AAPG GEO 2010 Middle East
Geoscience Conference & Exhibition
Innovative Geoscience Solutions – Meeting Hydrocarbon Demand in Changing Times
March 7-10, 2010 – Manama, Bahrain
Reservoir Porosity and Permeability Prediction from Petrographic Data Using Artificial Neural Network - A Case Study from Saudi Arabia
(1) Earth Sciences, KFUPM, Dhahran, Saudi Arabia.
(2) Earth Sciences, KFUPM, Dhahran, Saudi Arabia.
Understanding reservoir heterogeneity is essential for the assessing and the prediction of the reservoir properties and quality. This study investigates the prediction of the reservoir petrophysical properties of the Ordovician Upper Dibsiyah Member of the Wajid Sandstone in south west Saudi Arabia. The Artificial Neural Networks (ANNS) technique is used here to study the pattern recognition and correlation among the petrographic thin section data such as grain size, sorting, matrix % and cementation % and perophysical properties of the reservoir such as porosity, permeability and lithofacies.
For this purpose, artificial intelligence techniques were designed and developed and these are the multilayer perception (MLP) and the general regression neural network (GRNN). The good agreement between core data and precdicted values by neural netwoks demonstrate a successful implementation and validation of the network’s ability to map a complex non-linear relationship between petrographic data, permeability and porosity. The GRNN technique provides better prediction of the reservoir properties than that obtained from the use of the MLP technique.