Learning of discrete models of variational PDEs from data

by   Christian Offen, et al.

We show how to learn discrete field theories from observational data of fields on a space-time lattice. For this, we train a neural network model of a discrete Lagrangian density such that the discrete Euler–Lagrange equations are consistent with the given training data. We, thus, obtain a structure-preserving machine learning architecture. Lagrangian densities are not uniquely defined by the solutions of a field theory. We introduce a technique to derive regularisers for the training process which optimise numerical regularity of the discrete field theory. Minimisation of the regularisers guarantees that close to the training data the discrete field theory behaves robust and efficient when used in numerical simulations. Further, we show how to identify structurally simple solutions of the underlying continuous field theory such as travelling waves. This is possible even when travelling waves are not present in the training data. This is compared to data-driven model order reduction based approaches, which struggle to identify suitable latent spaces containing structurally simple solutions when these are not present in the training data. Ideas are demonstrated on examples based on the wave equation and the Schrödinger equation.


page 11

page 13

page 15


Learning discrete Lagrangians for variationalPDEs from data and detection of travelling waves

The article shows how to learn models of dynamical systems from data whi...

Algorithmic Probability-guided Supervised Machine Learning on Non-differentiable Spaces

We show how complexity theory can be introduced in machine learning to h...

Enhancement of shock-capturing methods via machine learning

In recent years, machine learning has been used to create data-driven so...

Feature Engineering with Regularity Structures

We investigate the use of models from the theory of regularity structure...

Extracting Dynamical Models from Data

The FJet approach is introduced for determining the underlying model of ...

Discrete Dirac reduction of implicit Lagrangian systems with abelian symmetry groups

This paper develops the theory of discrete Dirac reduction of discrete L...

A surrogate model for data-driven magnetic stray field calculations

In this contribution we propose a data-driven surrogate model for the pr...

Please sign up or login with your details

Forgot password? Click here to reset