Machine Learning-Based Statistical Closure Models for Turbulent Dynamical Systems

Abstract

We propose a Machine Learning (ML) non-Markovian closure modeling framework for accurate predictions of statistical responses of turbulent dynamical systems subjected to external forcings. One of the difficulties in this statistical closure problem is the lack of training data, which is a configuration that is not desirable in supervised learning with neural network models. In this study with the 40-dimensional Lorenz-96 model, the shortage of data (in temporal) is due to the stationarity of the statistics beyond the decorrelation time, thus, the only informative content in the training data is on short-time transient statistics. We adopted a unified closure framework on various truncation regimes, including and excluding the detailed dynamical equations for the variances. The closure frameworks employ a Long-Short-Term-Memory architecture to represent the higher-order unresolved statistical feedbacks with careful consideration to account for the intrinsic instability yet producing stable long-time predictions. We found that this unified agnostic ML approach performs well under various truncation scenarios. Numerically, the ML closure model can accurately predict the long-time statistical responses subjected to various time-dependent external forces that are not (and maximum forcing amplitudes that are relatively larger than those) in the training dataset.

arXiv comment8 figures

References in corpus (12)

• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Searching for turbulence models by artificial neural network
• Time-series learning of latent-space dynamics for reduced-order model closure
• Machine Learning for Prediction with Missing Dynamics
• A Priori Estimation Of Memory Effects In Coarse-Grained Nonlinear Systems Using The Mori-Zwanzig Formalism
• Kernel-based Prediction of Non-Markovian Time Series
• Linear theory for filtering nonlinear multiscale systems with model error
• Comparison of continuous and discrete-time data-based modeling for hypoelliptic systems
• Adaptive Error Covariances Estimation Methods for Ensemble Kalman Filters
• Model Reduction with Memory and the Machine Learning of Dynamical Systems
• Modeling of Missing Dynamical Systems: Deriving Parametric Models using a Nonparametric Framework

Cited by in corpus (1)

• A Data-Driven Statistical-Stochastic Surrogate Modeling Strategy for Complex Nonlinear Non-stationary Dynamics