BubbleSH: A Dataset of Rising Bubbles with Deformable Interfaces

2026-07-08

AI Summary

This work addresses the challenge of modeling multiscale dynamics of deformable bubbles in multiphase flows, which has been hindered by the lack of high-quality, lightweight datasets capturing morphological evolution. To this end, we introduce BubbleSH, a novel dataset generated from high-fidelity direct numerical simulations of three-dimensional bubble swarms, where bubble shapes are compactly represented using spherical harmonics. BubbleSH provides the first lightweight benchmark that incorporates deformable interfaces and strongly coupled interactions, enabling generative modeling and the study of chaotic multiphase systems. We further propose an equivariant probabilistic simulator tailored for trajectory and morphology prediction, along with dedicated evaluation metrics, demonstrating its effectiveness in forecasting the future state distribution of bubble ensembles and establishing a new data-driven benchmark for multiphase flow simulation.

Abstract

Bubbly flows exhibit complex multiscale dynamics, with deformable bubbles interacting through the surrounding liquid and giving rise to strongly coupled kinematic and morphological behavior. We present BubbleSH, a bubbly flows dataset consisting of transient, three-dimensional bubble-swarm dynamics obtained from high-fidelity direct numerical simulations of bubbles rising in a periodic domain. The dataset provides time-resolved bubble trajectories, velocities, and shape evolution, with bubble morphology compactly represented using spherical harmonics. Designed to be lightweight yet physically expressive, the dataset enables data-driven modeling of bubbly flow simulators where shape deformation and bubble-bubble interactions play a central role. We characterize the dataset with bubble kinematics, morphology, and interaction patterns, and introduce evaluation metrics for both trajectory and shape prediction. The sensitivity of bubble-swarm dynamics to local perturbations makes BubbleSH particularly well suited to generative models that learn distributions over possible future trajectories. We evaluate a permutationally and translationally equivariant probabilistic emulator on BubbleSH given the proposed metrics. Therefore, we establish a compact, high-fidelity dataset and a benchmark for developing and evaluating data-driven models of deformable, chaotic multiphase systems.

Problem

• bubbly flows
• deformable interfaces
• bubble dynamics
• multiphase systems
• shape deformation

Innovation

• spherical harmonics
• deformable interfaces
• bubbly flows
• data-driven modeling
• equivariant generative models