Wave breaking is a ubiquitous phenomenon in ocean dynamics, serving as a critical conduit for the exchange of momentum, heat, and energy between the atmosphere and the ocean. Although its vital role in air-sea moisture exchange is widely acknowledged, quantifying its exact impact on moisture flux remained quite challenging due to data limitations and the inherently turbulent nature of the process. To overcome these challenges, we construct a comprehensive 10-year global dataset that incorporates multiple breaking wave variables, informed by statistical breaking theories, to capture the intricacies of the breaking process and its consequential effects. We then employ a stacked machine learning model to elucidate the complex relationships between wave breaking and moisture flux. The performance of our stacked model, which is enriched with breaking wave variables, is validated against the fifth-generation European Centre for Medium-Range Weather Forecasts reanalysis data (ERA5). The results offer excellent predictions and highlight the importance of breaking-wave-related variables in regulating moisture flux, thereby substantiating the integral role of wave breaking in modulating air-sea interactions and moisture transport.