WorksPhysics and Astronomy
Recurrent Fourier Neural Operator for Event-by-Event Relativistic Hydrodynamics
Abstract
Relativistic hydrodynamics is a powerful tool to simulate the evolution of the quark–gluon plasma (QGP) in relativistic heavy-ion collisions, but event-by-event simulations are computationally demanding, especially for Bayesian analyses. We develop a recurrent Fourier neural operator (rFNO) that emulates the evolution of -dimensional relativistic hydrodynamics. Three networks are trained on the , , and lattices using profiles of the same VISH2+1 hydrodynamic events up to . The networks trained on the coarser lattices are then directly evaluated on the lattice without retraining, while the network provides the native-resolution reference. A comparison with the VISH2+1 results shows that the rFNO predictions across resolutions nicely capture the magnitude and structures of the temperature profiles, and describe the event-by-event eccentricities (), the momentum anisotropy , and their time evolution within the supervised proper-time interval. After the recurrent continuation to , the relative errors of the predicted and remain within about . These results demonstrate that the rFNO realizes zero-shot super-resolution predictions for relativistic hydrodynamics and can be recurrently continued beyond the supervised interval.