Cluster Counting Algorithm for the CEPC Drift Chamber using LSTM and DGCNN

Abstract

The particle identification (PID) of hadrons plays a crucial role in particle physics experiments, especially in flavor physics and jet tagging. The cluster-counting method, which measures the number of primary ionizations in gaseous detectors, is a promising breakthrough in PID. However, developing an effective reconstruction algorithm for cluster counting remains challenging. To address this challenge, we propose a cluster-counting algorithm based on long short-term memory and dynamic graph convolutional neural networks for the CEPC drift chamber. Experiments on Monte Carlo simulated samples demonstrate that our machine-learning-based algorithm surpasses traditional methods. It improves the $K/\pi$ separation of PID by 10\%, meeting the PID requirements of CEPC.

11 pages, 10 figures

References in corpus (15)

• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
• Neural Message Passing for Quantum Chemistry
• ParticleNet: Jet Tagging via Particle Clouds
• CEPC Conceptual Design Report: Volume 2 - Physics & Detector
• Precision Higgs Physics at CEPC
• Phase Transition Study meets Machine Learning
• Interfacing Geant4, Garfield++ and Degrad for the Simulation of Gaseous Detectors
• Analysis of $B_c\to \tau {\nu }_{\tau }$ at CEPC
• Search for invisible decay of a Higgs boson produced at the CEPC
• Measurements of decay branching fractions of $H\to b\bar{b}/c\bar{c}/gg$ in associated $(e^{+}{e}^{-}/{\mu }^{+}{\mu }^{-})H$ production at the CEPC
• Requirement analysis for dE/dx measurement and PID performance at the CEPC baseline detector
• Peak finding algorithm for cluster counting with domain adaptation
• Particle identification with the cluster counting technique for the IDEA drift chamber
• Simulation study of particle identification using cluster counting technique for the BESIII drift chamber
• Higgs to $\tau \tau$ analysis in the future $e^{+}{e}^{-}$ Higgs factories