Classifying near-threshold enhancement using deep neural network

Abstract

One of the main issues in hadron spectroscopy is to identify the origin of threshold or near-threshold enhancement. Prior to our study, there is no straightforward way of distinguishing even the lowest channel threshold-enhancement of the nucleon-nucleon system using only the cross-sections. The difficulty lies in the proximity of either a bound or virtual state pole to the threshold which creates an almost identical structure in the scattering region. Identifying the nature of the pole causing the enhancement falls under the general classification problem and supervised machine learning using a feed-forward neural network is known to excel in this task. In this study, we discuss the basic idea behind deep neural network and how it can be used to identify the nature of the pole causing the enhancement. The applicability of the trained network can be explored by using an exact separable potential model to generate a validation dataset. We find that within some acceptable range of the cut-off parameter, the neural network gives high accuracy of inference. The result also reveals the important role played by the background singularities in the training dataset. Finally, we apply the method to nucleon-nucleon scattering data and show that the network was able to give the correct nature of pole, i.e. virtual pole for ${}^1{S}_0$ partial cross-section and bound state pole for ${}^3{S}_0$.

arXiv comment10 pages, 4 figures, Contribution to the Proceedings for 8th Asia-Pacific Conference on Few-Body Problems in Physics (APFB2020), March 1-5 2021, Kanazawa, Japan

References in corpus (17)

• Machine learning and the physical sciences
• Construction of high-quality Nucleon-Nucleon potential models
• Hadronic molecules
• Non-Standard Heavy Mesons and Baryons, an Experimental Review
• Observation of structure in the $J/\psi$-pair mass spectrum
• Threshold cusps and triangle singularities in hadronic reactions
• Study of the lineshape of the ${\chi }_{c1}(3872)$ state
• Machine and Deep Learning Applications in Particle Physics
• Explaining the Many Threshold Structures in the Heavy-Quark Hadron Spectrum
• Structure and compositeness of hadron resonances
• Heavy hadronic molecules with pion exchange and quark core couplings: a guide for practitioners
• ChainerMN: Scalable Distributed Deep Learning Framework
• Soft two-meson-exchange nucleon-nucleon potentials. I. Planar and crossed-box diagrams
• Soft two-meson-exchange nucleon-nucleon potentials. II. One-pair and two-pair diagrams
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• Classifying Pole of Amplitude Using Deep Neural Network
• Model independent analysis of coupled-channel scattering: a deep learning approach

Cited by in corpus (8)

• Machine Learning in Nuclear Physics
• Model independent analysis of coupled-channel scattering: a deep learning approach
• Identifying Hadronic Molecular States with a Neural Network
• Study of exotic hadrons with machine learning
• Interpretation of near-threshold peaks using the method of independent S-matrix poles
• Predicting the Masses of Exotic Hadrons with Data Augmentation Using Multilayer Perceptron
• Formulation of causality-preserving quantum time of arrival theory
• Learning Pole Structures of Hadronic States using Predictive Uncertainty Estimation