Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors

TLDR

Pattern recognition in high‑energy physics differs from traditional computer vision, requiring reconstruction algorithms to identify and measure particle kinematics in complex detector systems, with charged‑particle tracking and calorimeter shower reconstruction posing high‑dimensional, sparse, geometrically complex challenges that graph neural networks can address by incorporating domain knowledge into graph representations. The study demonstrates the applicability of GNNs to these two diverse particle reconstruction problems. The authors apply GNNs to charged‑particle trajectory and calorimeter shower reconstruction, using graph structures to model detector data.

Abstract

Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in high energy collisions and recorded with complex detector systems. Two critical applications are the reconstruction of charged particle trajectories in tracking detectors and the reconstruction of particle showers in calorimeters. These two problems have unique challenges and characteristics, but both have high dimensionality, high degree of sparsity, and complex geometric layouts. Graph Neural Networks (GNNs) are a relatively new class of deep learning architectures which can deal with such data effectively, allowing scientists to incorporate domain knowledge in a graph structure and learn powerful representations leveraging that structure to identify patterns of interest. In this work we demonstrate the applicability of GNNs to these two diverse particle reconstruction problems.