Abstract
The effect of shale on the evaluation of water saturation in shaly porous media is yet to be fully understood. Wide varieties of water saturation models for shaly sands are currently in use. However, none is universally accepted by log analysts and each model estimates water saturation value significantly different from the others. Error in water saturation can result in either underestimation or overestimation of hydrocarbon reserves, which will influence management decision on a given field. A laboratory measurement of water saturation is the most accurate but limited by time and cost, thereby forcing the industry to rely on these models. In this paper, we show how a computer artificial intelligence ( AI) system can predict water saturation with an accuracy of 93% compared to selected saturation models. Three saturation models were selected and subjected to same well log data as the AI model to estimate water saturation. The estimated saturation values for AI and other saturation models were then compared with experimental values for 147 core samples and results showed that the AI model was able to use shale affected log data to accurately predict water saturation while the saturation models did the same with lesser accuracy of 63, 50, and 43%. A statistical and graphical comparison of accuracy and error between the AI technique and selected models is presented.