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 2206.03439physics.comp-phcs.NAmath.NA
收藏

利用深度学习求解非局部 Fokker-Planck 方程

Solving Non-local Fokker-Planck Equations by Deep Learning

Senbao Jiang, Xiaofan Li

AI总结:

本文提出 trapz-PiNNs,将修正梯形法则融入物理信息神经网络,用于求解二维和三维空间分数阶 Fokker-Planck 方程,验证了二阶精度并在多个算例上展示了高精度预测能力。

摘要:

物理信息神经网络(PiNNs)近年来已成为在各类初边值条件下求解一大类偏微分方程的有力求解器。本文提出 trapz-PiNNs,即结合了最近为精确计算分数阶拉普拉斯算子而发展的修正梯形法则的物理信息神经网络,用于求解二维和三维空间分数阶 Fokker-Planck 方程。我们详细描述了修正梯形法则,并验证了其二阶精度。通过在多种数值算例上以较低的 $\mathcal{L}^2$ 相对误差预测解,我们证明了 trapz-PiNNs 具有很高的表达能力。我们还使用逐点绝对误差和相对误差等局部指标来分析哪些方面可以进一步改进。我们提出了一种有效方法,在可以获得真解高保真模拟的物理观测数据时,提升 trapz-PiNN 在局部指标上的性能。除了深度学习求解器通常具有的自适应性和网格无关性等优点外,trapz-PiNN 还能够求解具有任意 $α\in (0,2)$ 的分数阶拉普拉斯算子的偏微分方程,并且专门适用于矩形区域。它还具有推广到更高维度的潜力。

英文摘要:

Physics-informed neural networks (PiNNs) recently emerged as a powerful solver for a large class of partial differential equations under various initial and boundary conditions. In this paper, we propose trapz-PiNNs, physics-informed neural networks incorporated with a modified trapezoidal rule recently developed for accurately evaluating fractional laplacian and solve the space-fractional Fokker-Planck equations in 2D and 3D. We describe the modified trapezoidal rule in detail and verify the second-order accuracy. We demonstrate trapz-PiNNs have high expressive power through predicting solution with low $\mathcal{L}^2$ relative error on a variety of numerical examples. We also use local metrics such as pointwise absolute and relative errors to analyze where could be further improved. We present an effective method for improving performance of trapz-PiNN on local metrics, provided that physical observations of high-fidelity simulation of the true solution are available. Besides the usual advantages of the deep learning solvers such as adaptivity and mesh-independence, the trapz-PiNN is able to solve PDEs with fractional laplacian with arbitrary $α\in (0,2)$ and specializes on rectangular domain. It also has potential to be generalized into higher dimensions.

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。

↑