arXiv:2606.17180v1 Announce Type: new Abstract: This chapter discusses how a data-driven machine learning approach can reproduce key aspects of the physical behavior of multiphase flows in complex geological formations. We propose an end-to-end graph neural surrogate tailored to CO$_2$ plume migration forecasting in geological storage. The method is evaluated on the SPE11A benchmark, a well-known industry test case designed to assess CO$_2$ storage scenarios and characterized by sharp gas-water interfaces, strong advective transport, and rapid convective mixing with fingering development. The
The increasing maturity of GNNs combined with urgent demands for scalable and accurate CO2 storage monitoring solutions drives this development.
Accurate and fast forecasting of CO2 migration is critical for the safe and effective implementation of carbon capture and storage (CCS) projects, which are essential for climate mitigation efforts.
This breakthrough offers a potential pathway to significantly accelerate CO2 storage site assessment and operational monitoring, reducing costs and risks compared to traditional simulation methods.
- · Carbon capture and storage industry
- · Geological survey companies
- · Machine learning researchers
- · Energy transition investors
- · Traditional geological simulation software vendors (if they fail to adapt)
- · Companies relying solely on slow, computationally intensive modeling
Faster and more reliable CO2 storage operations become possible, accelerating CCS deployment.
Increased investor confidence in CCS projects leads to greater capital allocation and scaling of the industry.
Improved CCS technology could alter global energy policy and potentially impact the price stability of carbon credits.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG