Temporal updating scheme for probabilistic neural network with applicationto satellite cloud classification

In cloud classification from satellite imagery, temporal change in the imag es is one of the main factors that causes degradation in the classifier per formance. In this paper, a novel temporal updating approach is developed fo r probabilistic neural network (PNN) classifiers that can be used to track temporal changes in a sequence of images. This is done by utilizing the tem poral contextual information and adjusting the PNN to adapt to such changes . Whenever a new set of images arrives, an initial classification is first performed using the PNN updated up to the last frame while at the same time , a prediction using Markov chain models is also made based on the classifi cation results of the previous frame. The results of both the old PNN and t he predictor are then compared. Depending on the outcome, either a supervis ed or an unsupervised updating scheme is used to update the PNN classifier. Maximum likelihood (ML) criterion is adopted in both the training and upda ting schemes. The proposed scheme is examined on both a simulated data set and the Geostationary Operational Environmental Satellite (GOES) 8 satellit e cloud imagery data. These results indicate the improvements in the classi fication accuracy when the proposed scheme is used.