Reconstruction of Large Radius Tracks with the Exa.TrkX pipeline

TL;DR

The paper presents the Exa.TrkX pipeline, an end-to-end machine learning approach that effectively reconstructs large radius tracks at the LHC, potentially enabling real-time new physics searches.

Contribution

It introduces a novel ML-based track finding pipeline that is agnostic to track positions and capable of reconstructing both prompt and large radius tracks simultaneously.

Findings

High efficiency in reconstructing large radius tracks

Simultaneous reconstruction of prompt and large radius tracks

Potential for real-time physics analysis

Abstract

Particle tracking is a challenging pattern recognition task at the Large Hadron Collider (LHC) and the High Luminosity-LHC. Conventional algorithms, such as those based on the Kalman Filter, achieve excellent performance in reconstructing the prompt tracks from the collision points. However, they require dedicated configuration and additional computing time to efficiently reconstruct the large radius tracks created away from the collision points. We developed an end-to-end machine learning-based track finding algorithm for the HL-LHC, the Exa.TrkX pipeline. The pipeline is designed so as to be agnostic about global track positions. In this work, we study the performance of the Exa.TrkX pipeline for finding large radius tracks. Trained with all tracks in the event, the pipeline simultaneously reconstructs prompt tracks and large radius tracks with high efficiencies. This new capability offered by the Exa.TrkX pipeline may enable us to search for new physics in real time.