arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02788cs.LGcs.AIphysics.comp-ph
收藏

保结构学习提升神经PDE在几何泛化中的表现

Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs

University of California, Berkeley(加州大学伯克利分校)

Benjamin D. Shaffer, Shawn Koohy, Brooks Kinch, M. Ani Hsieh, Nathaniel Trask

AI总结:

提出General-Geometry Neural Whitney Forms (Geo-NeW)方法,通过联合学习微分算子和兼容的降阶有限元空间,结合有限元外微积分精确保持物理守恒律,显著提升对未见几何域的泛化能力。

摘要:

我们旨在为科学和工程开发物理基础模型,这些模型能为偏微分方程(PDE)提供实时解,并在适应未见几何时保持结构和精度。为此,我们引入了通用几何神经Whitney形式(Geo-NeW):一种数据驱动的有限元方法。我们联合学习一个微分算子和定义在底层几何上的兼容降阶有限元空间。求解所得模型以生成预测,同时通过有限元外微积分精确保持物理守恒律。几何通过基于Transformer的编码和作为学习到的有限元空间的基础,以离散化网格的形式进入模型。这明确地将底层几何和施加的边界条件与解联系起来,为学习神经PDE提供了强大的归纳偏置,我们证明这改善了对未见域的泛化。我们提供了一种本构模型的新参数化,确保解的存在性和唯一性。我们的方法在几个稳态PDE基准测试中展示了最先进的性能,并在分布外几何上比传统基线有显著改进。

英文摘要:

We aim to develop physics foundation models for science and engineering that provide real-time solutions to Partial Differential Equations (PDEs) which preserve structure and accuracy under adaptation to unseen geometries. To this end, we introduce General-Geometry Neural Whitney Forms (Geo-NeW): a data-driven finite element method. We jointly learn a differential operator and compatible reduced finite element spaces defined on the underlying geometry. The resulting model is solved to generate predictions, while exactly preserving physical conservation laws through Finite Element Exterior Calculus. Geometry enters the model as a discretized mesh both through a transformer-based encoding and as the basis for the learned finite element spaces. This explicitly connects the underlying geometry and imposed boundary conditions to the solution, providing a powerful inductive bias for learning neural PDEs, which we demonstrate improves generalization to unseen domains. We provide a novel parameterization of the constitutive model ensuring the existence and uniqueness of the solution. Our approach demonstrates state-of-the-art performance on several steady-state PDE benchmarks, and provides a significant improvement over conventional baselines on out-of-distribution geometries.

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。

↑