Publication:
On the role of polynomials in RBF-FD approximations: II. numerical solution of elliptic PDEs

Loading...
Thumbnail Image
Identifiers
Publication date
2017-03-01
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
RBF-generated finite differences (RBF-FD) have in the last decade emerged as a very powerful and flexible numerical approach for solving a wide range of PDEs. We find in the present study that combining polyharmonic splines (PHS) with multivariate polynomials offers an outstanding combination of simplicity, accuracy, and geometric flexibility when solving elliptic equations in irregular (or regular) regions. In particular, the drawbacks on accuracy and stability due to Runge's phenomenon are overcome once the RBF stencils exceed a certain size due to an underlying minimization property. Test problems include the classical 2-D driven cavity, and also a 3-D global electric circuit problem with the earth's irregular topography as its bottom boundary. The results we find are fully consistent with previous results for data interpolation.
Description
Keywords
Elliptic Pdes, RBF-FD, Polynomials, Polyharmonic splines, Runge's phenomenon, Meshless
Bibliographic citation
Bayona, V., Flyer, N., Fornberg, B., Barnett, G. A. (2017). On the role of polynomials in RBF-FD approximations: II. Numerical solution of elliptic PDEs. Journal of Computational Physics, 332, 257–273.