Abstract

Incomplete or sparse data, such as geologic or formation characteristics, introduces a high level of risk for oil exploration and development projects. “Expert” systems are used in several disciplines and industries, including such disciplines as medical diagnosis. They have demonstrated beneficial results in modeling the decision-making process of knowledgeable experts. A state-of-the-art “Expert” exploration tool is proposed for oil exploration. This tool relies on a digital data base, and computer maps generated by neural networks using “fuzzy” logic. Fuzzy logic is a relatively new, mathematical treatment of imprecise or non-explicit parameters and values. Oil prospecting risk can be reduced with the use of a properly developed and validated “Fuzzy Expert Exploration” (FEE) Tool.

Analysis to date includes generation of regional scale maps of aeromagnetic, gravity, formation tops and thickness, source rocks, and production data for the Brushy Canyon Formation in the Delaware Basin of New Mexico. Fuzzy logic and neural networks will be used to find correlations between the data and data attributes, such as formation curvature and field scale production maps. A preliminary Java-based expert system is being used to model the thought processes of a human explorationist, and to evaluate new prospects between, or away from, existing Brushy Canyon fields. The final product will be available on the web and will use public data.