Assisting Seismic Image Interpretations with Hyperknowledge

Seismic data interpretation process is a time consuming and knowledge intensive process. Recently, research community proposed machine learning techniques to extract information from seismic images, aiming at assisting this interpretation process. Although useful, these techniques solve just part of the seismic interpretation problem. They focus on identifying specific features (e.g. salt diapirs, reservoir facies, mini-basins) but they fail in identifying and analyzing the spatial correlation among them. In this work we propose the use of hyper knowledge specifications to address this issue. The main contribution of this work is not only to present hyper knowledge templates to this problem, but also the discussions about how to map hyperknowledge as a knowledge graph as well as creating a reasoning engine that exploits the knowledge graph representation.