End-to-end multi-particle reconstruction in high occupancy imaging calorimeters with graph neural networks

TL;DR

This paper introduces a novel end-to-end graph neural network-based algorithm for reconstructing multiple particles in high-occupancy calorimeters, achieving efficient and accurate results in complex high-luminosity conditions.

Contribution

It presents the first single-shot calorimetric reconstruction method for thousands of particles using graph neural networks with object condensation in high-luminosity environments.

Findings

High reconstruction efficiency and energy resolution.

Effective jet reconstruction performance.

Feasible inference computational cost.

Abstract

We present an end-to-end reconstruction algorithm to build particle candidates from detector hits in next-generation granular calorimeters similar to that foreseen for the high-luminosity upgrade of the CMS detector. The algorithm exploits a distance-weighted graph neural network, trained with object condensation, a graph segmentation technique. Through a single-shot approach, the reconstruction task is paired with energy regression. We describe the reconstruction performance in terms of efficiency as well as in terms of energy resolution. In addition, we show the jet reconstruction performance of our method and discuss its inference computational cost. To our knowledge, this work is the first-ever example of single-shot calorimetric reconstruction of ${\cal O}(1000)$ particles in high-luminosity conditions with 200 pileup.