Development of machine learning analyses with graph neural network for the WASA-FRS experiment

被引：0

作者：

Ekawa, H. ^{[1
]}

Dou, W. ^{[1
,2
]}

Gao, Y. ^{[1
,3
,4
]}

He, Y. ^{[1
,5
]}

Kasagi, A. ^{[1
,6
]}

Liu, E. ^{[1
,3
,4
]}

Muneem, A. ^{[1
,7
]}

Nakagawa, M. ^{[1
]}

Rappold, C. ^{[8
]}

Saito, N. ^{[1
]}

Saito, T. R. ^{[1
,5
,9
]}

Taki, M. ^{[10
]}

Tanaka, Y. K. ^{[1
]}

Wang, H. ^{[1
]}

Yoshida, J. ^{[1
,11
]}

机构：

[1] RIKEN, High Energy Nucl Phys Lab, Cluster Pioneering Res, Wako, Japan

[2] Saitama Univ, Dept Phys, Saitama, Japan

[3] Chinese Acad Sci, Inst Modern Phys, Lanzhou, Peoples R China

[4] Univ Chinese Acad Sci, Beijing, Peoples R China

[5] Lanzhou Univ, Sch Nucl Sci & Technol, Lanzhou, Peoples R China

[6] Gifu Univ, Grad Sch Engn, Gifu, Japan

[7] Ghulam Ishaq Khan Inst Engn Sci & Technol, Fac Engn Sci, Topi, Pakistan

[8] CSIC, Inst Estruct Mat, Madrid, Spain

[9] GSI Helmholtz Ctr Heavy Ion Res, Darmstadt, Germany

[10] Rikkyo Univ, Grad Sch Artificial Intelligence & Sci, Tokyo, Japan

[11] Tohoku Univ, Dept Phys, Sendai, Japan

来源：

EUROPEAN PHYSICAL JOURNAL A | 2023年 / 59卷 / 05期

关键词：

BINDING-ENERGY VALUES; COLLISIONS;

D O I：

10.1140/epja/s10050-023-01016-5

中图分类号：

O57 [原子核物理学、高能物理学];

学科分类号：

070202 ;

摘要：

The WASA-FRS experiment aims to reveal the nature of light A hypernuclei with heavy-ion beams. The lifetimes of hypernuclei are measured precisely from their decay lengths and kinematics. To reconstruct a p(- )track emitted from hypernuclear decay, track finding is an important issue. In this study, a machine learning analysis method with a graph neural network (GNN), which is a powerful tool for deducing the connection between data nodes, was developed to obtain track associations from numerous combinations of hit information provided in detectors based on a Monte Carlo simulation. An efficiency of 98% was achieved for tracking p(-) mesons using the developed GNN model. The GNN model can also estimate the charge and momentum of the particles of interest. More than 99.9% of the negative charged particles were correctly identified with a momentum accuracy of 6.3%.

引用

页数：13