土壤含水量高光谱灰色关联度估测模式

针对土壤含水量高光谱估测中的不确定性,基于灰色系统理论,建立土壤含水量灰色关联度高光谱估测模式。首先根据光谱特征因子的非时间数据序列特性,利用基于加权距离的灰色关联度计算方法,构建灰色关联度预测模型;然后利用识别残差建立修正模型,提出了具有残差修正的灰色关联度预测模式,并应用于山东省泰安市土壤水含量高光谱估测。结果表明,检验样本的平均相对误差为3.614%,而基于经典的灰色关联模式和线性回归模型的平均相对误差分别为4.762%和6.841%。应用实例说明提出的模式是有效的。

Grey Relation Estimating Pattern of Soil Water Content Based on Hyper-Spectral Data

As to the uncertainties in estimating the soil water content based on hyper-spectral the grey relation de-gree estimating pattern based on hyper-spectral is established according to grey system theory. First on the basis of non-time data series characteristics of spectral characteristic factors a grey relation degree calculating method based on weighted distance is used to establish the grey relation degree predicting model then by making full use of recognition error a modified model is given and the grey relation estimating pattern with the residual modifica-tion is proposed. At last the pattern proposed in this paper is applied to the hyper-spectral estimation of soil water content of the samples collected from Taian City in Shandong Province. The results indicate that the testing sam-ples average relative error is 3.614% while the average relative errors of the classic grey relation pattern and lin-er regression model are 4.762% and 6.841% respectively. The application example shows that the pattern proposed in this paper is valid.