arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04883nlin.PScs.LG
收藏

使用可分离高斯神经网络学习行进孤立波

Learning Traveling Solitary Waves Using Separable Gaussian Neural Networks

California Polytechnic State University(加州州立理工大学)

Siyuan Xing, Efstathios G. Charalampidis

AI总结:

本研究提出将新型可分离高斯神经网络(SGNN)融入物理信息神经网络(PINNs)框架,通过转换至共行波坐标系解决大域传播失效问题,以极少神经元实现了多类偏微分方程孤立波解的高精度逼近。

摘要:

本文采用机器学习方法学习各类偏微分方程(PDE)族中的行进孤立波。我们将一种名为可分离高斯神经网络(Separable Gaussian Neural Networks, SGNN)的新型可解释神经网络(NN)架构融入物理信息神经网络(Physics-Informed Neural Networks, PINNs)框架。与将时空数据作为独立输入处理的传统PINNs不同,本方法利用波动特性将数据转换至所谓的共行波坐标系,这一调整有效解决了PINNs应用于大计算域时的传播失效问题。实验中,SGNN架构对(1+1)维b族PDE中的单峰子、多峰子及静态解均展现出稳健的逼近能力。此外,我们拓展了研究范围,不仅探究了ab族中的峰子解,还研究了(2+1)维Rosenau-Hyman族PDE中的紧子解。与多层感知机(MLP)的对比分析表明,SGNN在神经元数量不足十分之一的情况下即可达到相当的精度,凸显了其高效性及在求解复杂非线性PDE方面更广泛的应用潜力。

英文摘要:

In this paper, we apply a machine-learning approach to learn traveling solitary waves across various families of partial differential equations (PDEs). Our approach integrates a novel interpretable neural network (NN) architecture, called Separable Gaussian Neural Networks (SGNN) into the framework of Physics-Informed Neural Networks (PINNs). Unlike the traditional PINNs that treat spatial and temporal data as independent inputs, the present method leverages wave characteristics to transform data into the so-called co-traveling wave frame. This adaptation effectively addresses the issue of propagation failure in PINNs when applied to large computational domains. Here, the SGNN architecture demonstrates robust approximation capabilities for single-peakon, multi-peakon, and stationary solutions within the (1+1)-dimensional, $b$-family of PDEs. In addition, we expand our investigations, and explore not only peakon solutions in the $ab$-family but also compacton solutions in (2+1)-dimensional, Rosenau-Hyman family of PDEs. A comparative analysis with MLP reveals that SGNN achieves comparable accuracy with fewer than a tenth of the neurons, underscoring its efficiency and potential for broader application in solving complex nonlinear PDEs.

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。

↑