基于高分辨率反射光谱的土壤营养元素估算模型

MODEL FOR ESTIMATING SOIL NUTRIENT ELEMENTS BASED ON HIGH RESOLUTION REFLECTANCE SPECTRA

研究了土壤中营养元素含量(N、P、K)与土壤可见光/近红外光谱之间的关系。在对原始光谱进行预处理分析后,计算出了4种光谱指标:反射率Reflectance、一阶导数FDR、倒数之对数log(1/R)和波段深度Depth。通过偏最小二乘回归分析建立了营养元素与4种光谱指标的经验模型,并且利用验证样本集对回归模型进行了验证。结果表明,可见光/近红外反射光谱具有快速估算土壤中营养元素含量的潜力。

Relationship between contents of soil nutrient elements （N, P and K） and laboratory VNIR （visible-near infrared） spectra of the soil is analyzed in this article. Some spectra are pre-processed before calculation of four spectral indices, including inverse spectra （1/R）, first derivative reflectance spectra （FDR）, inverse-log spectra （log （1/R）） and Depth. Based on the partial least square regression method, statistical relationships between these indices and contents of soil nutrient elements are established by calibration set. Then the regression model is verified by test set. The results showed that VNIR （visible-near infrared） spectra of soil are potentially useful for rapid estimation of content of the nutrient elements in the soil.