Abstract
Current feature space models of desertification were almost linear, which ignored the complicated and non-linear relationships among variables for monitoring desertification. Fully considering the influencing factors of the desertification process in Naiman Banner, four sensitive indices including MSAVI, NDVI, TGSI, and Albedo have been selected to construct five feature spaces. Then, the precisions of different feature space models for monitoring desertification information (including non-linear and linear models) have been compared and analyzed. The non-linear Albedo-MSAVI feature space model for Naiman Banner has higher efficiency with the overall precision of 90.1%, while that of Albedo-TGSI had the worst precision with 0.69. Overall, the feature space model (non-linear) of Albedo-MSAVI has the highest applicability for monitoring the desertification information in Naiman Banner.
Highlights
Desertification, one of the most serious eco-environmental problems, has become a major land degradation type occurring over the world during the past decades [1]
CONSTRUCTION OF THE FEATURE SPACE As was shown in Figure 2, five feature spaces were constructed based on the above four sensitive indices, which were divided into two categories
Five point clusters that distributed in different regions in the Albedo-modified soil adjusted vegetation index (MSAVI) feature space were selected according to the distance to the point (1, 0)
Summary
Desertification, one of the most serious eco-environmental problems, has become a major land degradation type occurring over the world during the past decades [1]. Desertification has become a major environmental problem that is hampering socio-economic development and threatening its ecological environment in Naiman Banner under the joint actions of climate change and human activity [1]. Based on Landsat Images, [13] analyzed the relationships between levels of desertification and the surface water in Naiman Banner.In addition, automatic classification methods have often been utilized to obtain the desertification information in large area, the improvement of classification accuracy is limited to a certain extent. The feature space model has been widely utilized to quantitatively obtain the desertification information, which could better reflect the land surface change information of desertification [8], [10], [14]. The feature space models have been constructed with some sensitive parameters
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
