Segmenting gas bubbles in multiphase flows is a critical yet unsolved challenge in numerous industrial settings, from metallurgical processing to maritime drag reduction. Traditional approaches — and most recent learning-based methods — assume near-spherical shapes, limiting their effectiveness in regimes where bubbles undergo deformation, coalescence, or breakup. This complexity is particularly evident in air lubrication systems, where coalesced bubbles form amorphous and topologically diverse patches. In this work, we revisit the problem through the lens of modern vision foundation models. We cast the task as a transfer learning problem and demonstrate, for the first time, that a fine-tuned Segment Anything Model (SAM v2.1) can accurately segment highly non-convex, irregular bubble structures using as few as 100 annotated images.

The global energy transition requires novel carbon utilization methods to enable integrated and optimized low-carbon energy production. Coupling CO₂-based geothermal energy extraction with CO₂-enhanced oil recovery (EOR) represents a promising yet largely unexplored approach for improving resource efficiency and carbon sequestration. This study investigates the integration of CO₂-Plume Geothermal (CPG) energy production with CO₂-EOR in mature oil reservoirs using numerical simulations of conceptual heterogeneous reservoir models. The interplay between EOR and CPG performance in terms of energy production and CO₂ storage is evaluated and compared to understand the geotechnical implications of this integration. The analysis highlights that initiating CPG operations after EOR significantly benefits from the established CO₂ plume, facilitating immediate and efficient geothermal energy extraction. Results show that integrating CPG with EOR increases total energy recovery by 20%–50% relative to the energy produced by EOR alone, yielding CPG thermal power outputs ranging from 13 to 23 MW_th/km². Continued CO₂ injection during CPG operations further increases total CO₂ storage by 80%–280%, driven primarily by improved volumetric sweep of previously unswept reservoir volumes and enhanced CO₂ density resulting from reservoir cooling. While reservoir heterogeneity strongly influences oil recovery during EOR, its effect on CPG thermal output is less pronounced, since native reservoir fluids (oil and brine) have already been largely displaced during the EOR stage, and the CO₂ plume gradually stabilizes over time. These findings demonstrate the viability and advantages of integrated CO₂-EOR and CPG systems, offering insights into novel methods essential for sustainable subsurface resource management and climate-change mitigation.