Artificial neural network applications on remotely sensed imagery

Huge amount of remotely sensed imagery data provide the possibility and challenges to extract knowledge from them. In this paper, we propose a model for using artificial neural networks to perform unsupervised learning on remotely sensed imagery. This model generates self-organizing maps (SOM) based on remotely sensed imagery and related data such as yield, nitrate, and moisture. It correlates these maps and projects these output into a SOM. In addition, it uses wavelets for data pre-processing. The model also derives important rules. The entire model is implemented as a distributed system using CORBA. Performance analysis shows the model is efficient and effective for performing clustering on remotely sensed imagery.