Multi-particle reconstruction in the High Granularity Calorimeter using object condensation and graph neural networks

TL;DR

This paper introduces an end-to-end machine learning approach using graph neural networks and object condensation to accurately reconstruct multiple particles in high-granularity calorimeter data, addressing challenges posed by high-luminosity LHC conditions.

Contribution

It presents a novel integrated method combining clustering, classification, and regression with GravNet GNNs and a new matching technique for particle shower reconstruction.

Findings

High reconstruction efficiency demonstrated

Effective handling of complex event environments

Promising direction for future research

Abstract

The high-luminosity upgrade of the LHC will come with unprecedented physics and computing challenges. One of these challenges is the accurate reconstruction of particles in events with up to 200 simultaneous proton-proton interactions. The planned CMS High Granularity Calorimeter offers fine spatial resolution for this purpose, with more than 6 million channels, but also poses unique challenges to reconstruction algorithms aiming to reconstruct individual particle showers. In this contribution, we propose an end-to-end machine-learning method that performs clustering, classification, and energy and position regression in one step while staying within memory and computational constraints. We employ GravNet, a graph neural network, and an object condensation loss function to achieve this task. Additionally, we propose a method to relate truth showers to reconstructed showers by maximising the energy weighted intersection over union using maximal weight matching. Our results show the efficiency of our method and highlight a promising research direction to be investigated further.