Analyzing Spatial -Temporal Geographic Information based on Blackboard Architecture and Multi-Agent System

Summary In a lot of theoretical and practical applications of different geographical disciplines, the use of Geographical Information Systems (GIS) is by now a more or less common issue. Visualization, presentation, administration and analysis of geographical relevant data are a main feature of scientific research and teaching. Furthermore, in commercial contexts like advertisement, marketing, navigation, administration, project management and planning becomes crucial. The retrieval and location of geographic information will require a significant amount of time and effort. In addition, different users usually have different views and interests in the same information. In order to resolve such problems, this paper proposes a generic geographic information model system based on blackboard architecture and multi-Agent (MA) architecture. By paralyzing tasks and offering more efficiency and flexibility, this approach seems to be fruitful in order to construct flexible and extensible system improving more capability and efficiency of GIS services. We further illustrate the design and implementation of the multi-agent system that uses image analysis agents for generating and processing parallel programs by calling the available method. In a first time, we validated our approach on satellite images of SPOT4 representing a north Tunisian region for different dates in order to detect changes for a possible prediction and a better decision making and in a second time we represent how to model and represent geographic data.