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

For the Panoma project the geomodel workflow included the following steps:

  1. Identification of lithofacies and associated petrophysical properties in a subset of cores
    • 1900’ of core was described at half-foot intervals using a digital description scheme that allowed efficient lumping and splitting options
    • Cores were from 8 wells (triangles) selected to give optimal geographic and stratigraphic coverage
  2. Lithofacies were then predicted in 500 non-cored wells using a neural network trained on the core lithofacies
  3. Next was the building a 3D cellular model by extrapolating lithofacies into areas between the lithofacies wells using commercial stochastic modeling software

The focus of this paper is on the identification of lithofacies in core and prediction of these lithofacies in non-cored wells


top of report

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

http://www.kgs.ku.edu/PRS/publication/2003/ofr2003-68/slide5.html