Applications of deep learning to relativistic hydrodynamics

TL;DR

This paper demonstrates that deep learning, specifically a stacked U-net neural network, can accurately predict the final states of relativistic hydrodynamics simulations, significantly speeding up event-by-event modeling of quark-gluon plasma evolution.

Contribution

The study introduces a deep neural network approach to predict relativistic hydrodynamics outcomes, offering a faster alternative to traditional simulation methods.

Findings

Neural network predictions match the magnitude and structures of final profiles.

The model accurately reproduces eccentricity distributions $P( ext{ε}_n)$ for n=2,3,4.

Deep learning captures key features of non-linear hydrodynamic evolution.

Abstract

Relativistic hydrodynamics is a powerful tool to simulate the evolution of the quark gluon plasma (QGP) in relativistic heavy ion collisions. Using 10000 initial and final profiles generated from 2+1-d relativistic hydrodynamics VISH2+1 with MC-Glauber initial conditions, we train a deep neural network based on stacked U-net, and use it to predict the final profiles associated with various initial conditions, including MC-Glauber, MC-KLN and AMPT and TRENTo. A comparison with the VISH2+1 results shows that the network predictions can nicely capture the magnitude and inhomogeneous structures of the final profiles, and nicely describe the related eccentricity distributions $P(\varepsilon_n)$ (n=2, 3, 4). These results indicate that deep learning technique can capture the main features of the non-linear evolution of hydrodynamics, showing its potential to largely accelerate the event-by-event simulations of relativistic hydrodynamics.