A Novel Deep Learning Method for Detecting Nucleon-Nucleon Correlations

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.