Detecting temporal changes in satellite imagery using ANN

One of the most interesting aspects of the world is that it can be considered made up of patterns. In the most pattern recognition problem pattern have a dynamic nature and non-adaptive algorithms (instruction sets) will fail to give a realistic solution to model them. In these cases, adaptive algorithms are used and among them, neural networks have the greatest hit. For example, the defense applications very frequently need to record, detect, identify and classify images of objects or signals coming from various directions and from various sources - static or dynamic. There are many applications in remote sensing where study of dynamic data is needed such as deforestation, effects of natural and man made disasters, migration in the paths of rivers due to the dynamic nature of Earth's plates. Artificial Neural Networks (ANN) can play a role in modeling such applications because of their capability to model nonlinear processes and to identify unknown patterns and images based on their learning model, or to forecast certain outcomes by extrapolation. In this study we present results on classifying the images using SOFM classification and detect temporal changes in patterns.