Soil classification of Qinghai Lake basin based on remote sensing

The aim of this study is to test the feasibility of soil classification based on remote sensing in a typical area of Qinghai Lake basin. The authors employed TM image and terrain data as main data sources,and used GeoEye- 1 high- resolution remote sensing images and soil map as auxiliary data sources. The TM image was processed to extract classification features by using a variety of image processing techniques,which included such means as principal component analysis,tasseled cap transformation,and band math. Supported by ArcGIS9. 3 software,the authors detected several topographical features with DEM,such as elevation,slope and aspect. Then, the authors incorporated all classification features into a dataset,and used maximum likelihood classifier of supervision to classify the soil of the test area. The results suggest that the combination of remote sensing image with terrain data can distinguish nine soil subcategories and one non- soil unit. The overall classification accuracy can reach 91. 76%.