Desertification is an alarming sign of land degradation in Henshan county of northwest china. Due to the considerable costs of detailed ground surveys of this phenomenon, remote sensing is an appropriate alternative for analyzing and evaluating the risks of the expansion of land degradation. Degradation features can be detected directly or indirectly by using image data. In this paper, based on the Hyperion images of Hengshan desertification region of northwest china, a new algorithm aimed at land degradation mapping, called Land Degradation Index (LDI), was put forward. This new algorithm is based on the classified process. We applied the linear spectral unmixing algorithm with the training samples derived from the formerly classified process so as to find out new endmembers in the RMS error imagine. After that, using neutral net mapping with new training samples, the classified result was gained. In addition, after applying mask processing, the soils were grouped to 3 types (Kappa =0.90): highly degraded soils, moderately degraded soils and slightly degraded soils. By analyzing 3 mapping methods: mixture-classification, the spectral angle mapper and mixturetuned matched filtering, the results suggest that the mixture-classification has the higher accuracy (Kappa=0.7075) than the spectral angle mapper (Kappa=0.5418) and the mixture-tuned matched filter (Kappa=0.6039). As a result, the mixture-classification is selected to carry out Land Degradation Index analysis.

Date Published: 3 November 2008
PDF: 9 pages
Proc. SPIE 7145, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Monitoring and Assessment of Natural Resources and Environments, 71451R (3 November 2008); doi: 10.1117/12.813045

Published in SPIE Proceedings Vol. 7145:
Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Monitoring and Assessment of Natural Resources and Environments
Lin Liu; Xia Li; Kai Liu; Xinchang Zhang; Yong Lao, Editor(s)