期刊
出版社
ROYAL SOC
DOI: 10.1098/rspa.2020.1004
关键词
delay differential equations; reduced-order-model; turbulence closure; ecosystem modelling; data assimilation; machine learning
资金
- Office of Naval Research [N00014-20-12023]
- Mechanical Engineering Department at MIT
- MathWorks
This study introduces a novel methodology for learning non-Markovian closures for known-physics/low-fidelity models using data from high-fidelity simulations. The neural closure models efficiently capture truncated modes in reduced-order-models and enhance long-term prediction accuracy, requiring smaller networks with limited additional computational cost.
Complex dynamical systems are used for predictions in many domains. Because of computational costs, models are truncated, coarsened or aggregated. As the neglected and unresolved terms become important, the utility of model predictions diminishes. We develop a novel, versatile and rigorous methodology to learn non-Markovian closure parametrizations for known-physics/low-fidelity models using data from high-fidelity simulations. The new neural closure models augment low-fidelity models with neural delay differential equations (nDDEs), motivated by the Mori-Zwanzig formulation and the inherent delays in complex dynamical systems. We demonstrate that neural closures efficiently account for truncated modes in reduced-order-models, capture the effects of subgrid-scale processes in coarse models and augment the simplification of complex biological and physical-biogeochemical models. We find that using non-Markovian over Markovian closures improves long-term prediction accuracy and requires smaller networks. We derive adjoint equations and network architectures needed to efficiently implement the new discrete and distributed nDDEs, for any time-integration schemes and allowing non-uniformly spaced temporal training data. The performance of discrete over distributed delays in closure models is explained using information theory, and we find an optimal amount of past information for a specified architecture. Finally, we analyse computational complexity and explain the limited additional cost due to neural closure models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据