A grey relationship-based soil organic matter content inversion pattern

In this paper a grey weighted relationship prediction pattern is proposed for the soil organic matter content spectral inversion under the uncertainties between soil organic matter contents and spectral characteristics and the theory of grey system. In order to take full use of the information of grey relationship sequences, the maximum grey relationship discrimination principles are improved, by the utilization of the soil organic matter content weighted grey recognition model based on grey relationship. As a example it is used to carry out the soil organic matter hyper-spectral inversion analysis of Hengshan County in Shanxi Province. The results show that, the sample's average prediction accuracy is 94.917% which proves that this model is valid.