Machine-learning-based identification for initial clustering structure in relativistic heavy-ion collisions

Abstract

$\alpha$-clustering structure is a significant topic in light nuclei. A Bayesian convolutional neural network (BCNN) is applied to classify initial non-clustered and clustered configurations, namely Woods-Saxon distribution and three-$\alpha$ triangular (four-$\alpha$ tetrahedral) structure for ${}^{12}$C (${}^{16}$O), from heavy-ion collision events generated within a multi-phase transport (AMPT) model. Azimuthal angle and transverse momentum distributions of charged pions are taken as inputs to train the classifier. On multiple-event basis, the overall classification accuracy can reach $95\%$ for ${}^{12}$C/${}^{16}$O + ${}^{197}$Au events at $\sqrt{S_{NN}}=$ 200 GeV. With proper constructions of samples, the predicted deviations on mixed samples with different proportions of both configurations could be within $5\%$. In addition, setting a simple confidence threshold can further improve the predictions on the mixed dataset. Our results indicate promising and extensive possibilities of application of machine-learning-based techniques to real data and some other problems in physics of heavy-ion collisions.

arXiv comment12 pages, 11 figures; Accepted by Physical Review C

References in corpus (46)

• Deep Learning in Neural Networks: An Overview
• Machine learning phases of matter
• A Multi-Phase Transport Model for Relativistic Heavy Ion Collisions
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• HIJING 1.0: A Monte Carlo Program for Parton and Particle Production in High Energy Hadronic and Nuclear Collisions
• Learning phase transitions by confusion
• Formation of superdense hadronic matter in high energy heavy-ion collisions
• ZPC 1.0.1: a parton cascade for ultrarelativistic heavy ion collisions
• Ab initio calculation of the Hoyle state
• Structure and rotations of the Hoyle state
• Partonic effects on the elliptic flow at relativistic heavy ion collisions
• Structure of ground and excited states of ${}^{12}$C
• Evidence for Triangular D_3h Symmetry in 12C
• Elliptic flow in the Gaussian model of eccentricity fluctuations
• Elliptic and triangular flow in p+Pb and peripheral Pb+Pb collisions from parton scatterings
• Detection of phase transition via convolutional neural network
• Giant Dipole Resonance as a Fingerprint of $\alpha$ Clustering Configurations in ${}^{12}$C and ${}^{16}$O
• System-size independence of directed flow at the Relativistic Heavy-Ion Collider
• Anomalous chiral transports and spin polarization in heavy-ion collisions
• Predictions for $\sqrt{s_{NN}}=5.02$ TeV Pb+Pb Collisions from a Multi-Phase Transport Model
• Signatures of alpha clustering in light nuclei from relativistic nuclear collisions
• Di-hadron azimuthal correlation and Mach-like cone structure in parton/hadron transport model
• Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
• Nuclear cluster structure effect on elliptic and triangular flows in heavy-ion collisions
• Initial eccentricity fluctuations and their relation to higher-order flow harmonics
• Neural Networks for Impact Parameter Determination
• A machine learning study to identify spinodal clumping in high energy nuclear collisions
• Nuclear liquid-gas phase transition with machine learning
• Dipole oscillation modes in light $\alpha$-clustering nuclei
• $\alpha$-clustering effect on flows of direct photons in heavy-ion collisions
• Alpha clusters and collective flow in ultra-relativistic carbon - heavy nucleus collisions
• Photonuclear reaction as a probe for $\alpha$-clustering nuclei in the quasi-deuteron region
• Determining the temperature in heavy-ion collisions with multiplicity distribution
• Novel mechanism for electric quadrupole moment generation in relativistic heavy-ion collisions
• Dipole excitation of ${}^6$Li and ${}^9$Be studied with an extended quantum molecular dynamics model
• Clustering structure effect on Hanbury-Brown-Twiss correlation in ${}^{12}$C + ${}^{197}$Au collisions at 200 GeV}
• Two-proton momentum correlation from photondisintegration of $\alpha$-clustering light nuclei in the quasi-deuteron region
• Anisotropy fluctuation and correlation in central $\alpha$-clustered ${}^{12}$C+${}^{197}$Au collisions
• Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks
• Collective flows of $\alpha$-clustering ${}^{12}\mathrm{C}$ + ${}^{197}\mathrm{Au}$ by using different flow analysis methods
• Electromagnetic field from asymmetric to symmetric heavy ion collision at 200 GeV/c
• An efficient method for mapping the 12C+12C molecular resonances at low energies
• Thermal photons as a sensitive probe of $\alpha$-cluster in C+Au collisions at the BNL Relativistic Heavy Ion Collider
• Yield ratio of neutrons to protons in ${}^{12}C(d,n{)}^{13}$N and ${}^{12}C(d,p{)}^{13}$C from 0.6 MeV to 3 MeV
• Parton collisional effect on the conversion of geometry eccentricities into momentum anisotropies in relativistic heavy-ion collisions
• Predicting quantum many-body dynamics with transferable neural networks

Cited by in corpus (17)

• Machine Learning in Nuclear Physics
• Exploring QCD matter in extreme conditions with Machine Learning
• System dependence of away-side broadening and $\alpha$-clustering light nuclei structure effect in dihadron azimuthal correlations
• Effects of clustered nuclear geometry on the anisotropic flow in O-O collisions at the LHC within a multiphase transport model framework
• Constraining the Woods-Saxon potential in fusion reactions based on the neural network
• Short range correlations in the extended quantum molecular dynamics model
• Anisotropic flow fluctuation as a possible signature of clustered nuclear geometry in O-O collisions at the Large Hadron Collider
• System evolution of forward-backward multiplicity correlations in a multi-phase transport model
• Machine learning method for ${}^{12}$C event classification and reconstruction in the active target time-projection chamber
• Determination of impact parameter in high-energy heavy-ion collisions via deep learning
• Production and anisotropic flow of thermal photons in collision of $\alpha$-clustered carbon with heavy nuclei at relativistic energies
• Shell quenching in nuclear charge radii based on Monte Carlo dropout Bayesian neural network
• Role of clustered nuclear geometry in particle production through p-C and p-O collisions at the Large Hadron Collider
• Probing the sensitivity of anisotropic flow coefficients to the initial nuclear structure in pO and OO collisions at the LHC
• Probing Nuclear Geometry through Multi-Particle Azimuthal Correlations and Rapidity-Even Dipolar Flow in ${}^{16}$O+${}^{16}$O Collisions
• Jet momentum reconstruction in the QGP background with machine learning
• Further exploration of the machine-learning-based nuclear mass table