Temporal super-resolution of cavitating hydrofoil velocity fields via few-shot learning with low-cost phase information

In fluid experiments, obtaining velocity fields at high temporal resolution is often prohibitively expensive. This study introduces a semi-supervised deep learning framework that leverages low-cost, high-speed cavitation phase imaging to eliminate the need for high-frequency velocity labels. Applied to cavitating hydrofoil flows, the method reconstructs temporally super-resolved velocity fields from sparse, low-frequency samples and demonstrates robust generalization under unsteady conditions. These results highlight an efficient and economical approach for modeling complex multiphase flows.