Cloud top height plays an important roll in the energy budget and is also important for aviation. This thesis concerns the quality control of cloud top height (CTH) retrievals. The approach for quality controlling retrieved CTH has been using the forward simulating software RTTOV. An error estimation function has been developed as well as an investigation to what simplifications can be done regarding the forward simulations for CTH purposes at SMHI. The purpose of the error estimation function is to validate CTH output from CTH retrieval algorithms by giving a rough error estimate of the retrieved CTH compared to what forward simulations predict. For simplifying the forward simulations the most promising results have been shown for lower clouds. Further testing is still of interest and for future work suggestions are provided regarding the error estimation function as well as for simplifying the forward simulations.

In this thesis the predictive models the multilayer perceptron and random forest are evaluated to predict cloud top pressure. The dataset used in this thesis contains brightness temperatures, reflectances and other useful variables to determine the cloud top pressure from the Advanced Very High Resolution Radiometer (AVHRR) instrument on the two satellites NOAA-17 and NOAA-18 during the time period 2006-2009. The dataset also contains numerical weather prediction (NWP) variables calculated using mathematical models. In the dataset there are also observed cloud top pressure and cloud top height estimates from the more accurate instrument on the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) satellite. The predicted cloud top pressure is converted into an interpolated cloud top height. The predicted pressure and interpolated height are then evaluated against the more accurate and observed cloud top pressure and cloud top height from the instrument on the satellite CALIPSO. The predictive models have been performed on the data using different sampling strategies to take into account the performance of individual cloud classes prevalent in the data. The multilayer perceptron is performed using both the original response cloud top pressure and a log transformed repsonse to avoid negative values as output which is prevalent when using the original response. Results show that overall the random forest model performs better than the multilayer perceptron in terms of root mean squared error and mean absolute error.