模糊c均值聚类方法在黑河下游土壤属性制图中的初步应用研究

Preliminary application of the fuzzy C-mean clustering method to the soil mapping in the lower reaches of Heihe River

运用模糊c均值聚类方法初步研究了我国典型干旱区黑河下游的土壤属性空间分布规律。通过分析该地区的地形参数(坡度,沿剖面曲率和沿等高线曲率),植被指数(NDVI)及地质数据,设计了16个野外典型样本采集点及9个独立样本用于结果验证。应用室内试验,测定土样的3个属性特征(饱和导水率、土壤容重及土壤含水量)。以模糊隶属度作为权重,运用加权平均法计算得到三组土壤属性的空间分布,结果与9个独立采样点进行对比,无显著性差别。表明该方法在极端干旱区黑河下游地形较平缓地区适用性较强,结果能够满足应用需求,为该区域的地表过程研究提供宝贵的数据支持。

The distributions of the terrain factors（including the slope,profile curvature and contour curvature）,geology and normalized difference vegetation index in lower Heihe River were clustered using fuzzy c-means method.Fuzzy membership distribution of 15 groups of environmental factors were derived to position 16 soil samples in the area with membership larger than 0.9.9 individual soil samples were collected to verify the results.The soil physical parameters（including the saturated hydraulic conductivity,bulk density and soil water content） were measured in the lab experiments.The soil property distributions were calculated using the weighted average method with fuzzy membership as the weight.The calculated results were verified to be not significant different from the measured values.It means that the method discussed in this study is very suitable to be applied in the lower Heihe River.The results satisfied with the requirement of the application and supplied very important data to the studies of the area earth＇s surface process.