--> Abstract: Lithofacies Classification and Prediction Using Seismic, Well logs, and Core Data: A Supervised Neural Network Methodology Applied in a Carbonate Formation in Saudi Arabia, by C.G. Macrides and H.H. Soepriatna, #90188 (2014)

Datapages, Inc.Print this page

Lithofacies Classification and Prediction Using Seismic, Well logs, and Core Data: A Supervised Neural Network Methodology Applied in a Carbonate Formation in Saudi Arabia

C.G. Macrides1 and H.H. Soepriatna1

1Saudi Aramco

Abstract

To optimally produce the upper Jurassic carbonate reservoirs of an oil field in the Eastern Province of Saudi Arabia, it is essential to delineate the distribution of the most porous carbonate facies within the target intervals. Although impedance inversion is a good first step in that direction, further insights into reservoir quality can be gained by incorporating seismic attributes to predict reservoir properties such as porosity and lithofacies. A three-step methodology is presented that integrates post-stack seismic data with sonic, density and porosity logs, core data, and lithofacies logs to derive lithofacies volumes, in a Bayesian probabilistic sense, in the target reservoir.

 

AAPG Search and Discovery Article #90188 ©GEO-2014, 11th Middle East Geosciences Conference and Exhibition, 10-12 March 2014, Manama, Bahrain