Abstract: Artificial Neural Network (ANN) is applied to estimate humidity profiles of high resolution. The use of satellites together GPS (Global Positioning System) data to supply data to study the atmosphere opens perspectives to improve the research on climate and the capacity on weather forecast. In this sense, many techniques were developed for retrieving atmospheric profiles (temperature, pressure and water vapor) using GPS radio occultation. A new method based on ANN to retrieve water vapor profiles is presented. In this paper, a fully connected multi-layer network is constructed. By comparing the retrieved profiles with the corresponding ones from the CHAMP-ISCD (Challenging Mini-satellite satellite Payload for Geoscientific Research and Application), it can be concluded the ANN is convenient and an accurate tool to get humidity profiles. This method constructs humidity profiles. These retrieved profiles of water vapor pressure profiles presents bias of 0.06 hPa and maximum standard deviation of 0.75 hPa. These results can be employed to the atmospheric data assimilation to improve the initial condition of the models of Numerical Weather Prediction (NWP).