Neural net classifier for satellite imageries

Accurate identification of cloud type is an important aspect of weather forecasting. One of the primary application of the remotely sensed cloud cover data is to provide synoptic cloud cover information over extensive data-sparse regions; particularly the oceans and deserts. In south-east Asia, information on cloud cover data are obtained from the infrared and visible channels of Geostationary Meterological Satellite. These imageries contain data of clouds. By extracting the textural features embedded in the images, information on cloud types can be derived and mapped spatially. An artificial neural network is used as a classifier to identify different cloud types through comprehensive training cycles. The architecture of the network used in the present study is multi-layered with feedforward and backpropagation. The study makes use of a classification scheme based on the SYNOP code of the World Meterological Organization (WMO). The average cloud classification accuracy obtained in this study is 40%.