Spatial data mining, i.e., mining knowledge from large amounts of spatial d
ata, is a demanding field since huge amounts of spatial data have been coll
ected in various applications, ranging from remote sensing to geographical
information systems (GIS), computer cartography, environmental assessment a
nd planning. The collected data far exceeds people's ability to analyze it.
Thus, new and efficient methods are needed to discover knowledge from larg
e spatial databases. Most of the spatial data mining methods do not take in
to account the uncertainty of spatial information. In our work we use objec
ts with broad boundaries, the concept that absorbs all the uncertainty by w
hich spatial data is commonly affected and allows computations in the prese
nce of uncertainty without rough simplifications of the reality. The topolo
gical relations between objects with a broad boundary can be organized into
a three-level concept hierarchy. We developed and implemented a method for
an efficient determination of such topological relations. Based on the hie
rarchy of topological relations we present a method for mining spatial asso
ciation rules for objects with uncertainty. The progressive refinement appr
oach is used for the optimization of the mining process. (C) 2000 Elsevier
Science B.V. All rights reserved.