An inverse algorithm was developed to profile the vertical structure of temperature and humidity using a feed-forward neural network. Numerous simulations using the inverse algorithm (inverse model) have been conducted and compared with various existing independent techniques. The inverse model is highly efficient at profiling the temperature and humidity vertical structure compared to the existing conventional approaches. The statistical methods notorious for their high computational, altitude-dependent error and inability to retrieve the vertical temperature and humidity profiles are diminished when the inverse model is used. The inverse model’s diurnal and seasonal cycle profiles are also superior to those of other independent existing methods, which may be helpful for assimilation in numerical weather forecast models. We suggest that incorporating such an inverse model into the ground-based microwave radiometer (GMWR) will improve the quality of temperature and humidity profiles and weather forecasting. The developed inverse model has a resolution of 50 meters between the surface to 500 meters and 100 meters between 500-2000 meters, and 500 meters beyond 2000 meters.