arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.03469math.NAcs.NA
收藏

模型误设定下基于物理引导的算子学习修正

Physics-guided correction for operator learning under model misspecification

Shanghai Normal University(上海师范大学);Imperial College London(帝国理工学院);Tongji University(同济大学);Shanghai Jiao Tong University(上海交通大学)

Lei Ma, Nicolas Boullé, Yu-Sen Yang, Hao Wu, Ling Guo

AI总结:

针对物理模型误设定问题,提出一种物理引导的算子修正框架,将目标算子分解为近似物理模型先验和可学习修正项,采用串行DeepONet架构实现,结合物理残差与数据一致性训练,有效降低误设定误差。

摘要:

物理信息算子学习通过结合观测数据与支配物理定律,为近似偏微分方程的解算子提供了一种高效框架。然而,现有方法大多隐含假设给定的支配方程是准确的。在实际应用中,模型简化、缺失物理效应、参数漂移或不完整的本构关系可能导致模型误设定,这一假设可能不成立。本文提出了一种物理引导的算子修正框架,用于在误设定支配方程下学习解算子。在算子层面,目标映射被分解为由近似物理模型诱导的先验算子和一个可学习的修正算子,后者负责处理剩余差异。尽管该公式与架构无关,我们使用串行DeepONet架构实现,其中第一个DeepONet提供先验预测,第二个DeepONet学习一个基于输入函数和先验预测的条件加性修正。学习到的修正被纳入物理残差,并与数据一致性约束一起训练,使模型在适应不准确支配方程的同时保留有用的物理结构。在扩散-反应、Burgers、空腔流动和超弹性问题上的数值实验表明,所提方法显著降低了由误设定物理引起的误差。在稀疏和噪声观测下的额外测试进一步证明了该框架的鲁棒性,以及通过深度集成提供信息性不确定性估计的能力。

英文摘要:

Physics-informed operator learning provides an efficient framework for approximating solution operators of partial differential equations by combining observational data with governing physical laws. However, most existing methods implicitly assume that the prescribed governing equation is accurate. This assumption may fail in practical applications, where model simplifications, missing physical effects, parameter drift, or incomplete constitutive relations can lead to model misspecification. In this work, we propose a physics-guided operator correction framework for learning solution operators under misspecified governing equations. At the operator level, the target mapping is decomposed into a prior operator induced by an approximate physical model and a learnable correction operator that accounts for the remaining discrepancy. We realize the operator model correction using a serial DeepONet architecture, where the first DeepONet provides a solution prediction and the second DeepONet learns an additive correction conditioned on both the input function and the solution prediction. The learned correction is incorporated into the physics residual and trained together with data-consistency constraints, allowing the model to retain useful physical structure while adapting to inaccurate governing equations. Numerical experiments on diffusion-reaction, Burgers, cavity flow, and hyperelastic problems show that the proposed method substantially reduces errors induced by misspecified physics. Additional tests under sparse and noisy observations further demonstrate the robustness of the framework and its ability to provide informative uncertainty estimates through deep ensembles.

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。

↑