High-resolution acoustic-impedance inversion based on a deep-learning-aided representation model of nonstationary seismic data

Abstract

Building a high-resolution acoustic-impedance (AI) model based on nonstationary seismic data plays a key role in reservoir predictions. However, the common AI inversion methods are faced with two main shortcomings. First, because of the nonstationary feature of seismic data, a multi-parameter inverse problem should be considered, to not only estimate AI but also to estimate a time-varying wavelet or a quality factor (Q) model, leading the problem to be more ill-posed. Second, the resolution of the estimated AI is limited due to the band-limited nature of nonstationary seismic data. To address these issues, we propose a new nonstationary seismic AI inversion method. Notably, we propose a deep-learning-aided representation model to replace the nonstationary convolution model to solve the forward problem in inversion. Benefiting from multi-source information (seismic data and well-log data), and the powerful nonlinear function fitting ability of deep learning, this model can map high-resolution AI to band-limited nonstationary seismic data without requiring a time-varying wavelet or a quality factor model. A new deep learning architecture is proposed for processing the spatio-temporal seismic data with better accuracy. In addition, total-variation (TV) regularization is adopted to enforce a physically reasonable AI model. Both 3D synthetic data and field data experiments are conducted, and their results clearly demonstrate that the proposed method has significant advantages over other common methods in building a high-resolution AI model.