Speaker
Description
Accurately determining the nuclear equation of state (EoS) at finite baryon chemical potential ($\mu_B$) is crucial yet challenging in studying QCD matter under extreme conditions. This study develops a deep learning-assisted quasi-parton model using three deep neural networks. It reconstructs the QCD EoS at zero $\mu_B$ and predicts the EoS and transport coefficient $\eta/s$ at finite $\mu_B$. The model-derived EoS aligns well with lattice QCD results from Taylor expansion techniques. The minimum $\eta/s$ is about 175 MeV and decreases with increasing chemical potential within the confidence interval. This model offers a robust framework for understanding the QCD EoS at finite $\mu_B$ and provides essential input for relativistic hydrodynamic simulations of nuclear matter in heavy-ion collisions by the RHIC beam energy scan program.
