Deep Learning Accelerated Blind Seismic Acoustic-Impedance Inversion

Blind seismic acoustic-impedance (AI) inversion is a technique for obtaining the AI of the subsurface medium without being given a wavelet. An effective way to solve the blind inversion problem is to split the multiparameter problem into two single-parameter subproblems and solve them in an alternative iteration way. However, this method becomes time-consuming when dealing with large-scale 3-D problems and faces challenges in selecting suitable regularization parameters. To overcome these shortcomings, we propose a deep learning accelerated blind seismic AI inversion (DLA-BSAII) method. It mainly has three steps. First, only a few 2-D profiles are selected from the whole 3-D data, and their corresponding AI models and wavelets are inverted using the conventional blind seismic AI inversion method. Second, the results of the first step are used to train deep networks to realize the nonlinear mapping from a 2-D seismic profile to AI and wavelet. In addition, the trained deep networks are used to generate predictions of AI models and wavelets for the remaining 2-D profiles. Third, benefiting from the predicted AI models and wavelets, a new alternative iteration method with fewer but more effective regularization terms is proposed to obtain the final inverted AI models and wavelets of the remaining 2-D profiles. It has the advantages of easier selection of regularization parameters and faster convergence speed. Synthetic and field data examples verify that DLA-BSAII outperforms conventional methods in terms of both efficiency and inversion accuracy.