PROJECT TITLE :

Estimation of Fractional Vegetation Cover in Semiarid Areas by Integrating Endmember Reflectance Purification Into Nonlinear Spectral Mixture Analysis

ABSTRACT:

Fractional vegetation cover (FVC) is one in all the elemental parameters for characterizing terrestrial ecosystems, with wide uses in varied environmental and climate-related modeling applications. The remote sensing technique provides a distinctive chance for estimating FVC over massive geographical areas by employing spectral mixture analysis (SMA). The effectiveness of SMA depends largely on the correct extraction of representative and pure endmembers. But, in arid and semiarid environments that have sparse vegetation distributions, most current SMA models could manufacture giant biases due to difficulties in obtaining pure vegetation spectra from the satellite images. This letter developed a replacement approach to estimate FVC from satellite observations by integrating an endmember spectrum purification procedure into a nonlinear SMA model. The proposed method is capable of extracting pure endmember spectra while pure vegetation endmember isn't present in target images in arid and semiarid environments, which improves the accuracy of FVC retrievals. Validation experiments conducted in the Xilingol grassland, Inner Mongolia, China, demonstrate that the proposed method produces a lot of correct FVC estimates $(mathbfRMSE< mathbf0.13, mathbfAD< mathbf0.06)$ than do current algorithms. The higher performance of the proposed method will be attributed to the purified vegetation spectra that a lot of closely resemble the $64000 pure vegetation spectra.