Multi-nucleon transfer reaction between 136Xe beam and 198Pt target was performed using the VAMOS++ spectrometer at GANIL to study the structure of n-rich nuclei around N=126. Unambiguous charge state identification was obtained by combining two supervised machine learning methods, deep neural network (DNN) and positional correction using a gradient-boosting decision tree (GBDT). The new method reduced the complexity of the kinetic energy calibration and outperformed the conventional method, improving the charge state resolution by 8%
@article{arxiv.2311.07103,
title = {Particle Identification at VAMOS++ with Machine Learning Techniques},
author = {Y. Cho and Y. H. Kim and S. Choi and J. Park and S. Bae and K. I. Hahn and Y. Son and A. Navin and A. Lemasson and M. Rejmund and D. Ramos and D. Ackermann and A. Utepov and C. Fourgeres and J. C. Thomas and J. Goupil and G. Fremont and G. de France and Y. X. Watanabe and Y. Hirayama and S. Jeong and T. Niwase and H. Miyatake and P. Schury and M. Rosenbusch and K. Chae and C. Kim and S. Kim and G. M. Gu and M. J. Kim and P. John and A. N. Andreyev and W. Korten and F. Recchia and G. de Angelis and R. M. Pérez Vidal and K. Rezynkina and J. Ha and F. Didierjean and P. Marini and D. Treasa and I. Tsekhanovich and J. Dudouet and S. Bhattacharyya and G. Mukherjee and R. Banik and S. Bhattacharya and M. Mukai},
journal= {arXiv preprint arXiv:2311.07103},
year = {2023}
}