On the role of polynomials in RBF-FD approximations: I. Interpolation and accuracy

AMS Citation:
Flyer, N., B. Fornberg, V. Bayona, and G. A. Barnett, 2016: On the role of polynomials in RBF-FD approximations: I. Interpolation and accuracy. Chinese Journal of Computational Physics, 321, 21-38, doi:10.1016/j.jcp.2016.05.026.
Date:2016-09-15
Resource Type:article
Title:On the role of polynomials in RBF-FD approximations: I. Interpolation and accuracy
Abstract: Radial basis function-generated finite difference (RBF-FD) approximations generalize classical grid-based finite differences (FD) from lattice-based to scattered node layouts. This greatly increases the geometric flexibility of the discretizations and makes it easier to carry out local refinement in critical areas. Many different types of radial functions have been considered in this RBF-FD context. In this study, we find that (i) polyharmonic splines (PHS) in conjunction with supplementary polynomials provide a very simple way to defeat stagnation (also known as saturation) error and (ii) give particularly good accuracy for the tasks of interpolation and derivative approximations without the hassle of determining a shape parameter. In follow-up studies, we will focus on how to best use these hybrid RBF polynomial bases for FD approximations in the contexts of solving elliptic and hyperbolic type PDEs.
Peer Review:Refereed
Copyright Information:Copyright 2016 Elsevier.
OpenSky citable URL: ark:/85065/d72z176c
Publisher's Version: 10.1016/j.jcp.2016.05.026
Author(s):
  • Natasha Flyer - NCAR/UCAR
  • Bengt Fornberg
  • Victor Bayona
  • Gregory Barnett
  • Random Profile

    SCIENTIST III

    Recent & Upcoming Visitors