Bio

Elisabeth Rau is a fourth-year doctoral candidate at Baylor University in the Applied Petroleum Studies Program. Her current research investigates the use of machine learning models for petroleum geology related questions. She received her BS in geology from Colorado State University and will pursue a career in the energy sector following graduation from Baylor.

Abstract

With the rapidly growing and globally expanding inventory of large and complex datasets, i.e., “big data”, machine learning has become a popular data analytics technique within the geoscience community. Here, we evaluate the effectiveness of machine learning in the prediction of facies, facies associations, and reservoir versus non-reservoir rock types in a proven shale reservoir. The Late Devonian Duvernay Formation is a major petroleum source rock in the Western Canada Sedimentary Basin (WCSB) that with recent advances in drilling and completions technology has become a target for exploration and production. Using the Duvernay Formation as a case study, both the benefits and limitations of machine learning derived facies and reservoir quality predictions from wireline logs are evaluated and discussed.