Beyond 4D Tracking: Using Cluster Shapes for Track Seeding

TL;DR

This paper introduces a novel track seeding method at the LHC that leverages cluster shape information, processed via neural networks, to reduce fake backgrounds and improve efficiency in event reconstruction.

Contribution

It proposes using cluster shape data, previously underutilized, with neural networks to enhance track seeding accuracy at the LHC.

Findings

Cluster shape information significantly reduces fake track candidates.

Neural networks effectively distinguish true tracks from background.

Method maintains high efficiency while lowering combinatorial background.

Abstract

Tracking is one of the most time consuming aspects of event reconstruction at the Large Hadron Collider (LHC) and its high-luminosity upgrade (HL-LHC). Innovative detector technologies extend tracking to four-dimensions by including timing in the pattern recognition and parameter estimation. However, present and future hardware already have additional information that is largely unused by existing track seeding algorithms. The shape of clusters provides an additional dimension for track seeding that can significantly reduce the combinatorial challenge of track finding. We use neural networks to show that cluster shapes can reduce significantly the rate of fake combinatorical backgrounds while preserving a high efficiency. We demonstrate this using the information in cluster singlets, doublets and triplets. Numerical results are presented with simulations from the TrackML challenge.