arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.16117nucl-thastro-ph.HEgr-qc
收藏

用物理信息神经网络求解BDNK扩散方程

Solving BDNK diffusion using physics-informed neural networks

Illinois Center for Advanced Studies of the Universe and Department of Physics, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校物理系及宇宙高级研究中心);Department of Physics, North Carolina State University(北卡罗来纳州立大学物理系)

Vicente Chomalí-Castro, Nick Clarisse, Nicki Mullins, Jorge Noronha

AI总结:

本文提出SA-PINN-ACTO框架,结合自适应PINN与边界条件精确处理,用于求解BDNK扩散方程并验证其在光滑与不连续初始条件下的性能。

摘要:

在本文中,我们将相对论性的BDNK(Bemfica-Disconzi-Noronha-Kovtun)扩散方程改写为守恒通量形式,并使用二阶Kurganov-Tadmor有限体积方案和物理信息神经网络(PINNs)在(1+1)维空间中求解。特别地,我们引入了SA-PINN-ACTO框架,该框架结合了自适应PINN技术,并通过网络原始输出的代数变换精确执行初始和周期性边界条件,使网络仅需最小化PDE残差。我们对光滑和不连续的初始数据进行了测试,包括平凡和动态演化的速度和温度BDNK背景,以及两种特征速度。SA-PINN-ACTO方法在光滑剖面中与收敛的Kurganov-Tadmor解匹配,而对于不连续剖面,误差增加,反映了PINNs在尖锐梯度附近预期的局限性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑