灌丛化草原灌木和草本植物光谱特征差异及灌木盖度反演——以内蒙古镶黄旗为例

Spectral feature differences between shrub and grass communities and shrub coverage retrieval in shrub-encroached grassland in Xianghuang Banner, Nei Mongol, China

灌丛化草原已成为我国干旱、半干旱地区一种重要的植被类型,但目前有关灌丛化草原灌木和草本植物光谱特征以及灌木盖度的遥感反演研究鲜有报道。相比传统的野外调查方法,基于遥感影像的灌木盖度反演为实现长时间、大范围灌丛化草原灌木盖度监测提供了可能。该研究综合利用灌木和草本植物光谱特征差异以及季相差异,以内蒙古镶黄旗灌丛化草原区为例,通过线性模型和多端元混合光谱分解模型,实现了利用中分辨率Landsat卫星影像的灌木盖度反演。对镶黄旗优势灌木和草本植物群落的光谱特征分析表明,小叶锦鸡儿(Caragana microphylla)灌木群落的红边斜率、归一化植被指数和改进红边归一化植被指数值均高于以羊草(Leymus chinensis)、克氏针茅(Stipa krylovii)为优势种的草本植物群落,并且其红边位置有"红移"趋势。两种模型反演所得镶黄旗灌丛化草原区灌木盖度平均值均为13%,绝大多数区域灌木盖度低于25%。相比基于盛夏时节影像的多端元混合光谱分解模型,利用灌木和草本植物季相特征差异建立的基于初秋时节影像的线性模型更适合灌丛化草原灌木盖度的遥感反演。

Aims Shrub-encroached grassland has become an important vegetation type in China＇s arid and semi-arid re- gion. Our study objective is to explore the spectral features of shrub and grass communities, as well as their em- pirical relationships with shrub coverage. The quantitative estimation of shrub cover based on medium-resolution Landsat satellite imagery provides the practical basis for long term retrieval of large areas of shrub expansion in the grassland region. Methods Linear models and Multiple Endmember Spectral Analysis Model （MESMA） based on medium reso- lution Landsat satellite imagery were developed to quantify the shrub coverage in a shrub-encroached grassland region in Xianghuang Banner, Nei Mongol using the spectral features and their seasonal differences between the shrub and grass communities. Important findings Compared to Leymus chinensis and Stipa krylovii dominated grass communities, Caragana microphylla community had a higher normalized difference vegetation index （NDVI）, modified red edge normal- ized difference vegetation index （mNDVI705）, and red edge slope. The red edge position of C. microphylla commu- nity shifted to longer wavelengths. The average and the maximum shrub coverage was 13% and 25%, respectively, in the shrub-encroached grassland based on both models. The correlation coefficient of determination （R2） and root mean square error （RMSE） of the linear model was 0.31 and 0.05, respectively. We found that the linear model based on seasonal differences of shrub and grass community was more suitable for retrieving shrub coverage in the study area from medium resolution imagery than the MESMA model that is based on mid-summer images.