Neural inversion for oil saturation from seismic velocities

The degree of oil saturation has been estimated from velocity measurements of unconsolidated sediments in a laboratory environment using a petrophysical model and artificial neural network (ANN). Velocities, Vp, Vs, and their ratio Vp/Vs, (inputs to ANN) as well as the oil saturation level (output) of unconsolidated materials from an oil field were measured. The ANN is trained with simulated data based on a petrophysical model. The weighting coefficients developed from the training arc then used to invert for the unknown oil saturation level given the laboratory measured velocities. Simultaneous use of Vp, Vs and Vp, Vs, as input variables to the network in training the network give more accurate predictions than when say, Vp, Vs is used individually as input attribute in the inversion process. The results show a good match between the neural network-predicted and the measured degree of oil saturation.

Duke Scholars

Author Fred K. Boadu Civil and Environmental Engineering