Using Ontologies for Integrated Geographic Information Systems

TLDR

The Earth is now surrounded by vast amounts of spatial data from advanced collection technologies, creating challenges for integrating diverse geographic information. The paper aims to introduce a GIS architecture that enables seamless, flexible geographic information integration based on semantic value, with special emphasis on remote sensing and GIS integration. The authors propose an ontology‑driven GIS that acts as a system integrator, using ontologies as components alongside databases and employing multiple ontology levels to guide extraction of general or detailed information across classification stages. Users can retrieve embedded knowledge by browsing ontologies within the system.

Abstract

Today, there is a huge amount of data gathered about the Earth, not only from new spatial information systems, but also from new and more sophisticated data collection technologies. This scenario leads to a number of interesting research challenges, such as how to integrate geographic information of different kinds. The basic motivation of this paper is to introduce a GIS architecture that can enable geographic information integration in a seamless and flexible way based on its semantic value and regardless of its representation. The proposed solution is an ontology‐driven geographic information system that acts as a system integrator. In this system, an ontology is a component, such as the database, cooperating to fulfill the system’s objectives. By browsing through ontologies the users can be provided with information about the embedded knowledge of the system. Special emphasis is given to the case of remote sensing systems and geographic information systems. The levels of ontologies can be used to guide processes for the extraction of more general or more detailed information. The use of multiple ontologies allows the extraction of information in different stages of classification. The semantic integration of aerial images and GIS is a crucial step towards better geospatial modeling.