为麦克斯韦方程从噪声数据学习导数算子的能耗稳定方法
An Energy Stable Approach for Learning Derivative Operators from Noisy Data for Maxwells Equations
AI总结:
本文提出SP-ADMM方法,通过减少参数化学习能量稳定的导数算子,保持能量守恒,适用于噪声数据和隐含算子场景。
摘要:
我们开发了一种结构保持的ADMM方法(SP-ADMM),用于从噪声数据中学习麦克斯韦方程的能量稳定的空间导数卷积算子。从无源麦克斯韦系统出发,我们关注一维简化系统,其能量守恒依赖于空间导数算子的斜反对称性。所学导数表示为紧凑的周期卷积算子。与标准约束ADMM不同,后者学习完整算子并通过等式约束施加斜反对称性,SP-ADMM通过减少参数化仅使用独立正侧算子系数来强制斜反对称性。数值实验显示,SP-ADMM在隐含算子和噪声数据情况下特别有效。在清洁数据、噪声导数数据、多种初始条件、不同隐含斜反对称算子、训练集大小、正则化参数、约束消解和长时间模拟中,SP-ADMM实现了最小的最终时间电场误差,同时保持能量到舍入精度。层状介质麦克斯韦传播测试进一步表明,所学的结构保持卷积算子在物理反射/传输设置中与经典有限差分方法具有竞争力。总体而言,SP-ADMM提供了一种数据驱动的方法来学习准确的麦克斯韦卷积算子,同时保留底层方程的能量守恒结构。
英文摘要:
We develop a structure-preserving ADMM method, denoted SP-ADMM, for learning energy-stable spatial derivative stencils for Maxwell equations from noisy data. Starting from the source-free Maxwell system, we focus on a one-dimensional reduction whose energy conservation depends on the skew-adjointness of the spatial derivative operator. The learned derivative is represented by a compact periodic convolution stencil. Unlike standard constrained ADMM, which learns the full stencil and imposes skew-adjointness through equality constraints, SP-ADMM enforces skew-adjointness by construction through a reduced parameterization using only the independent positive-side stencil coefficients. Numerical experiments show that SP-ADMM is especially effective in hidden operator and noisy-data regimes. Across clean data, noisy derivative data, multiple initial conditions, different hidden skew-adjoint operators, training-set sizes, regularization parameters, constraint ablations, and long-time simulations, SP-ADMM achieves the smallest final-time electric-field error while preserving energy to roundoff accuracy. A layered-medium Maxwell propagation test further shows that the learned structure-preserving stencil remains competitive with classical finite differences in a physical reflection/transmission setting. Overall, SP-ADMM provides a data-driven way to learn accurate Maxwell stencils while retaining the energy-conserving structure of the underlying equations.
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。