Application of Neural Network Technique for Facies-Controlled Modeling in Block Fa2 of Shanian Oilfield

Artificial neural network technique has been widely used in the reservoir characterization at present time. With the advantage of nonlinear computing and self-error correction, it can assist petroleum engineers in solving some complex reservoir engineering problems, such as formation porosity prediction from geophysical well logs with accuracy comparable to actual core analysis and interpretation. Based on the classification analysis for the sedimentary microfacies and the estimation for the petrophysical property by using the BP neural network, combining with the thought of facies-controlled modeling, this paper presents a reasonable and valuable method to establish the 3D reservoir model, which could provide significant geological and geophysical basis for the further research of improving recovery ratio and the potential of residual oil. The result of the research indicates that the method is quite effective and gets satisfying prediction precision for the petrophysical property in reservoir modeling.