Neural networks and their applications in lithostratigraphic interpretation of seismic data for reservoir characterization

Modern 3D seismic data and the associated extracted attributes have allowed better description of reservoir heterogeneities and more realistic assessment of hydrocarbons in place. However, the establishment of a complicated nonlinear relationship between seismic attributes and reservoir properties has been a major challenge for working geoscientists. Recently, supervised neural networks have been used for predicting reservoir properties away from the boreholes in interwell regions after establishing the relationship between seismic attributes and well-log data. The effectiveness of these neural network techniques in 3D seismic interpretation is demonstrated in this paper through a real data example from India's Cambay Basin.