At a GSH West Tech Breakfast Meeting, to be held December 12th, Peter Wang, GeoComputing Group, will present a case study, Exploring for Wolfcamp Reservoirs, Eastern Shelf of the Permian Basin, Texas, Using a Machine Learning Approach. This paper is co-authored by Bruno de Ribet (Emerson E&P Software), Monte Meers (Independent Geologist), Howard “Pete” Renick (Independent Geologist), Russ Creath (Reservoir Geophysicist, Hardin International), and Ryan McKee (Geophysical Technician, RAM Imaging Technology).
The talk is open to the general public, free of charge. GSH members, please register on the GHS Event page.
Time: 7:00 (breakfast) - 8:30. Talk to begin at 7:30.
If you have questions about event registration or society membership, please contact GSH.
|Voxel visualization display of the Lower and Upper Wolfcamp oil-filled facies probability cloud, Eastern Shelf of Permian Basin, TX
One of the leading challenges in hydrocarbon exploration and production 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.