A machine learning study on spinodal clumping in heavy ion collisions

Possible observables of baryon number clustering due to the instabilities occurring at a first order QCD phase transition are discussed. The dynamical formation clusters can be described by numerical fluid dynamics, augmented with gradient term and an equation state mechanically unstable region. It is shown that description this transition, in nuclear collisions, will lead dense boundary. State-of-the-art machine learning methods find coordinate space clumping leaves characteristic imprints on spatial net density distribution almost every event. On other hand momentum distributions do not show any clear event-by-event features. 'third order' cumulant, skewness, shows peak beam energy where system, created heavy ion collision, reaches deconfinement transition.