Application of machine learning in the determination of impact parameter in the ${}^{132}$Sn+${}^{124}$Sn system

Abstract

Background: ${}^{132}$Sn+${}^{124}$Sn collisions at the beam energy of 270 MeV$/$nucleon have been performed at the Radioactive Isotope Beam Factory (RIBF) in RIKEN to investigate the nuclear equation of state. Reconstructing impact parameter is one of the important tasks in the experiment as it relates to many observables. Purpose: In this work, we employ three commonly used algorithms in machine learning, the artificial neural network (ANN), the convolutional neural network (CNN) and the light gradient boosting machine (LightGBM), to determine impact parameter by analyzing either the charged particles spectra or several features simulated with events from the ultra-relativistic quantum molecular dynamics (UrQMD) model. Method: To closely imitate experimental data and investigate the generalizability of the trained machine learning algorithms, incompressibility of nuclear equation of state and the in-medium nucleon-nucleon cross sections are varied in the UrQMD model to generate the training data. Results: The mean absolute error $\Delta b$ between the true and the predicted impact parameter is smaller than 0.45 fm if training and testing sets are sampled from the UrQMD model with the same parameter set. However, if training and testing sets are sampled with different parameter sets, $\Delta b$ would increase to 0.8 fm. Conclusion: The generalizability of the trained machine learning algorithms suggests that these machine learning algorithms can be used reliably to reconstruct impact parameter in experiment.

9 pages,9 figures

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Learning in Neural Networks: An Overview
• Towards Understanding Astrophysical Effects of Nuclear Symmetry Energy
• Systematics of Stopping and Flow in Au+Au Collisions
• Dynamics of clusters and fragments in heavy-ion collisions
• Transport approaches for the Description of Intermediate-Energy Heavy-Ion Collisions
• Symmetry energy investigation with pion production from Sn+Sn systems
• Progress of Quantum Molecular Dynamics model and its applications in Heavy Ion Collisions
• A fast centrality-meter for heavy-ion collisions at the CBM experiment
• Constraining the high-density behavior of nuclear equation of state from strangeness production in heavy-ion collisions
• UrQMD calculations of two-pion HBT correlations in central Pb-Pb collisions at $\sqrt{s_{NN}}=2.76$ TeV
• Network structure of thermonuclear reactions in nuclear landscape
• Topology of nuclear reaction networks of interest for astrophysics

Cited by in corpus (1)

• Impact of quadrupole deformation on intermediate-energy heavy-ion collisions