At the beginning of the 21st century, a new phase of strongly interacting matter, known as the
quark-gluon plasma (QGP), was established [1]. To study QGP formation in heavy-ion collisions,
the solution of system of relativistic hydrodynamics equations with a specific equation of state (EoS)
is typically employed. In light of difficulties for non-zero baryonic potentials within Lattice QCD,
various holographic models based on the AdS/CFT duality have been proposed to obtain the QGP
EoS from the thermodynamic properties of a corresponding black brane in AdS5 [2].
In this work, we discuss possible phenomenological approach for incorporating not only the
baryon chemical potential but also the quantum numbers of strangeness and charge into holographic
thermodynamics. The method proposed employs a phenomenological hypothesis inspired by the
thermodynamic dependencies of the hadron gas model. The Thermal FIST [3] package helps us to
find the definition for the full chemical potential, which behaves like a hadron gas in the characteristic
temperature range. We apply machine learning methods to address regression and optimization
problems during the calibration of the model’s free parameters using LQCD results for quark masses
that approximate the physical values [4]. For practical applications in heavy-ion collision studies,
the holographic EoS with strangeness and charge is incorporated into the hydrodynamical packages
MUSIC [5] and vHLLE [6].