Comparing Interpolations Using Standard and Normalized Radial Basis Functions

Abstract

Radial basis functions (RBFs) are commonly used in solving partial differential equations, interpolation and ap-proximation of scalar and vector data, image reconstruction, geographic information systems, and machine learning. In this contribution, the properties of interpolations using standard and normalized RBFs are compared, and the impact of an added polynomial term is analyzed using various samplings of input functions. Experimental results across a range of tested kernel functions and shape parameters are provided.