Skip to main content
ediopen

Southern Appalachia NLCD Landcover

Satellite imagery (mosaicked +ETM and TM imagery satellite imagery from late 2005 through mid-2006) were downloaded from the web for spring, leafoff, and leafon conditions (Fig. 2). From these layers we derived tasseled cap bands 1,2,3. Other data used included digital elevation models (DEMs), DEM slope calculations, and 2006 NAPP DOQQs (used for training sets). We classified imagery using classification and regression tree method (CART) using a combination of Landsat TM imagery and ancillary data. The specific CART program used was See5, which implements a gain ratio criterion in tree development and pruning (Quinlan, 1993). We used boosting and cross-validation to improve classification accuracy (boosting) and estimate accuracy (cross-validation).

ShareScore

36/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
8
Harmonization
8
Access
8
Reuse readiness
4
Engagement
8

Topics