On Mining Satellite and other Remotely Sensed Images

Advanced data mining technologies and the large quantities of Remotely Sensed Imagery provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data sets composed of images and associated ground data, can be of importance in precision agriculture, community planning, resource discovery and other areas. However, in most cases the image data sizes are too large to be mined in a reasonable amount of time using standard methods. A new spatial data organization, bit Sequential organization (bSQ) and a new “data-mining ready” data structure, the Peano Count Tree (Ptree) provide a lossless and compressed representation of image data which facilitate association rule mining, classification and other data mining techniques markedly. In this paper we propose a new model for association rule mining and classification on spatial datasets using Ptrees. Experimental results show the new model applies well to data mining on Remotely Sensed Imagery data.