Prestack seismic inversion for elastic parameters using model-data-driven generative adversarial networks

Abstract

Model-data-driven (MDD) generative adversarial networks (GANs) using prestack seismic data to estimate elastic parameters are proposed. First, by traverse sampling of elastic parameter model space and Gaussian sampling, a complete elastic parameter data set is generated. Second, several reflection coefficient sequences are constructed to produce synthetic prestack amplitude-versus-angle (AVA) gathers using the Zoeppritz equations. Third, conditional GANs (CGANs) are trained using synthetic data sets to establish a relationship between the synthetic prestack AVA gathers and elastic parameters. By using low-frequency constraints, the absolute values of the elastic parameters from the prestack AVA gathers are computed. To apply the networks trained with synthetic to field seismic data, Gaussian noise is added to the synthetic prestack AVA gathers of the training data set. Synthetic prestack AVA gathers with different signal-to-noise ratios are used to verify the robustness of the proposed method and explore its generalization to field seismic data. By testing MDD-CGANs applied to a 2D elastic parameter model, the inversion results by MDD-CGANs are closer to the true values than those by the limited-data-driven CGANs and fully convolutional networks. By applying MDD-CGANs to field prestack AVA gathers in the Tarim Basin, West China, more accurate and high-resolution results are obtained than those obtained using the conventional prestack amplitude-variation-with-offset elastic parameters inversion approach.