Performance of a geometric deep learning pipeline for HL-LHC particle tracking

@article{Ju2021PerformanceOA,
  title={Performance of a geometric deep learning pipeline for HL-LHC particle tracking},
  author={Xiangyang Ju and Daniel Murnane and Paolo Calafiura and Nicholas Choma and Sean Conlon and Steven Andrew Farrell and Yaoyuan Xu and Maria Spiropulu and J. R. Vlimant and Adam Aurisano and Jeremy Hewes and Giuseppe Cerati and Lindsey Gray and Thomas Klijnsma and Jim Kowalkowski and Markus Atkinson and Mark S. Neubauer and Gage DeZoort and Savannah Thais and Aditi Chauhan and Alex Schuy and Shih-Chieh Hsu and Alexandra Ballow and Alina Lazar},
  journal={The European Physical Journal C},
  year={2021}
}
The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. Exa.TrkX’s tracking pipeline groups detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity Calorimeter. This paper documents new… Expand
1 Citations

Figures and Tables from this paper

Charged Particle Tracking via Edge-Classifying Interaction Networks
TLDR
This work adapts the physics-motivated interaction network (IN) GNN toward the problem of particle tracking in pileup conditions similar to those expected at the high-luminosity Large Hadron Collider, and demonstrates the IN’s excellent edge-classification accuracy and tracking efficiency through a suite of measurements at each stage of GNN-based tracking. Expand

References

SHOWING 1-10 OF 71 REFERENCES
The HEP.TrkX Project: Deep Learning for Particle Tracking
TLDR
The evolution and performance of recurrent (LSTM) and convolutional neural networks moving from basic 2D models to more complex models and the challenges of scaling up to realistic dimensionality/sparsity are presented. Expand
The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking
TLDR
This contribution will describe the initial explorations into this relatively unexplored idea space of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data. Expand
Novel deep learning methods for track reconstruction
For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew inspiration fromExpand
Beyond 4D tracking: using cluster shapes for track seeding
TLDR
This work uses neural networks to show that cluster shapes can reduce significantly the rate of fake combinatorical backgrounds while preserving a high efficiency using the information in cluster singlets, doublets and triplets. Expand
Towards a realistic track reconstruction algorithm based on graph neural networks for the HL-LHC
The physics reach of the HL-LHC will be limited by how efficiently the experiments can use the available computing resources, i.e. affordable software and computing are essential. The development ofExpand
Parallel track reconstruction in CMS using the cellular automaton approach
TLDR
A new cellular automaton based track reconstruction, which copes with the complex detector geometry of CMS, is presented and it is shown that a significant speedup can be attained by using GPU architectures while achieving a reasonable physics performance at the same time. Expand
arXiv : Comparison of two hardware-based hit filtering methods for trackers in high-pileup environments
TLDR
A comparison of two methods for filtering detector hits to be used for triggering on particle tracks: one based on a pattern matching technique using Associative Memory (AM) chips and the other based on the Hough transform, which finds that, while both methods are feasible options for an efficient track trigger, the AM based pattern matching produces a lower number of hit combinations whilst keeping more of the true signal hits. Expand
DeepCore: Convolutional Neural Network for high $p_T$ jet tracking
Tracking in high-density environments, such as the core of TeV jets, is particularly challenging both because combinatorics quickly diverge and because tracks may not leave anymore individual "hits"Expand
The Tracking Machine Learning Challenge: Accuracy Phase
This paper reports the results of an experiment in high energy physics: using the power of the “crowd” to solve difficult experimental problems linked to tracking accurately the trajectory ofExpand
Description and performance of track and primary-vertex reconstruction with the CMS tracker
A description is provided of the software algorithms developed for the CMS tracker both for reconstructing charged-particle trajectories in proton-proton interactions and for using the resultingExpand
...
1
2
3
4
5
...