标题： 一种新颖的深度学习方法用于探测核子-核子关联 显示英文标题

标题： A Novel Deep Learning Method for Detecting Nucleon-Nucleon Correlations

摘要： 本研究利用能标为$\sqrt{s_{\rm NN}}=3$GeV 的重离子碰撞的强子输运模型 SMASH，探讨核子-核子关联对重离子碰撞的影响，研究对象为$^{197}{\rm Au}$+$^{197}{\rm Au}$碰撞。 我们开发了一种创新的蒙特卡罗采样方法，该方法结合了单核子分布和核子-核子关联。 通过比较三种初始核结构配置——标准的Woods-Saxon分布（未校正，un-corr）、硬球排斥（阶梯校正，step corr）以及从头计算的核子-核子关联（nn-corr），我们发现除了超中央碰撞外，传统可观测量之间的差异极小。 当区分未校正(un-corr)与核子关联校正(nn-corr)配置时，传统的基于注意力机制的点云网络和多事件混合分类器未能成功（准确率约为50%）。 为了解决这一问题，我们开发了一种新型深度学习架构，集成了多事件统计和高维潜在空间特征相关性，整体分类准确率达到60%，对于中心碰撞则提升至70%。 此方法通过高维潜在空间中的统计分析提取微妙的核结构信号，为研究重离子碰撞中初始态核属性和夸克-胶子等离子体特性提供了新的范式。 它克服了传统单事件分析在检测初始态细微差异方面的局限性。 显示英文摘要

摘要： This study investigates the impact of nucleon-nucleon correlations on heavy-ion collisions using the hadronic transport model SMASH in $\sqrt{s_{\rm NN}}=3$ GeV $^{197}{\rm Au}$+$^{197}{\rm Au}$ collisions. We developed an innovative Monte Carlo sampling method that incorporates both single-nucleon distributions and nucleon-nucleon correlations. By comparing three initial nuclear configurations - a standard Woods-Saxon distribution (un-corr), hard-sphere repulsion (step corr), and ab initio nucleon-nucleon correlations (nn-corr)- we revealed minimal differences in traditional observables except for ultra-central collisions. When distinguishing between un-corr and nn-corr configurations, conventional attention-based point cloud networks and multi-event mixing classifiers failed (accuracy ~50%). To resolve this, we developed a novel deep learning architecture integrating multi-event statistics and high-dimensional latent space feature correlations, achieving 60\% overall classification accuracy, which improved to 70\% for central collisions. This method enables the extraction of subtle nuclear structure signals through statistical analysis in high-dimensional latent space, offering a new paradigm for studying initial-state nuclear properties and quark-gluon plasma characteristics in heavy-ion collisions. It overcomes the limitations of traditional single-event analysis in detecting subtle initial-state differences.