Unsupervised landcover classification in a topographically diverse region of north-central British Columbia.

Landcover mapping is an important tool for natural resource managers. The incorporation of remotely sensed data to produce landcover maps is becoming more common, as a result of lower cost and greater availability of image data. One factor that can negatively affect landcover classifications is topographic variation, particularly in mountainous areas. For this study, four unsupervised classification methods were compared using Landsat Thematic Mapper data (TM) to test the effect of topography on landcover classification. One scenario involved using only TM data, another combined TM data with an Incidence channel, a third used principal component analysis (PCA) and the last used selective principal component analysis (SPCA). Each classification was tested for two different classification legends. The first was based on habitat mapping while the other was a general landcover legend taken from a national mapping project. In each case, the imagery was pre-stratified using a normalized difference vegetation index and was clustered with the K-Means unsupervised classification method. Results showed that the combination of TM bands 3, 4, 5 and Incidence modestly increased the classification accuracy for both legends although accuracies were lower than 62%. The PCA and SPCA scenarios, which other research had shown held promise as a means of topographic compensation, did not produce higher accuracy without considerable class aggregation.