Combined track finding with GNN & CKF

TL;DR

This paper introduces a hybrid approach combining Graph Neural Networks and the Classical Kalman Filter to improve track reconstruction in high-energy physics detectors, especially in outer detector regions with lower resolution.

Contribution

It presents a novel combination of GNN-based track finding with CKF to enhance performance across detector regions, leveraging the strengths of both methods.

Findings

GNN effectively identifies track candidates in the inner pixel region.

CKF improves track reconstruction in outer detector regions.

The combined method shows promising results in simulated high pile-up scenarios.

Abstract

The application of Graph Neural Networks (GNN) in track reconstruction is a promising approach to cope with the challenges arising at the High-Luminosity upgrade of the Large Hadron Collider (HL-LHC). GNNs show good track-finding performance in high-multiplicity scenarios and are naturally parallelizable on heterogeneous compute architectures. Typical high-energy-physics detectors have high resolution in the innermost layers to support vertex reconstruction but lower resolution in the outer parts. GNNs mainly rely on 3D space-point information, which can cause reduced track-finding performance in the outer regions. In this contribution, we present a novel combination of GNN-based track finding with the classical Combinatorial Kalman Filter (CKF) algorithm to circumvent this issue: The GNN resolves the track candidates in the inner pixel region, where 3D space points can represent measurements very well. These candidates are then picked up by the CKF in the outer regions, where the CKF performs well even for 1D measurements. Using the ACTS infrastructure, we present a proof of concept based on truth tracking in the pixels as well as a dedicated GNN pipeline trained on $t\bar{t}$ events with pile-up 200 in the OpenDataDetector.