Automated supervised land use classification and change detection: An image fusion based approach

The ability to rapidly identify and exploit large area land use change over time using high resolution multispectral data was investigated. An image fusion based automated supervised land use classification and change detection algorithm was developed. The algorithm leverages the accuracy and stability of a coarser resolution MODIS product to achieve an automated higher resolution Landsat based product that can be rapidly implemented to cover large regions of interest. Through the fusion of two publicly available data sources, a superior higher resolution land classification product was obtained. The classifier´s training data was autonomously quality controlled through the use of both spatial and spectral processing steps to further enhance algorithm performance. This effort demonstrated a novel methodology that is easily scalable across various spatial resolutions and can be applied to numerous earth observing systems and application areas.