Saved in:
Bibliographic Details
Main Authors: Chomalí-Castro, Vicente, Clarisse, Nick, Mullins, Nicki, Noronha, Jorge
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.16117
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915803827273728
author Chomalí-Castro, Vicente
Clarisse, Nick
Mullins, Nicki
Noronha, Jorge
author_facet Chomalí-Castro, Vicente
Clarisse, Nick
Mullins, Nicki
Noronha, Jorge
contents In this work, we reformulate the relativistic BDNK (Bemfica-Disconzi-Noronha-Kovtun) diffusion equation in flux-conservative form, and solve the resulting equations in $(1+1)$D using both a second-order Kurganov-Tadmor finite volume scheme and physics-informed neural networks (PINNs). In particular, we introduce the SA-PINN-ACTO framework, which combines the self-adaptive PINN technique with an exact enforcement of initial and periodic boundary conditions through an algebraic transform of the network's raw output, allowing the network to focus solely on minimizing the PDE residual. We test both approaches on smooth and discontinuous initial data, for both trivial and dynamically evolving velocity and temperature BDNK backgrounds, and for two characteristic speeds. The SA-PINN-ACTO method matches the converged Kurganov-Tadmor solutions for smooth profiles, while for discontinuous profiles the errors increase, reflecting an expected limitation of PINNs near sharp gradients.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16117
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Solving BDNK diffusion using physics-informed neural networks
Chomalí-Castro, Vicente
Clarisse, Nick
Mullins, Nicki
Noronha, Jorge
Nuclear Theory
High Energy Astrophysical Phenomena
General Relativity and Quantum Cosmology
In this work, we reformulate the relativistic BDNK (Bemfica-Disconzi-Noronha-Kovtun) diffusion equation in flux-conservative form, and solve the resulting equations in $(1+1)$D using both a second-order Kurganov-Tadmor finite volume scheme and physics-informed neural networks (PINNs). In particular, we introduce the SA-PINN-ACTO framework, which combines the self-adaptive PINN technique with an exact enforcement of initial and periodic boundary conditions through an algebraic transform of the network's raw output, allowing the network to focus solely on minimizing the PDE residual. We test both approaches on smooth and discontinuous initial data, for both trivial and dynamically evolving velocity and temperature BDNK backgrounds, and for two characteristic speeds. The SA-PINN-ACTO method matches the converged Kurganov-Tadmor solutions for smooth profiles, while for discontinuous profiles the errors increase, reflecting an expected limitation of PINNs near sharp gradients.
title Solving BDNK diffusion using physics-informed neural networks
topic Nuclear Theory
High Energy Astrophysical Phenomena
General Relativity and Quantum Cosmology
url https://arxiv.org/abs/2602.16117