Recurrent Fourier Neural Operator for Event-by-Event Relativistic Hydrodynamics

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 $(2+1)$-dimensional relativistic hydrodynamics. Three networks are trained on the $32\times32$, $64\times64$, and $128\times128$ lattices using profiles of the same \textsc{VISH2+1} hydrodynamic events up to $τ-τ_0=4.8~\mathrm{fm}/c$. The networks trained on the coarser lattices are then directly evaluated on the $128\times128$ lattice without retraining, while the $128\times128$ network provides the native-resolution reference. A comparison with the \textsc{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 $\varepsilon_n$ ($n=2,3,4$), the momentum anisotropy $\varepsilon_p$, and their time evolution within the supervised proper-time interval. After the recurrent continuation to $τ-τ_0=6.4~\mathrm{fm}/c$, the relative errors of the predicted $\varepsilon_n$ and $\varepsilon_p$ remain within about $10\%$. These results demonstrate that the rFNO realizes zero-shot super-resolution predictions for relativistic hydrodynamics and can be recurrently continued beyond the supervised interval.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16511
Primary Topic
High-Energy Particle Collisions Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Recurrent Fourier Neural Operator for Event-by-Event Relativistic Hydrodynamics

Lingxiao Wang, Xiangrun Bao, Huichao Song
arXiv (Cornell University)
High-Energy Particle Collisions Research
preprint

Recurrent Fourier Neural Operator for Event-by-Event Relativistic Hydrodynamics

Lingxiao Wang, Xiangrun Bao, Huichao Song
preprint en

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 $(2+1)$-dimensional relativistic hydrodynamics. Three networks are trained on the $32\times32$, $64\times64$, and $128\times128$ lattices using profiles of the same \textsc{VISH2+1} hydrodynamic events up to $τ-τ_0=4.8~\mathrm{fm}/c$. The networks trained on the coarser lattices are then directly evaluated on the $128\times128$ lattice without retraining, while the $128\times128$ network provides the native-resolution reference. A comparison with the \textsc{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 $\varepsilon_n$ ($n=2,3,4$), the momentum anisotropy $\varepsilon_p$, and their time evolution within the supervised proper-time interval. After the recurrent continuation to $τ-τ_0=6.4~\mathrm{fm}/c$, the relative errors of the predicted $\varepsilon_n$ and $\varepsilon_p$ remain within about $10\%$. These results demonstrate that the rFNO realizes zero-shot super-resolution predictions for relativistic hydrodynamics and can be recurrently continued beyond the supervised interval.

arXiv (Cornell University)
High-Energy Particle Collisions Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon