Neural network-based cloud detection/classification using textural and spectral features

An efficient and robust neural network-based scheme is introduced in this paper to perform automatic cloud detection and classification. An unsupervised Kohonen neutral network was used to classify, the cloud contents of a 8/spl times/8 blocks in an image into ten different cloud classes. Inputs to the network consisted of textural features of each block obtained using an efficient feature extraction scheme namely, the wavelet transform (WT). This scheme not only reduces the dimensionality of the data but also extracts useful features of the data. To improve the detection rate and reduce the false positive rate, especially for low clouds and thin high clouds, a multi-channel fusion system was constructed to combine the results of different optical bands. All alternative approach for automatic cloud detection/classification based on multi-spectral features was also studied to analyze and compare the effectiveness of multi-spectral-based scheme vs textural-based scheme. The results using high resolution GOES 8 data show the promise of the Kohonen neural network when used in conjunction with WT as feature extractor for cloud detection/classification.