monitoring, especially under the challenges of climate change. Traditional field-based surveys are costly, labor-intensive, and difficult to implement at large scales, while optical remote sensing and synthetic aperture radar (SAR) methods, though effective, remain constrained by specific limitations. Recently, Global Navigation Satellite System Reflectometry (GNSS-R) has emerged as a promising alternative, offering continuous, low-cost, and all-weather observations. Reflected GNSS signals from vegetation provide structural and density-related information that can be used to infer biophysical parameters such as biomass. This study evaluates the potential of machine learning algorithms for estimating vegetation biomass in northern Vietnam using GNSS-R data collected by the CyGNSS satellite constellation. Results indicate a strong correlation (up to 0.99) between GNSS-R signal features and biomass density. The findings highlight the effectiveness of GNSS-R combined with machine learning for rapid, scalable, and continuous biomass monitoring, with implications for forest resource management and climate change research