Discovering Order in Chaos: Using a Heuristic Ontology to Derive Spatio-Temporal Sequences for Cadastral Data

Abstract

A heuristic ontology is an ontology that describes concepts using heuristics (‘rules of thumb’ or guidelines) rather than axioms as in a classical ontology. The heuristics can be used to establish whether a given instance is a member of the concept defined by the heuristics in a data-driven manner. The approach may be particularly useful if data is poor, irregular or incomplete. A heuristic ontology was used to determine whether given collections of land parcels are valid spatio-temporal sequences and thus automatically derive sequence data that would otherwise have to be maintained manually, achieving levels of precision of 94% and recall of 67%.