Plausible reasoning from spatial observations

TL;DR

This paper presents a method for plausible reasoning about large-scale spatial properties using belief functions to extrapolate incomplete pointwise observations, accounting for influence decay and dependence in aggregation.

Contribution

It introduces a novel approach combining belief functions and a modified Dempster's rule to model spatial influence and dependence in reasoning from incomplete data.

Findings

Effective extrapolation of spatial observations demonstrated

Influence strength decreases with distance

Aggregation method accounts for dependence between observations

Abstract

This article deals with plausible reasoning from incomplete knowledge about large-scale spatial properties. The availableinformation, consisting of a set of pointwise observations,is extrapolated to neighbour points. We make use of belief functions to represent the influence of the knowledge at a given point to another point; the quantitative strength of this influence decreases when the distance between both points increases. These influences arethen aggregated using a variant of Dempster's rule of combination which takes into account the relative dependence between observations.