Cluster Counting Algorithm for Drift Chamber using LSTM and DGCNN

Particle identification (PID) of hadrons plays a crucial role in particle physics experiments, especially for flavor physics and jet tagging. The cluster counting method, which measures the number of primary ionizations in gaseous detectors, represents a promising breakthrough in PID. However, developing an effective reconstruction algorithm for cluster counting remains a major challenge. In this study, we address this challenge by proposing a cluster counting algorithm based on long short-term memory and dynamic graph convolutional neural networks. Leveraging Monte Carlo simulated samples, our machine learning-based algorithm surpasses traditional methods. Specifically, it achieves a remarkable 10% improvement in K/π separation for PID performance.