(Revised) RECURSIVE ESTIMATION FOR 2-D ISOTROPIC RANDOM FIELDS

In this paper we develop efficient recursive smoothing algorithms for isotropic random fields described by non-causal internal differen-tial models. The 2-D estimation problem is shown to be equivalent to a countably infinite set of 1-D separable two-point boundary value smoothing problems. The 1-D smoothing problems are solved using ei-ther a Markovianization approach followed by a standard 1-D smooth-ing algorithm, or by using a recently developed smoothing technique for two-point boundary value problems. The desired field estimate is then obtained as a properly weighted sum of the 1-D smoothed estimates