Predicting oil saturation from velocities using petrophysical models and artificial neural networks

The degree of oil saturation has been estimated from velocity measurements of unconsolidated sediments at a laboratory scale using a petrophysical model and artificial neural network (ANN) as an inversion tool. Laboratory measurements of velocities, Vp, Vs and their ratio Vp/Vs as well as the oil saturation levels of unconsolidated materials from an oil field were performed and the data were analyzed. It was observed that the ratio Vp/Vs increase with an increase in temperature for all saturation level. Beyond a critical saturation level (Soil=40%), Vp increases with an increase in temperature while Vp/Vs decreases with an increase in temperature. An ANN is trained with simulated data based on the petrophysical model. The weighting coefficients developed from the training are 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 or Vs is used individually as input attribute in the inversion process. The results show a good match between the predicted and the measured degree of oil saturation.