Speaker
Description
We present a data-driven deep learning framework for predicting multiple bulk observables in Au+Au collisions at RHIC energies. A single neural network is trained exclusively on experimental measurements of charged particle pseudorapidity density distributions, transverse momentum spectra and elliptic flow coefficients over a broad range of collision energies and centralities, without using simulation outputs as training targets. The network architecture is inspired by the stages of a heavy-ion collision, from the quark-gluon plasma to chemical and kinetic freeze-out, and employs locally connected hidden layers and a structured input design that encodes basic geometric and kinematic features of the system. We demonstrate that these physics-motivated choices significantly improve test performance compared to purely fully connected baselines. The trained model is then used to predict the above observables at RHIC energies, and the results are further cross-checked against the energy dependence of the total charged particle multiplicity per participant pair, as well as against a CLVisc hydrodynamic calculation with T\raisebox{-0.5ex}{R}ENTo initial conditions. Our findings indicate that such physics-guided neural networks can provide useful data-driven interpolation tools for RHIC observables in regions not currently covered by the available measurements, and can support further phenomenological studies.
