arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04923cs.LG
收藏

通过学习函数扩展对神经算子施加边界条件

Imposing Boundary Conditions on Neural Operators via Learned Function Extensions

Department of Mechanical and Process Engineering, ETH Zurich, Switzerland(机械与过程工程系,苏黎世联邦理工学院,瑞士);Seminar for Applied Mathematics, ETH Zurich, Switzerland(应用数学研讨会,苏黎世联邦理工学院,瑞士);ETH AI Center, Zurich, Switzerland(苏黎世联邦理工学院人工智能中心,瑞士)

Sepehr Mousavi, Siddhartha Mishra, Laura De Lorenzis

AI总结:

本文提出一种框架,通过函数扩展使神经算子能够处理复杂的非齐次边界条件,通过映射边界数据到潜在伪扩展,使标准算子学习架构能利用边界信息,从而提升对复杂边界条件和输入域函数的依赖学习能力。

摘要:

神经算子已显现为求解偏微分方程(PDEs)的强大替代方案,但其处理一般高度变化的边界条件(BCs)的能力仍然有限。现有方法在解算子对边界强迫敏感时往往失效。我们提出一种通用框架,通过函数扩展对神经算子施加复杂非齐次边界条件。我们的关键思想是将边界数据映射到整个空间域上的潜在伪扩展,使任何标准算子学习架构都能消费边界信息。所得到的算子,结合任意的域到域神经算子,可以同时学习复杂边界条件和输入域函数的丰富依赖性。为验证此设定,我们构建了18个具有挑战性的数据集,涵盖泊松、线弹性及超弹性问题,具有高度变化、混合型、分量级和多段边界条件的多样化几何体。我们的方法在多个数据集上均取得了最先进的准确性,超越基线方法,且无需超参数调优。总体而言,我们的结果表明,学习边界到域的扩展是一种有效且实用的策略,用于在现有神经算子框架中施加复杂的边界条件,从而为更广泛的PDE主导问题提供准确且稳健的科学机器学习模型。

英文摘要:

Neural operators have emerged as powerful surrogates for the solution of partial differential equations (PDEs), yet their ability to handle general, highly variable boundary conditions (BCs) remains limited. Existing approaches often fail when the solution operator exhibits strong sensitivity to boundary forcings. We propose a general framework for conditioning neural operators on complex non-homogeneous BCs through function extensions. Our key idea is to map boundary data to latent pseudo-extensions defined over the entire spatial domain, enabling any standard operator learning architecture to consume boundary information. The resulting operator, coupled with an arbitrary domain-to-domain neural operator, can learn rich dependencies on complex BCs and input domain functions at the same time. To benchmark this setting, we construct 18 challenging datasets spanning Poisson, linear elasticity, and hyperelasticity problems, with highly variable, mixed-type, component-wise, and multi-segment BCs on diverse geometries. Our approach achieves state-of-the-art accuracy, outperforming baselines by large margins, while requiring no hyperparameter tuning across datasets. Overall, our results demonstrate that learning boundary-to-domain extensions is an effective and practical strategy for imposing complex BCs in existing neural operator frameworks, enabling accurate and robust scientific machine learning models for a broader range of PDE-governed problems.

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。

↑