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.cluster_counting_ml_codes:Python codes to train and test machine learning model for cluster counting. Including LSTM for peak finding and DGCNN for clusterization.samplesCERN ROOT files of simulation samples of waveforms of the signal in drift chamber cells.