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.
Highlights
Clustering is an extensively existing phenomenon in nuclei
We train a Bayesian convolutional neural network (BCNN) using the two-dimensional (2D) spectrum of azimuthal angle and transverse momentum to provide the information on the initial configuration of 12C / 16O
/ 16O + 197Au censimulated by the string melting a multiphase transport (AMPT) model
Summary
Clustering is an extensively existing phenomenon in nuclei. Especially in light nuclei, the mean field effect is not strong enough to break cluster structure, leading to possible observations of clustering behaviors in the excited states or even in the ground state. An obtuse triangular configuration of α clusters is predicted from an ab initio lattice simulation using effective field theory [9,10]. The later-discovered high-spin Jπ = 5− state fits well to the ground-state rotational band predicted by the algebraic cluster model (ACM). Because the final-state anisotropy can reflect initial geometry and modern neural networks are powerful tools for extracting information from complex datasets, we expect that they could learn more features from anisotropic distributions, which may offer new ways to solve the current limitations. We train a Bayesian convolutional neural network (BCNN) using the two-dimensional (2D) spectrum of azimuthal angle and transverse momentum to provide the information on the initial configuration of 12C / 16O.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
