The Modified Model of Soil Organic Matter Content Grey Relation Estimation Pattern Based on Hyper-spectral Data

Soil organic matter is one of the important indexes of soil fertility, and using hyper-spectral technology to determine soil organic matter content rapidly is of great significance for developing precision agriculture. To further enhance estimation accuracy through the greyness of the soil organic matter content, the grey relational estimation pattern of soil organic matter content by hyper-spectral technology is established based on the grey relational theory. Based on the variance information between the identified samples and their corresponding patterns, the modified model of the estimated values of soil organic matter content is constructed. The proposed method in this paper is applied to the hyper-spectral estimation of soil organic matter content in Zhangqiu District of Jinan City, Shandong province. The experimental results show that the estimation accuracy of 16 identified samples is high, the average relative error is only 3.801%, and the determination coefficient R-2=0.9782. The results show that the modified model of soil organic matter content grey relation estimation pattern based on hyper-spectral data is valid.