Stability Preserving Data-driven Models With Latent Dynamics

Abstract

In this paper, we introduce a data-driven modeling approach for dynamics problems with latent variables. The state-space of the proposed model includes artificial latent variables, in addition to observed variables that can be fitted to a given data set. We present a model framework where the stability of the coupled dynamics can be easily enforced. The model is implemented by recurrent cells and trained using backpropagation through time. Numerical examples using benchmark tests from order reduction problems demonstrate the stability of the model and the efficiency of the recurrent cell implementation. As applications, two fluid-structure interaction problems are considered to illustrate the accuracy and predictive capability of the model.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Parameter estimation of ODE's via nonparametric estimators
• Data-driven recovery of hidden physics in reduced order modeling of fluid flows
• Data-driven model reduction, Wiener projections, and the Koopman-Mori-Zwanzig formalism
• IB2d: a Python and MATLAB implementation of the immersed boundary method
• On computing the distance to stability for matrices using linear dissipative Hamiltonian systems
• Approximating the nearest stable discrete-time system
• Coarse-graining Langevin dynamics using reduced-order techniques
• Robust Modeling of Unknown Dynamical Systems via Ensemble Averaged Learning