Target-Oriented Time-Lapse Elastic Full-Waveform Inversion Constrained by Deep Learning-Based Prior Model

Time-lapse (TL) seismic monitoring plays a vital role in reservoir characterization and management. Elastic full-waveform inversion (EFWI) has been applied to TL seismic data to allow for a quantitative estimation of time-varying elastic properties. However, the high-resolution inversion can be computationally intense and ill-posed. To estimate the high-resolution TL changes at a reasonable cost, we utilize two key techniques for the inversion: 1) we develop an elastic redatuming approach to retrieve the virtual elastic data for both base and monitor data at the target level using mainly a kinematically accurate velocity, thus reducing the computational cost by focusing the high-resolution inversion on the target zone, and 2) we integrate high-resolution well information and seismic data in the target-oriented inversion, where a high-resolution prior model is predicted by deep learning to regularize the inversion. A deep neural network (DNN) is capable of learning the mappings between the TL seismic estimation and the facies interpreted from well information after the training process. Thus, we can derive a prior model for TL changes by mapping the facies characterized by the property changes to the target inversion domain. We then implement the target-oriented TLEFWI regularized by the prior model, where the redatumed TL elastic data and the prior model jointly contribute to the inversion result. The numerical examples validate that the proposed approach enables us to retrieve the TL changes of elastic property in the target zone with improved resolution and well consistency.