arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.05512cs.LGphysics.comp-ph
收藏

偏微分方程解算子的单样本学习

One-shot learning for solution operators of partial differential equations

Yale University(耶鲁大学);Ansys Inc.(安sys公司);Wu Tsai Institute(蔡崇信研究所)

Anran Jiao, Haiyang He, Rishikesh Ranade, Jay Pathak, Lu Lu

AI总结:

本文提出首个仅需一个PDE解的单样本解算子学习方法,通过局部解算子与神经网络及FPI、LOINN、cLOINN等策略,在多种PDE上验证了有效性和泛化能力。

摘要:

从数据中学习和求解以偏微分方程(PDEs)表示的物理系统控制方程,是众多科学与工程领域中的核心挑战。传统的PDE数值求解方法对于复杂系统可能计算代价高昂,并且需要完整的物理系统PDE。另一方面,当前数据驱动的机器学习方法需要大量数据来学习PDE解算子的代理模型,这在实际中可能不可行。在此,我们提出首个仅需一个PDE解的解算子学习方法,即单样本学习。通过利用PDE的局部性原理,我们考虑小的局部域而非整个计算域,并定义局部解算子。随后使用神经网络训练该局部解算子,并利用其通过基于网格的不动点迭代(FPI)、无网格局部解算子信息神经网络(LOINN)或带修正的局部解算子信息神经网络(cLOINN)来预测新输入函数的解。我们在多种PDE上测试了我们的方法,包括线性或非线性PDE、定义在复杂几何上的PDE以及PDE系统,证明了我们的方法在这些不同场景下的有效性和泛化能力。

英文摘要:

Learning and solving governing equations of a physical system, represented by partial differential equations (PDEs), from data is a central challenge in a variety of areas of science and engineering. Traditional numerical methods for solving PDEs can be computationally expensive for complex systems and require the complete PDEs of the physical system. On the other hand, current data-driven machine learning methods require a large amount of data to learn a surrogate model of the PDE solution operator, which could be impractical. Here, we propose the first solution operator learning method that only requires one PDE solution, i.e., one-shot learning. By leveraging the principle of locality of PDEs, we consider small local domains instead of the entire computational domain and define a local solution operator. The local solution operator is then trained using a neural network, and utilized to predict the solution of a new input function via mesh-based fixed-point iteration (FPI), meshfree local-solution-operator informed neural network (LOINN) or local-solution-operator informed neural network with correction (cLOINN). We test our method on diverse PDEs, including linear or nonlinear PDEs, PDEs defined on complex geometries, and PDE systems, demonstrating the effectiveness and generalization capabilities of our method across these varied scenarios.

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。

↑