Joint physics-based and data-driven time-lapse seismic inversion: Mitigating data scarcity

Abstract

In carbon capture and sequestration (CCS), developing rapid and effective imaging techniques is crucial for real-time monitoring of the spatial and temporal dynamics of CO2 propagation during/after injection. We propose an efficient “hybrid” time-lapse workflow that combines physics-based full-waveform inversion (FWI) and data-driven machine- learning (ML) inversion. The developed hybrid methodology simultaneously predicts the variations in velocity and satura- tion and achieves a high spatial resolution in the presence of realistic noise in the data. The method is validated on a syn- thetic CO2 -sequestration model based on the Kimberlina stor- age reservoir in California. The scarcity of the training data with the ML algorithm is addressed by developing a new data- generation technique with physics constraints. The proposed approach synthesizes a large volume of high-quality, physi- cally realistic training data, which is critically important in ac- curately characterizing the CO2 movement in the reservoir.