基于机器学习的相对论重离子碰撞初始团簇结构识别
Machine-learning-based identification for initial clustering structure in relativistic heavy-ion collisions
摘要：
$α$ -团簇结构是轻核研究的重要课题。应用贝叶斯卷积神经网络（BCNN）从多相输运（AMPT）模型内产生的重离子碰撞事件中对初始非聚类和聚类配置（即，$^{12}$ C（$^{16}$ O）的Woods-Saxon分布和三- $α$三角形（四- $α$四面体）结构）进行分类。以π介子的方位角和横向动量分布作为输入，对分类器进行训练。在多事例的基础上，对$\sqrt{S_{NN}} =$ 200 GeV的$^{12}$ C/ $^{16}$ O + $^{197}$ Au事例的分类精度可达$95\%$.通过合理的样品结构，两种构型不同比例的混合样品的预测偏差可以在$5\%$范围内。此外，设置一个简单的置信度阈值可以进一步提高对混合数据集的预测。我们的研究结果表明，基于机器学习的技术应用于实际数据和重离子碰撞物理中的一些其他问题的前景广阔的可能性。
英文摘要：
$α$-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-$α$ triangular (four-$α$ 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
