Prestack Waveform Inversion and Neural Network Interpolation - a Two-Step Approach to Log Prediction

G-16 PRESTACK WAVEFORM INVERSION AND NEURAL NETWORK INTERPOLATION - A TWO- STEP APPROACH TO LOG PREDICTION Abstract 1 AUGUST LAU 1 ALFONSO GONZALEZ 2 SUBHASHIS MALLICK 2 and DIANA GILLESPIE 2 We present a two-step approach to predict log information. In the first step nonlinear prestack waveform inversion is used to estimate VP VS and density from the prestack seismic data. This estimation is useful in areas with little or no well control as well as in mature basins where log information might be available but might not be complete. In the second step a neural network is used to