Extracting Lithofacies from Digital Well Logs Using Artificial Intelligence, Panoma (Council Grove) Field, Hugoton Embayment, Southwest Kansas
Kansas Geological Survey
Open-file Report 2003-68

After all the testing and model development, the final steps are to run neural network models on LAS files and output LAS formatted prediction files. The predicted lithofacies output LAS file has nine curves, the probability for the eight lithofacies and one discrete lithofacies (the most probable). Next, the lithofacies prediction files are imported into geologic applications for further geomodel development. Shown are results for one of the Keystone wells showing the predicted probabilities, predicted discrete lithofacies and the actual core-defined lithofacies for the seven Council Grove sequences studied.


top of report

e-mail : webadmin@kgs.ku.edu
Last updated January 2004

http://www.kgs.ku.edu/PRS/publication/2003/ofr2003-68/slide16.html