1887

Abstract

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 CO 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 CO 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.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202639092
2026-03-09
2026-02-11

  • From This Site

    /content/papers/10.3997/2214-4609.202639092
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Baklid, A., Korbøl, R. and Owren, G. [1996]. Sleipner Vest CO2 disposal, CO2 injection into a shallow underground acquifer. SPE Annual Technical Conference and Exhibition, Denver.
     [Google Scholar]
  2. Di, H., Li, Z. and Abubakar, A. [2022]. Using relative geologic time to constrain convolutional neural network-based seismic interpretation and property estimation. Geophysics, 87.
     [Google Scholar]
  3. HaveliaK., ManralS., Borgos, H.G. and FreemanS. [2022]. Integrated machine learning and physics-based workflows for rapid qualitative and quantitative insights on monitoring carbon capture and sequestration. First Break, 40 (10), 69–77.
     [Google Scholar]
  4. Kumar, S., Shekhar, S., Osabuohien, O.J., Salomia, G., Hasan, H., Assaf, G., Tran, D., Mihai, M.M., Velikanov, I., Biniwale, S. and MustaphaH. [2025]. Enhancing Seismic 2D and 3D Data Conditioning by Leveraging Machine Learning. International Petroleum Technology Conference, Kuala Lumpur, Malaysia.
     [Google Scholar]
  5. Li, Z. [2023]. Optimization of Relative Geological Time Derived From Flow Field - A Label Free Approach. SEG Technical Program Expanded Abstracts, 1103–1107.
     [Google Scholar]
  6. ManralS. [2020]. Enhancing Fault Interpretation Efficiency and Accuracy with Deep Convolutional Neural Network and Elastic Cloud Compute. First EAGE Digitalization Conference and Exhibition, Volume 2020, 1–5.
     [Google Scholar]
  7. Sarajaervi, M., Hellem Bo, T., Goledowski, B. and Nickel, M. [2020]. Robust Evaluation of Fault Prediction Results: Machine Learning Using Synthetic Seismic, First EAGE Digitalization Conference and Exhibition, Volume 2020, 1–5.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202639092
Loading
Automated Time-Lapse Seismic Analysis for CCS Monitoring Enabled by Relative Geological Time Workflow
Conference Proceedings 2026, 1 (2026); https://doi.org/10.3997/2214-4609.202639092
/content/papers/10.3997/2214-4609.202639092
/content/papers/10.3997/2214-4609.202639092
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error