Fitting scattered data on sphere-like surfaces using spherical splines (Q1815872)

Let \(S\) be the unit sphere or a sphere-like surface in \(\mathbb{R}^3\) (e.g., a part of the surface of an aircraft), and consider a set of scattered points on \(S\), along with real numbers associated with each of these points. The paper is devoted to the problem of finding a function on \(S\) which either interpolants or approximates these data. The authors present a new approach to this problem based on spaces of spherical splines which have many properties in common with the classical polynomial splines on planar triangulations, including a Bernstein-Bézier representation. Using these spaces, some analogs of classical interpolation and fitting methods are examined in detail. In particular, for interpolation, macro-element methods and minimal energy splines are discussed, and for fitting, discrete least squares and penalized squares are considered. The authors also report on numerical results and conclude the paper with remarks on open problems and new research directions.