Abstract: A new method applying an Artificial Neural Network (ANN) to retrieve high-resolution atmospheric profiles in the troposphere is presented. The use of satellite data for studing the atmosphere employing the GPS (Global Positioning System) data opens perspectives to improve the research on climate and the capacity on weather forecast. From this consideration, many techniques were developed for retrieving atmospheric profiles (temperature, pressure, and water vapor) using GPS radio occultation. The technique with ANN application establishes a non-linear relation with the meteorological variables. Profiles retrieved by the ANN using meteorological data from the CHAMP-ISCD (Challenging Mini-satellite Payload for Geoscientific Research and Application). It can be concluded that ANN is convenient and accurate tool to get atmospheric profiles.