oa Application of neural network in intelligent reservoir characterization: A case study from Ahwaz oil field, southwest Iran

Porosity and permeability are the most important hydrocarbon reservoir properties. There are two methods for determining porosity: directly by core analysis with helium injection, and indirectly by well-log analysis. Similarly, permeability can be determined in the laboratory from core samples by dry-air injection or well-testing methods. These methods are costly and time-consuming. Due to economic reasons and the inability to core horizontal wells, core data is available in a limited number of wells. However, most wells have well-log data. In the present study, intelligent computing neural networks, which are widely used nowadays in the petroleum industry, were used to predict porosity and permeability in the Asmari Formation. The MATLAB software was used to process neural networks for core and well logs data, including porosity and permeability. These networks were developed using an error backpropagation algorithm within feed-forward networks. After comparing the measured and network-predicted results, the parameters of the artificial neural networks (ANN) were adjusted for a desired network. The correlation coefficient between the core results and the ANNpredicted porosity and permeability were 0.92 and 0.82, respectively. These results show that intelligent neural network models predicted porosity and permeability accurately. Finally, the above-mentioned networks were generalized to a third well that had no core data.