Applications of deep learning to relativistic hydrodynamics

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 $P({\epsilon }_n)$ (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.

arXiv comment7 pages, 4 figures

References in corpus (51)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Glauber Modeling in High Energy Nuclear Collisions
• Machine learning phases of matter
• Collective flow and viscosity in relativistic heavy-ion collisions
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• New Forms of QCD Matter Discovered at RHIC
• Learning phase transitions by confusion
• Elliptic and triangular flow in event-by-event (3+1)D viscous hydrodynamics
• Hydrodynamic Modeling of Heavy-Ion Collisions
• Event-by-event anisotropic flow in heavy-ion collisions from combined Yang-Mills and viscous fluid dynamics
• Causal viscous hydrodynamics in 2+1 dimensions for relativistic heavy-ion collisions
• Applying Bayesian parameter estimation to relativistic heavy-ion collisions: simultaneous characterization of the initial state and quark-gluon plasma medium
• 200 A GeV Au+Au collisions serve a nearly perfect quark-gluon liquid
• Alternative ansatz to wounded nucleon and binary collision scaling in high-energy nuclear collisions
• First Results from Pb+Pb collisions at the LHC
• Machine learning quantum phases of matter beyond the fermion sign problem
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Multi-system Bayesian constraints on the transport coefficients of QCD matter
• Machine Learning Topological Invariants with Neural Networks
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Parameterized Machine Learning for High-Energy Physics
• Effects of initial flow velocity fluctuation in event-by-event (3+1)D hydrodynamics
• Results from the Relativistic Heavy Ion Collider
• Effects of fluctuations on the initial eccentricity from the Color Glass Condensate in heavy ion collisions
• Phenomenological constraints on the transport properties of QCD matter with data-driven model averaging
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Constraining the Eq. of State of Super-Hadronic Matter from Heavy-Ion Collisions
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Pseudorapidity distribution and decorrelation of anisotropic flow within CLVisc hydrodynamics
• Eccentricity fluctuations from the Color Glass Condensate at RHIC and LHC
• Eccentricity fluctuation effects on elliptic flow in relativistic heavy ion collisions
• Regressive and generative neural networks for scalar field theory
• Collective flow in 2.76 A TeV and 5.02 A TeV Pb+Pb collisions
• Hydrodynamic Collectivity in Proton--Proton Collisions at 13 TeV
• Deep Learning Topological Invariants of Band Insulators
• Principal component analysis of event-by-event fluctuations
• Correlations of flow harmonics in 2.76A TeV Pb--Pb collisions
• A machine learning study to identify spinodal clumping in high energy nuclear collisions
• Subleading harmonic flows in hydrodynamic simulations of heavy ion collisions
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• High order flow harmonics of identified hadrons in 2.76 A TeV Pb+Pb collisions
• Massively parallel simulations of relativistic fluid dynamics on graphics processing units with CUDA
• Principal-component analysis of two-particle azimuthal correlations in PbPb and pPb collisions at CMS
• Causal Viscous Hydrodynamics for Relativistic Heavy Ion Collisions
• Principal Component Analysis of collective flow in Relativistic Heavy-Ion Collisions
• $p_T$-Dependent Particle Number Fluctuations From Principal Component Analyses in Hydrodynamic Simulations of Heavy-Ion Collisions
• Interpretable deep learning for nuclear deformation in heavy ion collisions
• Probing heavy ion collisions using quark and gluon jet substructure with machine learning
• Robustness of principal component analysis on harmonic flow in heavy ion collisions
• On feasibility of azimuthal flow studies with Principal Component Analysis

Cited by in corpus (10)

• Heavy quark potential in quark-gluon Plasma: Deep neural network meets lattice quantum chromodynamics
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• Reconstructing spectral functions via automatic differentiation
• Determination of impact parameter in high-energy heavy-ion collisions via deep learning
• Machine learning approach to analyze heavy quark diffusion coefficient in relativistic heavy-ion collisions
• Non-equilibrium cumulants within model A from crossover to first-order phase transition side
• Ultra fast, event-by-event heavy-ion simulations for next generation experiments
• Fast prediction of the hydrodynamic QGP evolution in ultra-relativistic heavy-ion collisions using Fourier Neural Operators
• Toward a foundation model for heavy-ion collision experiments based on point-cloud diffusion
• Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions