Detection of low density natural forest in the Andes region using LANDSAT 8 imagery

抄録

Andean ecosystems in South-America are among the most diverse and threatened ecosystems in the world. Due to a long history of exploitation that still continues, the remaining natural forests in the Andes region are relict tree populations in inaccessible locations and open forests with low density of individuals.This study aims determine the best variables for detection and classification of Andean natural forests of low density by remote sensing techniques and to make a comparison of different classification techniques to determine the best classification method.Field data on Andean forest condition was gathered by plotless sampling survey in several locations in the department of Cuzco, Peru. We collected training data for land use classification analysis by using spectral mixture analysis and compare it with a classic random forest classification approach.