Analysis and Evaluation of Soil Fertility Status Based on Weighted K-means Clustering Algorithm

Abstract

AbstractGenerally K-means clustering algorithm can not distinguish the imbalance between attributes, so it can only be an independent investigation situation of each attribute but can not be comprehensive analysis of the soil fertility status. To solve this problem, this paper proposes a weighted K-means clustering algorithm to evaluate the soil fertility in Nong’an County, Jilin. The algorithm uses AHP to get the weight of soil nutrient attributes. Then combined with K-means clustering algorithm. Finally through the operational efficiency and accuracy to determine the optimal classification, that can improve the clustering algorithm of intelligent. The algorithm and the traditional K-means clustering algorithm are used in the comparison, tests showed that the weighted K-means clustering algorithm has a better accuracy, operational efficiency, significantly higher than the unweighted clustering algorithm; Comprehensive evaluation of the changes in soil nutrients after precision fertilization that used algorithm. The soil fertility status has a significantly improvement after years of continuous precision fertilizing. The results show that the improved clustering algorithm is a good method to comprehensive evaluation of soil fertility.KeywordsAHPWeighted K-means clusteringOptimal classificationSoil fertility evaluation