Abstract: Water vapor is an important component of the Earth's atmosphere. Although water vapor accounts for a small proportion of the atmosphere, it varies greatly in space and time, and thus plays an essential role in the formation and evolution of disastrous weathers. GNSS tomography can effectively obtain the three-dimensional (3D) distribution of water vapor with high precision and high spatiotemporal resolution, which has become a research focus of GNSS meteorology. In addition, satellitebased water vapor detection technology can provide a wide range of water vapor images, especially geostationary satellites with the advantages of wide spatial coverage and good temporal continuity, making them an important data source for water vapor monitoring research. In this study, we establish the tomography model by integrating Fengyun-4A (FY-4A) water vapor products and GNSS observation data. Tomography experiments are carried out using the observation data of Hunan Continuously Operating Reference Stations (HNCORS) to obtain the 3D distribution field of water vapor density in Hunan Province with high spatiotemporal resolution. The tomographic results are fully validated by GNSS and reanalysis data. In addition, based on the tomographic water vapor products, the multi-parameter neural network prediction model of rainfall area is constructed in this study, which further explores the application potential of water vapor tomography technology in rainfall prediction. This study will promote the improvement of monitoring and prediction capabilities for heavy rain and other disaster weather and has a great significance for flood monitoring in water projects.