Exploring for Wolfcamp Reservoir in the Permian Basin, Using a Machine Learning Approach
One of the leading challenges in hydrocarbon E&P is predicting rock types and fluid content distribution throughout the reservoir away from the boreholes. In this presentation, we will demonstrate the application of a neural network based machine learning methodology called Democratic Neural Network Association (DNNA) to the problem of finding oil-filled packstones in the Middle Wolfcamp, Eastern Shelf of the Permian Basin, Texas. The DNNA algorithm searched through fifteen 3D seismic volumes simultaneously, and was able to build a model which reconstructed the nine lithofacies. No evidence was seen of false positive or false negative predictions at the wells for the oil-filled packstone facies. The neural network learnings were applied through the 3D survey, and results were delivered with up to a 0.5 ms two-way time vertical resolution, or about 5 ft, a significant uplift from conventional seismic resolution. Lateral resolution was also improved. Additional drilling opportunities can be identified from the seismic facies thickness map or the facies probability voxel clouds.