Machine Learning for Particle Flow Reconstruction at CMS

Abstract

We provide details on the implementation of a machine-learning based particle flow algorithm for CMS. The standard particle flow algorithm reconstructs stable particles based on calorimeter clusters and tracks to provide a global event reconstruction that exploits the combined information of multiple detector subsystems, leading to strong improvements for quantities such as jets and missing transverse energy. We have studied a possible evolution of particle flow towards heterogeneous computing platforms such as GPUs using a graph neural network. The machine-learned PF model reconstructs particle candidates based on the full list of tracks and calorimeter clusters in the event. For validation, we determine the physics performance directly in the CMS software framework when the proposed algorithm is interfaced with the offline reconstruction of jets and missing transverse energy. We also report the computational performance of the algorithm, which scales approximately linearly in runtime and memory usage with the input size.

arXiv comment12 pages, 6 figures. Presented at the ACAT 2021: 20th International Workshop on Advanced Computing and Analysis Techniques in Physics Research, Daejeon, Kr, 29 Nov - 3 Dec 2021

References in corpus (25)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• A Brief Introduction to PYTHIA 8.1
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Dispelling the N^3 myth for the Kt jet-finder
• Particle-flow reconstruction and global event description with the CMS detector
• ParticleNet: Jet Tagging via Particle Clouds
• Jet reconstruction and performance using particle flow with the ATLAS Detector
• Pileup Per Particle Identification
• Graph Neural Networks in Particle Physics
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• JEDI-net: a jet identification algorithm based on interaction networks
• ABCNet: An attention-based method for particle tagging
• Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• The Tracking Machine Learning challenge : Accuracy phase
• Measurement of the Diffractive Structure Function F_2^D(4) at HERA
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• Towards a Computer Vision Particle Flow
• Measurement of sigma(ppbar -> Z + X) Br(Z -> tau+tau-) at sqrt(s)=1.96 TeV
• Reconstructing boosted Higgs jets from event image segmentation
• Hyperparameter optimization of data-driven AI models on HPC systems

Cited by in corpus (8)

• Reconstructing particles in jets using set transformer and hypergraph prediction networks
• HHH Whitepaper
• Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• Portable acceleration of CMS computing workflows with coprocessors as a service
• Set-Conditional Set Generation for Particle Physics
• Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders
• TIGER: A Topology-Agnostic, Hierarchical Graph Network for Event Reconstruction