ADDGEO: An Intelligent Agent to Assist Geologist Finding Petroleum in Offshore Lands
In this paper, we present an intelligent agent (ADDGEO) that assists geologists identifying rocks constituents during thin section analysis. ADDGEO is a hybrid tool using both a knowledge base and a neural net to recognize existent visual patterns in thin sections alone or with the user participation. ADDGEO was recently deployed in a Brazilian oil company presenting benefits to improve the geologists task completion. In addition, it has shown a potential use as a training tool.
KeywordsThin Section Radial Basis Function Neural Network Intelligent Agent Thin Section Analysis Diagnosis Task
Unable to display preview. Download preview PDF.
- 1.Garcia, A. C. B. — Active Design Documents: A New Approach for Supporting Documentation in Preliminary Routine Design — Ph. D. Thesis — Civil Engineering Department — Stanford University — 1992.Google Scholar
- 2.Decatur, S. E. — Applications of Neural Networks to Terrain Classifications — Proceedings of the International Joint Conference on Neural Networks 89 — Washington — 1989.Google Scholar
- 3.Roli, F., Serpico, S. and Vernazza, G. — Neural Networks for Classification od Remotely Sensed Images in Fuzzy Logic and Neural Networks Handbook — McGraw Hill Inc. — New York — 1996.Google Scholar
- 4.Hwang, J. N., Lay, S. R. and Kiang, R. — Robust Construction Neural Networks for Classification on Remotely Sensed Data — Proceedings of World Congress on Neural Networks 93 — Portland — 1993.Google Scholar
- 6.Klimasausker, Casimir C. e Guiner, John P. Neuralworks — Neuralware Inc.-Pitsburgh-1988.Google Scholar