基于空间连续性聚类算法的精准农业管理分区研究

该研究在K均值算法KM的基础上，根据空间单元位置的相互依赖关系，提出了一种新的空间连续性聚类算法SCKM。以北京精准农业示范基地获取的OMIS图像为数据源，选用K均值算法、等间隔法、分位数法、自然断点法等传统分区方法和SCKM算法，对肥水需求关键时期的小麦的长势差异进行了管理分区提取研究，并引入了权重方差和聚集度两种分区效果评价指标，对分区结果进行了比较和评价。结果表明：SCKM算法与传统分区方法分区结果相比，区内方差差异不显著；而空间聚集度远好于后者，利用SCKM法分区能够有效地去除大量的孤立单元或碎片。

Delineating precision agriculture management zones based on spatial contiguous clustering algorithm

Based on the traditional K-Means cluster (KM) and the spatial autocorrelation, a new method, Spatial Contiguous K-Means clustering algorithm (SCKM), was developed in this study. According to the spatial variability of wheat growth under within-field level extracted from OMIS image of the key growth stage, precision agriculture management zones were delineated by using the SCKM method and the traditional methods such as KM, Equal Interval, Quantile and Natural Breaks method. Two evaluation indices were employed to evaluate the zoned results of the above mentioned methods .The results showed that the sum of the weighted variance of the corresponding within-zones based on these methods appeared no significant difference, and that the SCKM method could remove a lot of isolated cell or patch and improved the continuity of the corresponding management zone map, compared with the traditional methods. The zoned result based on the SCKM method can be used as the variable management unit for precision agriculture and can be used to advise the sampling of subsequent soil or crop.