arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12706cs.LG
收藏

基于物理的拉普拉斯神经算子用于求解偏微分方程

Physics-Informed Laplace Neural Operator for Solving Partial Differential Equations

Department of Mathematics, Pohang University of Science and Technology (POSTECH)(POSTECH数学系);Division of Applied Mathematics, Brown University(布朗大学应用数学系);Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院机械工程系)

Heechang Kim, Qianying Cao, Hyomin Shin, Seungchul Lee, George Em Karniadakis, Minseok Choi

AI总结:

PILNO通过整合物理约束提升神经算子在求解偏微分方程时的准确性和鲁棒性,尤其在小数据和分布外场景下表现更优。

摘要:

神经算子已逐渐成为参数偏微分方程(PDEs)的快速替代求解器。然而,纯数据驱动的模型通常需要大量的训练数据,并且在小数据情况下泛化能力较差,尤其是在训练数据中未表示的(分布外)输入函数下表现不佳。为了解决这些限制,我们提出了基于物理的拉普拉斯神经算子(PILNO),通过嵌入偏微分方程、边界条件和初始条件残差将物理规律纳入训练中。为了提高表达能力,我们首先引入了先进的LNO(ALNO)主干,保留了极子-余数瞬态表示,同时用FNO风格的傅里叶乘法器替代了稳态分支。为了使基于物理的训练既数据高效又鲁棒,PILNO进一步利用(i)虚拟输入:一个未标记的输入函数集合,覆盖广泛的频谱范围,提供丰富的物理监督,并明确针对分布外(OOD)领域;以及(ii)时间因果性加权:对物理残差进行时间衰减的重新加权,优先考虑早期时间动态,并稳定时间依赖PDE的优化。在四个代表性基准测试中——Burgers方程、达西流、反应扩散系统以及受迫KdV方程——PILNO在小数据设置(例如N_train <= 27)中一致提高了准确性,减少了随机种子之间的运行变化,并在纯数据驱动基线中实现了更强的分布外泛化能力。

英文摘要:

Neural operators have emerged as fast surrogate solvers for parametric partial differential equations (PDEs). However, purely data-driven models often require extensive training data and can generalize poorly, especially in small-data regimes and under unseen (out-of-distribution) input functions that are not represented in the training data. To address these limitations, we propose the Physics-Informed Laplace Neural Operator (PILNO), which enhances the Laplace Neural Operator (LNO) by embedding governing physics into training through PDE, boundary condition, and initial condition residuals. To improve expressivity, we first introduce an Advanced LNO (ALNO) backbone that retains a pole-residue transient representation while replacing the steady-state branch with an FNO-style Fourier multiplier. To make physics-informed training both data-efficient and robust, PILNO further leverages (i) virtual inputs: an unlabeled ensemble of input functions spanning a broad spectral range that provides abundant physics-only supervision and explicitly targets out-of-distribution (OOD) regimes; and (ii) temporal-causality weighting: a time-decaying reweighting of the physics residual that prioritizes early-time dynamics and stabilizes optimization for time-dependent PDEs. Across four representative benchmarks -- Burgers' equation, Darcy flow, a reaction-diffusion system, and a forced KdV equation -- PILNO consistently improves accuracy in small-data settings (e.g., N_train <= 27), reduces run-to-run variability across random seeds, and achieves stronger OOD generalization with respect to input function statistics than purely data-driven baselines.

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。

↑