학술논문
Particle Identification at VAMOS++ with Machine Learning Techniques
Document Type
Working Paper
Author
Cho, Y.; Kim, Y. H.; Choi, S.; Park, J.; Bae, S.; Hahn, K. I.; Son, Y.; Navin, A.; Lemasson, A.; Rejmund, M.; Ramos, D.; Ackermann, D.; Utepov, A.; Fourgeres, C.; Thomas, J. C.; Goupil, J.; Fremont, G.; de France, G.; Watanabe, Y. X.; Hirayama, Y.; Jeong, S.; Niwase, T.; Miyatake, H.; Schury, P.; Rosenbusch, M.; Chae, K.; Kim, C.; Kim, S.; Gu, G. M.; Kim, M. J.; John, P.; Andreyev, A. N.; Korten, W.; Recchia, F.; de Angelis, G.; Vidal, R. M. Pérez; Rezynkina, K.; Ha, J.; Didierjean, F.; Marini, P.; Treasa, D.; Tsekhanovich, I.; Dudouet, J.; Bhattacharyya, S.; Mukherjee, G.; Banik, R.; Bhattacharya, S.; Mukai, M.
Source
Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, Volume 541, August 2023, Pages 240-242
Subject
Language
Abstract
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%