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

JOURNAL OF COMPUTATIONAL PHYSICS

卷:321

Article

Flyer, Natasha¹  Fornberg, Bengt²  Bayona, Victor³  Barnett, Gregory A.² 

[1] Natl Ctr Atmospher Res, Inst Math Appl Geosci, Boulder, CO 80305 USA

[2] Univ Colorado, Dept Appl Math, Boulder, CO 80309 USA

[3] Univ Bath, Dept Math Sci, Bath BA2 7AY, Avon, England

关键词: RBF-FD;    Polynomials;    Polyharmonic splines;    Interpolation;    Derivative approximations;   

DOI  :  10.1016/j.jcp.2016.05.026

来源: Elsevier

【 摘 要 】

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. (C) 2016 Elsevier Inc. All rights reserved.

【 授权许可】

Free