Author(s)

D. Saint-Joan & J. Desachy

Abstract

Cartographic problems solving in geographical information system for agriculture D. Saint-Joan & J. Desachy Institut de Recherche en Informatique de Toulouse, Universite Paul Sabatier 118, route de Narbonne 31062 Toulouse, France ABSTRACT The system described in this paper is a consequence of the use of artificial intelligence and Geographical Information System (CIS) for remote sensing image interpretation. The knowledge we are managing with for classification purposes on satellite images involves image data which can be used for reasoning on CIS. Our system computes a potentiality map for problem solution with a specification (characterizing the expert knowledge by means of production rules) provided by the user. This knowledge may be uncertain and imprecise and is obtained particularly by the fuzzy set theory. The solution potentialities are computed by an expert system using an inference network (an acyclic graph). This approach is extended with neighbourhood p

Keywords