Piet: a GIS-OLAP Implementation

Abstract

Data aggregation in Geographic Information Systems (GIS) is a desirable feature, although only marginally present in commercial systems nowadays, mostly through ad-hoc solu- tions. Integration between GIS and OLAP systems is still needed in commercial systems. With this in mind, we have developed Piet, a system that that makes use of a novel query processing technique: first, a process called subpoly- gonization decomposes each thematic layer into open con- vex polygons; then, another process computes and stores in a database the overlay of those layers for later use by the query processor. We describe in detail the implementation of Piet, and provide evidence, through experimentation over real-world maps, that overlay precomputation for spatial ag- gregate queries can be competitive with GIS systems that employ indexing schemes based on R-trees. Given that the data model and implementation do not prevent the use of traditional indexing techniques as R-tree and aR-trees, we our proposal against these techniques in our experiments.