[1][2] The systematic mapping of land cover patterns, including change detection, often follows two main approaches: Image pre-processing is normally done through radiometric corrections, while image processing involves the application of either unsupervised or supervised classifications and vegetation indices quantification for land cover map production.
However, the user defines the number of classes for which the computer will automatically generate by grouping similar pixels into a single category using a clustering algorithm.
Most of these indices make use of the relationship between red and near-infrared (NIR) bands of satellite images to generate vegetation properties.
Several vegetation indices have been developed; scientists apply these via remote sensing to effectively classify forest cover and land use patterns.
These spectral indices use two or more bands to accurately acquire surface reflectance of land features, thereby improving classification accuracy.