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

详细信息    查看全文

• 作者：Natasha Flyer^a ; ^{flyer@ucar.edu" class="auth_mail" title="E-mail the corresponding author} ; Bengt Fornberg^b ; ^{fornberg@colorado.edu" class="auth_mail" title="E-mail the corresponding author} ; Victor Bayona^c ; ^{victor.bayona.revilla@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Gregory A. Barnett^b ; ^{gregory.barnett@colorado.edu" class="auth_mail" title="E-mail the corresponding author}
• 关键词：RBF-FD ; Polynomials ; Polyharmonic splines ; Interpolation ; Derivative approximations
• 刊名：Journal of Computational Physics
• 出版年：2016
• 出版时间：15 September 2016
• 年：2016
• 卷：321
• 期：Complete
• 页码：21-38
• 全文大小：1286 K

文摘

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.