Smarter carbon storage powered by AI.

Smarter Carbon Storage Powered by AI

At Geoquest, we’re developing an advanced AI-driven framework to revolutionize how we validate geological carbon storage sites. Traditional methods are costly and slow. Our machine learning approach accelerates site validation, reduces risk, and dramatically cuts early-stage exploration costs.

  • The Challenge

    Identifying reliable carbon storage sites is critical to scaling global carbon sequestration. Current workflows involve expensive and time-consuming seismic surveys, well analysis, and geochemical testing, often yielding uncertain results.

  • Our Solution

    We’re creating a machine learning model that integrates:

    • 2D and 3D Seismic Attributes
    • Stratigraphic Well and Core Data
    • Geochemical and Compositional Signals
    • InSAR Surface Deformation (where data is available)

    Combining these diverse datasets, the AI model will accurately assess reservoir suitability and predict CO₂ injectivity, even with partial data. Unlike black-box systems, our model is designed to be fully interpretable by geoscientists and engineers.

  • Why It Matters

    • Accelerated Site Discovery: Faster and more accurate screening of viable carbon storage locations
    • Cost Reduction: Cuts exploration costs compared to conventional methods
    • Reduced Uncertainty: Quantifiable improvements in prediction confidence
    • Knowledge Generation: Links between surface signals and subsurface behavior provide a new foundation for understanding geomechanical dynamics
  • Expected Outcomes

    • A validated, field-calibrated AI tool for early-stage CCS reservoir evaluation
    • Potential peer-reviewed publications or patents
    • Continued development under Simpson Energy with recognition for contributing inventors

Join the Geoquest mailing list.