Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations

Abstract

The data-driven recovery of the unknown governing equations of dynamical systems has recently received an increasing interest. However, the identification of governing equations remains challenging when dealing with noisy and partial observations. Here, we address this challenge and investigate variational deep learning schemes. Within the proposed framework, we jointly learn an inference model to reconstruct the true states of the system and the governing laws of these states from series of noisy and partial data. In doing so, this framework bridges classical data assimilation and state-of-the-art machine learning techniques. We also demonstrate that it generalises state-of-the-art methods. Importantly, both the inference model and the governing model embed stochastic components to account for stochastic variabilities, model errors, and reconstruction uncertainties. Various experiments on chaotic and stochastic dynamical systems support the relevance of our scheme w.r.t. state-of-the-art approaches.

References in corpus (12)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Data-driven discovery of coordinates and governing equations
• A Recurrent Latent Variable Model for Sequential Data
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Neural Ordinary Differential Equations
• Data Driven Governing Equations Approximation Using Deep Neural Networks
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• Deep Kalman Filters
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Learning Dynamical Systems from Partial Observations
• EM-like Learning Chaotic Dynamics from Noisy and Partial Observations
• Joint learning of variational representations and solvers for inverse problems with partially-observed data

Cited by in corpus (3)

• Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
• Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
• Learning stochastic dynamical systems with neural networks mimicking the Euler-Maruyama scheme