Automated Time-Lapse Seismic Analysis for CCS Monitoring Enabled by Relative Geological Time Workflow

Summary The study highlights the application of a fully automated workflow for time-lapse seismic analysis to enhance the monitoring of carbon capture and storage (CCS) operations. By leveraging the Relative Geological Time (RGT) algorithm integrated with machine learning (ML)-based seismic inversion techniques, the workflow enables rapid and accurate insights into CO2 plume migration and subsurface changes. The RGT algorithm establishes a chronostratigraphic framework that aligns with seismic reflectors, ensuring geologically consistent and reliable interpretations. This automated workflow offers significant advantages for CCS monitoring, including reduced turnaround time, improved repeatability, and cost-effectiveness. By eliminating the need for manual interpretation and requiring only seismic volumes and well logs as input, the process enabled faster and more informed decision making. Additionally, the integration of RGB blending techniques with RGT-derived horizons improves the visualization of plume movement, providing a clearer understanding of spatial and temporal changes in CO2 distribution. In conclusion, this innovative workflow paves the way for the future integration of intelligent agents capable of autonomously processing incoming time-lapse seismic data using pre-trained machine learning models, improving the speed, efficiency, and accuracy of CCS monitoring operations.