الفهرس | Only 14 pages are availabe for public view |
Abstract This work presents an innovative technique that aims at predicting the quality of a petroleum reservoir using Artificial Neural Networks (ANN) analysis to seismic and well logs data. Supervised ANN has been deployed to predict several reservoir properties, once at a time, through training ANN to determine the seismic attributes that numerically represent accurately the measured properties in well logs, such as shale volume, porosity, permeability and water saturation. This predicted reservoir properties have been used by unsupervised ANN to determine the reservoir quality throughout the area covered by seismic data. Four grades or categories of reservoir quality, Very Good, Good, Bad and Very Bad, have been determined. The highest grade (category) is characterized by high porosity and permeability, and low water saturation and shale volume. Based variability of reservoir properties determined from seismic attributes analysis, the reservoir geobody is characterized into the predefined four reservoir grades (Very Good, Good, Bad and Very Bad) and their spatial distribution is displayed. Such information is highly valuable for optimum reservoir management and well placement that not only maximizes reservoir profitability through development of field production schemes but also minimizes uncertainties in drilling, production, injection and modeling processes. In addition, adopting the proposed methodology would entail cost reduction in well logging and core programs |