Skip to Main Content
In this paper a multilayer perceptron neural network is used to retrieve vertical atmospheric temperature profiles from satellite radiation data. The training set consists of data provided by the direct model characterized by the radiative transfer equation (RTE) and by real radiation data from the NOAA-HIRS/2 (high resolution infrared radiation) sounder. The retrieved vertical temperature profiles are compared to radiosonde measured data. The neural network performance is compared to the results of the projects by J.C. Carvalho et al (1999) and by F.M. Ramos et al (1999) who used regularization techniques. Neural network approaches are especially advantageous due to the embed parallelism that may imply in faster vertical temperature profiles retrieving systems.