Neural network enhanced computations on coarse grids

Jan Nordström, Oskar Ålund

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

Unresolved gradients produce numerical oscillations and inaccurate results. The most straightforward solution to such a problem is to increase the resolution of the computational grid. However, this is often prohibitively expensive and may lead to ecessive execution times. By training a neural network to predict the shape of the solution, we show that it is possible to reduce numerical oscillations and increase both accuracy and efficiency. Data from the neural network prediction is imposed using multiple penalty terms inside the domain.

Original languageEnglish
Article number109821
JournalJournal of Computational Physics
Volume425
DOIs
Publication statusPublished - 15 Jan 2021

Keywords

  • Boundary layer
  • Coarse grids
  • Neural network
  • Numerical oscillations
  • Penalty terms
  • Summation-by-parts

ASJC Scopus subject areas

  • Numerical Analysis
  • Modeling and Simulation
  • Physics and Astronomy (miscellaneous)
  • General Physics and Astronomy
  • Computer Science Applications
  • Computational Mathematics
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Neural network enhanced computations on coarse grids'. Together they form a unique fingerprint.

Cite this