Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

by   Vincent Le Guen, et al.

Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields. While purely data-driven approaches are arguably insufficient in this context, standard physical modeling based approaches tend to be over-simplistic, inducing non-negligible errors. In this work, we introduce the APHYNITY framework, a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models. It consists in decomposing the dynamics into two components: a physical component accounting for the dynamics for which we have some prior knowledge, and a data-driven component accounting for errors of the physical model. The learning problem is carefully formulated such that the physical model explains as much of the data as possible, while the data-driven component only describes information that cannot be captured by the physical model, no more, no less. This not only provides the existence and uniqueness for this decomposition, but also ensures interpretability and benefits generalization. Experiments made on three important use cases, each representative of a different family of phenomena, i.e. reaction-diffusion equations, wave equations and the non-linear damped pendulum, show that APHYNITY can efficiently leverage approximate physical models to accurately forecast the evolution of the system and correctly identify relevant physical parameters.


Deep learning for spatio-temporal forecasting – application to solar energy

This thesis tackles the subject of spatio-temporal forecasting with deep...

Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control

Data-driven control algorithms use observations of system dynamics to co...

Calibrated Forecasts of Quasi-Periodic Climate Processes with Deep Echo State Networks and Penalized Quantile Regression

Among the most relevant processes in the Earth system for human habitabi...

Convolutional recurrent autoencoder network for learning underwater ocean acoustics

Underwater ocean acoustics is a complex physical phenomenon involving no...

Towards Automated Statistical Physics : Data-driven Modeling of Complex Systems with Deep Learning

Rich phenomena from complex systems have long intrigued researchers, and...

Physics-Informed and Data-Driven Discovery of Governing Equations for Complex Phenomena in Heterogeneous Media

Rapid evolution of sensor technology, advances in instrumentation, and p...

Generalizing to New Physical Systems via Context-Informed Dynamics Model

Data-driven approaches to modeling physical systems fail to generalize t...

Please sign up or login with your details

Forgot password? Click here to reset