Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning

Abstract

The complexity of real-world geophysical systems is often compounded by the fact that the observed measurements depend on hidden variables. These latent variables include unresolved small scales and/or rapidly evolving processes, partially observed couplings, or forcings in coupled systems. This is the case in ocean-atmosphere dynamics, for which unknown interior dynamics can affect surface observations. The identification of computationally-relevant representations of such partially-observed and highly nonlinear systems is thus challenging and often limited to short-term forecast applications. Here, we investigate the physics-constrained learning of implicit dynamical embeddings, leveraging neural ordinary differential equation (NODE) representations. A key objective is to constrain their boundedness, which promotes the generalization of the learned dynamics to arbitrary initial condition. The proposed architecture is implemented within a deep learning framework, and its relevance is demonstrated with respect to state-of-the-art schemes for different case-studies representative of geophysical dynamics.

References in corpus (8)

• Optimization for deep learning: theory and algorithms
• Nonlinear Systems Identification Using Deep Dynamic Neural Networks
• Learning Stable Deep Dynamics Models
• Sea Level Anomaly Prediction using Recurrent Neural Networks
• Joint learning of variational representations and solvers for inverse problems with partially-observed data
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
• Bilinear residual Neural Network for the identification and forecasting of dynamical systems
• LyaNet: A Lyapunov Framework for Training Neural ODEs

Cited by in corpus (3)

• Deep learning delay coordinate dynamics for chaotic attractors from partial observable data
• Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
• Extending the trapping theorem to provide local stability guarantees for quadratically nonlinear models