheduled

20m

Belinda Hutchinson Building (The University of Sydney )

Contributed Oral AIP | Nuclear and Particle Physics (NUPP)

Description

The ATLAS detector at the Large Hadron Collider measures the energy of particles using calorimeters. These are volumes segmented into many individual cells, each recording a small deposit of energy as a particle passes through. The cell-by-cell structure has a natural geometric and topological form which is well suited to graph neural networks (GNNs), a class of machine learning models designed to learn from data with irregular, connected structure rather than a fixed grid. In ATL-PHYS-PUB-2022-040, the ATLAS Collaboration showed that by using calorimeter information alone, GNNs can accurately perform calibration on topoclusters (groups of neighbouring cells formed by clustering algorithms to represent deposits from a single particle) originating from both neutral and charged pions.

This presentation extends that approach to topoclusters arising from more complex event topologies, including neutral hadrons and dijets (pairs of collimated particle sprays produced in high-energy collisions). It further applies the technique to partially-subtracted clusters, which arise in ParticleFlow, a reconstruction strategy that combines calorimeter and tracking-detector information to improve energy measurement by removing the contribution of charged particles already measured elsewhere. The resulting calibration scheme is a potential candidate for post-ParticleFlow calibration for the High-Luminosity LHC.