Model Reduction with Memory and the Machine Learning of Dynamical Systems

Abstract

The well-known Mori-Zwanzig theory tells us that model reduction leads to memory effect. For a long time, modeling the memory effect accurately and efficiently has been an important but nearly impossible task in developing a good reduced model. In this work, we explore a natural analogy between recurrent neural networks and the Mori-Zwanzig formalism to establish a systematic approach for developing reduced models with memory. Two training models-a direct training model and a dynamically coupled training model-are proposed and compared. We apply these methods to the Kuramoto-Sivashinsky equation and the Navier-Stokes equation. Numerical experiments show that the proposed method can produce reduced model with good performance on both short-term prediction and long-term statistical properties.

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• On the difficulty of training Recurrent Neural Networks
• Quantifying and Reducing Model-Form Uncertainties in Reynolds-Averaged Navier-Stokes Simulations: A Data-Driven, Physics-Based Bayesian Approach

Cited by in corpus (11)

• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Time-series learning of latent-space dynamics for reduced-order model closure
• Data-driven model reduction, Wiener projections, and the Koopman-Mori-Zwanzig formalism
• Data-driven molecular modeling with the generalized Langevin equation
• Differentiable Molecular Simulations for Control and Learning
• Machine learning based non-Newtonian fluid model with molecular fidelity
• Ab Initio Generalized Langevin Equation
• Machine Learning-Based Statistical Closure Models for Turbulent Dynamical Systems
• Discovery of Dynamics Using Linear Multistep Methods
• Analytic Continuation of Noisy Data Using Adams Bashforth ResNet