Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
复制标题
机器学习与基于知识的建模相结合用于大型、复杂、时空系统的可伸缩预测和亚网格尺度闭合
DOI：
10.1063/5.0005541
复制
发表时间：
2020-02
期刊：
影响因子：
2.9
通讯作者：
Alexander Wikner;Jaideep Pathak;B. Hunt;M. Girvan;T. Arcomano;I. Szunyogh;A. Pomerance;E. Ott
中科院分区：
文献类型：
--
作者：
Alexander Wikner;Jaideep Pathak;B. Hunt;M. Girvan;T. Arcomano;I. Szunyogh;A. Pomerance;E. Ott
我们考虑常见的情况（例如，在天气预报中），其目标是当我们可以访问先前系统状态的时间序列数据和完整系统动态的不完美模型时，预测大型时空混沌动态系统的时间演化。具体来说，我们试图利用机器学习作为将过去数据的使用整合到预测中的重要工具。为了便于扩展到感兴趣的时空混沌系统是非常大的和复杂的常见场景，我们提出了两种方法相结合：（i）并行机器学习预测方案和（ii）一种混合技术的复合预测系统组成的基于知识的组件和基于机器学习的组件。我们证明，这种结合（i）和（ii）的方法不仅可以扩展到非常大的系统，以提供出色的性能，而且训练我们的多个并行机器学习组件所需的时间序列数据的长度大大小于没有并行化所需的长度。此外，考虑到计算实现的知识为基础的组件不解决亚网格尺度的过程的情况下，我们的计划是能够使用训练数据，将未解决的短尺度动态的效果后，解决了较长尺度的动态（亚网格尺度关闭）。
We consider the commonly encountered situation (e.g., in weather forecast) where the goal is to predict the time evolution of a large, spatiotemporally chaotic dynamical system when we have access to both time series data of previous system states and an imperfect model of the full system dynamics. Specifically, we attempt to utilize machine learning as the essential tool for integrating the use of past data into predictions. In order to facilitate scalability to the common scenario of interest where the spatiotemporally chaotic system is very large and complex, we propose combining two approaches: (i) a parallel machine learning prediction scheme and (ii) a hybrid technique for a composite prediction system composed of a knowledge-based component and a machine learning-based component. We demonstrate that not only can this method combining (i) and (ii) be scaled to give excellent performance for very large systems but also that the length of time series data needed to train our multiple, parallel machine learning components is dramatically less than that necessary without parallelization. Furthermore, considering cases where computational realization of the knowledge-based component does not resolve subgrid-scale processes, our scheme is able to use training data to incorporate the effect of the unresolved short-scale dynamics upon the resolved longer-scale dynamics (subgrid-scale closure).