A temporal adaptive probability neural network for cloud classification from satellite imagery

Cloud classification from satellite imagery is an important but very difficult task. Temporal changes are one of the main factors that cause degradation in the classifier performance when a sequence of imagery is to be processed A probability neural network (PNN)-based cloud classification system and its temporal updating scheme is proposed in this paper. This novel approach can track the temporal changes in the images by utilizing the temporal contextual information and adjust the neural network to adapt to such changes. The maximum likelihood (ML) criterion is adopted in both the training and updating schemes, and the well-known expectation-maximization (EM) approach is employed to achieve this goal. The proposed scheme is examined on the Geostationary Operational Environmental Satellite (GOES) 8 satellite cloud imagery and the results are promising. The proposed temporal updating scheme can also be applied to a number of other important applications where spatial-temporal classification of a sequence of images is needed.