Using
digital elevation model (DEM) data, its derivatives, and forest cover data, we
constructed neural networks to classify 27 land ecosystem classes at Duck
Mountain, Manitoba, Canada in
1995. Training and testing of
those neural networks were done using an existing land-systems map prepared
through airphoto interpretation and field studies. The method can increase classification accuracy by 10-30%
with a limited database compared to traditional methods. Land ecosystems classification provides
data set used to represent the spatial patterns of landscape physical
properties. With these land
systems classification results people can exploit land resources more
effectively.
Please go back my main homepage