PDE-NetGen 1.0: from symbolic partial differential equation (PDE) representations of physical processes to trainable neural network representations - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Geoscientific Model Development Année : 2020

PDE-NetGen 1.0: from symbolic partial differential equation (PDE) representations of physical processes to trainable neural network representations

Résumé

Bridging physics and deep learning is a topical challenge. While deep learning frameworks open avenues in physical science, the design of physically consistent deep neural network architectures is an open issue. In the spirit of physics-informed neural networks (NNs), the PDE-NetGen package provides new means to automatically translate physical equations, given as partial differential equations (PDEs), into neural network architectures. PDE-NetGen combines symbolic calculus and a neural network generator. The latter exploits NN-based implementations of PDE solvers using Keras. With some knowledge of a problem, PDE-NetGen is a plug-and-play tool to generate physics-informed NN architectures. They provide computationally efficient yet compact representations to address a variety of issues, including, among others, adjoint derivation, model calibration, forecasting and data assimilation as well as uncertainty quantification. As an illustration, the workflow is first presented for the 2D diffusion equation, then applied to the data-driven and physics-informed identification of uncertainty dynamics for the Burgers equation.
Fichier principal
Vignette du fichier
gmd-13-3373-2020.pdf (1.42 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02933377 , version 1 (08-09-2020)

Licence

Paternité

Identifiants

Citer

Olivier Pannekoucke, Ronan Fablet. PDE-NetGen 1.0: from symbolic partial differential equation (PDE) representations of physical processes to trainable neural network representations. Geoscientific Model Development, 2020, 13 (7), pp.3373-3382. ⟨10.5194/gmd-13-3373-2020⟩. ⟨hal-02933377⟩
74 Consultations
78 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More