Abstract

Numerical methods for approximately solving partial differential equations (PDE) are at the core of scientific computing. Often, this requires high-resolution or adaptive discretization grids to capture relevant spatio-temporal features in the PDE solution, e.g., in applications like turbulence, combustion, and shock propagation. Numerical approximation also requires knowing the PDE in order to construct problem-specific discretizations. Systematically deriving such solution-adaptive discrete operators, however, is a current challenge. Here we present an artificial neural network architecture for data-driven learning of problemand resolution-specific local discretizations of nonlinear PDEs. Our proposed method achieves numerically stable discretization of the operators in an unknown nonlinear PDE by spatially and temporally adaptive parametric pooling on regular Cartesian grids, and by incorporating knowledge about discrete time integration. Knowing the actual PDE is not necessary, as solution data is sufficient to train the network to learn the discrete operators. A once-trained neural architecture model can be used to predict solutions of the PDE on larger spatial domains and for longer times than it was trained for, hence addressing the problem of PDE-constrained extrapolation from data. We present demonstrative examples on long-term forecasting of hard numerical problems including equation-free forecasting of non-linear dynamics of forced Burgers problem on coarse spatio-temporal grids.

Full document

The PDF file did not load properly or your web browser does not support viewing PDF files. Download directly to your device: Download PDF document
Back to Top
GET PDF

Document information

Published on 11/03/21
Submitted on 11/03/21

Volume 400 - Biomechanics and Mechanobiology, 2021
DOI: 10.23967/wccm-eccomas.2020.132
Licence: CC BY-NC-SA license

Document Score

0

Views 35
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?