A Framework for Scientific Discovery in Geological Databases

It is common knowledge in the oil industry that the typical cost of drilling a new offshore well is in the range of $30-40 million, but the chance of that site being an economic success is 1 in 10. Recent advances in drilling technology and data collection methods have led to oil companies and their ancillary companies collecting large amounts of geophysical/geological data from production wells and exploration sites. This information is being organized into large company databases and the question is can this vast amount of history from previously explored fields be systematically utilized to evaluate new plays and prospects? A possible solution is to develop the capability for retrieving analog wells and fields for the new prospects and employing Monte Carlo methods with risk analysis techniques for computing the distributions of possible hydrocarbon volumes for these prospects. This may form the basis for more accurate and objective prospect evaluation and ranking schemes. However, with the development of more sophisticated methods for computer-based scientific discovery[6], the primary question becomes, can we derive more precise analytic relations between observed phenomena and parameters that directly contribute to computation of the amount of oil and gas reserves. For oil prospects, geologists compute potential recoverable reserves using the pore-volume equation[i]