Segmenting the complex and irregular in two-phase flows: A real-world empirical Study with SAM2

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. • Fine-tuned SAM2.1 model for bubble segmentation in complex two-phase flows, achieving high accuracy quantitive data with minimal data. • Reached F1 and Dice scores near 0.95 for medium and large bubbles using only 100 annotated images. • Introduced a data-efficient alternative to traditional methods that often struggle with generalization. • Enabled automated extraction of quantitative bubble characteristics (size, area fraction, and spatial distribution) to support measurement-driven analysis in multiphase flow studies. • Released labeled dataset and fine-tuning pipeline to promote low-effort, accurate segmentation in multiphase flow studies.