Spherical k-Nearest Neighbors Interpolation

Abstract

Geospatial interpolation is a challenging task due to real world data often being sparse, heterogeneous and inconsistent. For that matter, this work presents SkNNI, a spherical interpolation algorithm capable of working with such challenging geospatial data. This work also presents NDDNISD an accurate and efficient interpolation function for SkNNI which shines due to its spatial awareness in terms of proximity and distribution of observation neighbors. SkNNI's open source implementation is also discussed and illustrated with a simple usage example.