Landcover change modeling through visualization and classification enhancement of multi-temporal imagery

The natural environment endures natural and human-induced changes. Remote sensing has been providing monitoring oriented solutions by a series of methodologies which contribute to prudent environmental management. Analysis of multi-temporal satellite images for the observation of the land changes often includes error prone classification and change-detection techniques. The present study takes advantage of the temporal continuity of multi-temporal classified images, in order to model change trends and reduce classification uncertainty, based on reasoning rules. By revealing misclassification prone areas, training site selection is targeted. Moreover, computational tools are developed in order to disclose the alterations in land use dynamics and offer spatial reference to the pressures that land use classes impose. The proposed procedures are tested upon Landsat time series imagery, depicting the National Park of Ainos in Kefallinia, Greece.