喀斯特山区草地地上生物量遥感估测  

Estimation of Karst Mountain Grassland Aboveground Biomass Based on Linear Spectral Mixture Model

作　　者：陈全[1,2] 周忠发[1,2] 魏小岛[1,2] 

机构地区：[1]贵州师范大学中国南方喀斯特研究院,贵阳550001 [2]贵州省喀斯特山地生态环境国家重点实验室培育基地,贵阳550001

出　　处：《湖北农业科学》2014年第9期2013-2016,共4页Hubei Agricultural Sciences

基　　金：国家"973"计划项目(2012CB723202);贵州省国际科技合作计划项目(黔科合外G字[2012]7022号);贵州省社会发展科技攻关计划项目(黔科合GY字[2013]3062号);黔南州农业资源区划办公室委托项目

摘　　要：由于喀斯特山区地表破碎,环境异质性强,影像上混合像元现象严重,增加了草地地上生物量遥感估测的难度。以Landsat ETM+为数据源,将光谱混合分析技术应用于喀斯特山区草地地上生物量的遥感估测中,分析了基于线性混合分解模型分解的草地分量与实测草地地上生物量的相关关系,进而构建了喀斯特山区草地地上生物量估测模型为y赞=2 451.158x-280.461(r2=0.801 2),验证结果总体精度可达85%以上。基于光谱混合分析建立的草地地上生物量估测模型提高了喀斯特山区草地地上生物量遥感估测的精度,为喀斯特山区草地生长状况调查与监测提供了技术支持。The grassland is an important part of the Karst mountain ecosystems in Southern China and the basis of protecting the karst mountainous ecological environment and developing of grassland animal husbandry. In typical karst mountain area,the complex and broken ground surface leads to serious mixed pixel phenomenon. Linear spectral mixture model was used to estimate grassland aboveground biomass based on Landsat ETM＋image.The results showed that the grassland fraction extracted with the linear mixed model had obvious lineal correlation with the field data measured. Grassland aboveground biomass estimation model can be expressed by the equation y^=2 451.158x-280.461（r^2=0.801 2）. The accuracy validation showed that the overall accuracy was above 85%. The estimation model of grassland aboveground biomass which based on spectral mixture model can improve the estimation accuracy in karst mountainous area. This method can provide technical support for surveying and monitoring the growth of karst mountainous grass.

关 键 词：喀斯特山区 草地地上生物量 遥感估测 光谱混合分析 

分 类 号：S127[农业科学—农业基础科学] S812.5