PetroGrapher: managing petrographic data and knowledge using an intelligent database application

This paper describes the PetroGrapher system, an intelligent database application to support petrographic analysis and interpretation of oil reservoir rocks, and also data management using resources both from knowledge system technology and database technology. In this project, the visual tacit knowledge applied in petrographic analysis was made explicit through the collection of cases (rock descriptions) that were used in the development of a domain ontology organized in a partonomy. The expert-level features were called here visual chunks.The cases were further compared against the ontology to evidence the relations between described features, visual chunks and interpretations. The domain knowledge was represented through a set of frames and knowledge graphs, which allows identifying the visual chunks and associates them to the related interpretations. The system was developed in a tight couple architecture that associates a relational database system, which acts as a repository for the knowledge base and user data, and an object-oriented component, which preserves the semantic of data and develops inferences. The system was validated by tree groups of users with different levels of expertise.