arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.02871cs.LGmath-phmath.MPphysics.comp-ph
收藏

用于离子输运物理信息深度学习的注意力增强神经微分方程

Attention-enhanced neural differential equations for physics-informed deep learning of ion transport

Center for Computational Science and Engineering(计算科学与工程中心);Massachusetts Institute of Technology (MIT)(麻省理工学院)

Danyal Rehman, John H. Lienhard

AI总结:

本文提出结合电中性归纳偏置的注意力增强神经微分方程框架,用于建模纳米多孔膜中的离子输运,并验证其在泛化、离子配对关系揭示及复杂输运建模上优于传统 PDE 方法。

摘要:

物种输运模型通常将偏微分方程(PDE)与受阻输运理论中的关系相结合,以量化通过复杂纳米多孔系统的电迁移、对流和扩散输运;然而,这些公式往往是对主导动力学的大幅简化,导致基于 PDE 的模型泛化性能较差。鉴于人们对物理科学中深度学习方法的兴趣日益增长,我们开发了一种基于机器学习的方法,以表征离子跨纳米多孔膜的输运。我们提出的框架以注意力增强神经微分方程为核心,该方程结合了基于电中性的归纳偏置,以相对于传统基于 PDE 的方法提升泛化性能。此外,我们研究了注意力机制在揭示不同混合物组成中具有物理意义的离子配对关系方面的作用。进一步,我们考察了在基于 PDE 模型的模拟数据上进行预训练的重要性,以及硬归纳偏置与软归纳偏置带来的性能收益。我们的结果表明,物理信息深度学习解决方案可以优于其经典的基于 PDE 的对应方案,并为跨多种应用对复杂输运现象进行建模提供有前景的途径。

英文摘要:

Species transport models typically combine partial differential equations (PDEs) with relations from hindered transport theory to quantify electromigrative, convective, and diffusive transport through complex nanoporous systems; however, these formulations are frequently substantial simplifications of the governing dynamics, leading to the poor generalization performance of PDE-based models. Given the growing interest in deep learning methods for the physical sciences, we develop a machine learning-based approach to characterize ion transport across nanoporous membranes. Our proposed framework centers around attention-enhanced neural differential equations that incorporate electroneutrality-based inductive biases to improve generalization performance relative to conventional PDE-based methods. In addition, we study the role of the attention mechanism in illuminating physically-meaningful ion-pairing relationships across diverse mixture compositions. Further, we investigate the importance of pre-training on simulated data from PDE-based models, as well as the performance benefits from hard vs. soft inductive biases. Our results indicate that physics-informed deep learning solutions can outperform their classical PDE-based counterparts and provide promising avenues for modelling complex transport phenomena across diverse applications.

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。

↑