What is it about?
Permeability logs are critical data used to assess hydrocarbon reservoir quality, which can impede the confidence of reservoir productivity without proper characterization. We have devised a model to predict permeability in two offset boreholes where permeability does not exist. The model was constructed using an artificial neural network algorithm based on permeability data acquired in a new borehole.
Featured Image
Photo by Sisyphus Sosorakis on Unsplash
Why is it important?
Several boreholes do not have a complete set of logs, and a permeability log is not available because of the cost of acquiring and processing data. The algorithm has demonstrated that when permeability is available in one borehole, a model can be devised to predict permeability in other boreholes. This algorithm is significantly effective because it requires permeability data to be acquired only in one selected borehole.
Perspectives
The three permeability logs enable us to assign permeability to the sandbeds intercepted by the three boreholes. A sandbed is characterized as a connected flow unit between boreholes. The algorithm can be applied to process data from additional nearby boreholes and predict permeability in hydrocarbon reservoirs located at other sites.
Geophysicist Jorge O Parra
Southwest Research Institute
Read the Original
This page is a summary of: Deep learning for predicting permeability logs in offset wells using an artificial neural network at a Waggoner Ranch reservoir, Texas, The Leading Edge, March 2022, Society of Exploration Geophysicists,
DOI: 10.1190/tle41030184.1.
You can read the full text:
Resources
Contributors
The following have contributed to this page
