CERN Accelerating science

Article
Report number arXiv:2309.06782
Title Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors
Author(s) Pata, Joosep (NICPB, Tallinn) ; Wulff, Eric (CERN) ; Mokhtar, Farouk (UC, San Diego) ; Southwick, David (CERN) ; Zhang, Mengke (UC, San Diego) ; Girone, Maria (CERN) ; Duarte, Javier (UC, San Diego)
Publication 2024-04-10
Imprint 2023-09-13
Number of pages 21
Note 21 pages, 10 figures
In: Commun. Phys. 7 (2024) 124
DOI 10.1038/s42005-024-01599-5
Subject category stat.ML ; Mathematical Physics and Mathematics ; physics.ins-det ; Detectors and Experimental Techniques ; hep-ex ; Particle Physics - Experiment ; cs.LG ; Computing and Computers ; physics.data-an ; Other Fields of Physics
Abstract Efficient and accurate algorithms are necessary to reconstruct particles in the highly granular detectors anticipated at the High-Luminosity Large Hadron Collider and the Future Circular Collider. We study scalable machine learning models for event reconstruction in electron-positron collisions based on a full detector simulation. Particle-flow reconstruction can be formulated as a supervised learning task using tracks and calorimeter clusters. We compare a graph neural network and kernel-based transformer and demonstrate that we can avoid quadratic operations while achieving realistic reconstruction. We show that hyperparameter tuning significantly improves the performance of the models. The best graph neural network model shows improvement in the jet transverse momentum resolution by up to 50% compared to the rule-based algorithm. The resulting model is portable across Nvidia, AMD and Habana hardware. Accurate and fast machine-learning based reconstruction can significantly improve future measurements at colliders.
Copyright/License publication: © 2024 The Author(s) (License: CC-BY-4.0)
preprint: (License: CC BY 4.0)



Corresponding record in: Inspire


 Záznam vytvorený 2024-01-05, zmenený 2024-10-02


Plný text:
2309.06782 - Nahraj plný textPDF
document - Nahraj plný textPDF
  • Send to ScienceWise.info