基于光谱数据降维的农田土壤-作物全氮含量协同检测

Integrated Detection of Soil-Crop Nitrogen Content in Agricultural Fields Based on Spectral Data Downscaling

为了提高农田土壤-作物全氮一体化检测精度,以冬小麦冠层光谱为研究对象,定量分析了4种数据降维方法(保持邻域嵌入法(NPE)、t分布随机近邻嵌入法(t-SNE)、拉普拉斯映射法(LE)和局部线性嵌入法(LLE))在冠层光谱特征提取及作物、土壤全氮含量检测精度。分别采集了豫麦49-198、周麦27、矮抗58和西农509等4个品种的冬小麦在4个施氮水平下的作物冠层光谱反射率以及对应的作物、土壤全氮含量。选取波段400~900 nm的可见光与部分近红外波段分别进行NPE、t-SNE、LE以及LLE数据降维处理,随后在4组降维特征的基础上,建立了随机森林回归模型。对比全谱信息以及4组降维特征在作物、土壤全氮含量的预测性能表明,利用LLE-RF混合方法取得了最优的氮素预测效果,作物全氮含量预测决定系数R^(2)_(v)为0.9150,预测均方根误差(RMSEP)为0.2212 mg/kg;土壤全氮含量预测决定系数R^(2)_(v)为0.8009;RMSEP仅为0.0085 mg/kg,均优于原始全谱数据以及其他3组降维特征。实验结果表明,利用LLE降维后得到的特征光谱信息可有效地表征作物全氮含量以及土壤全氮含量。

In order to improve the accuracy of integrated soil-crop total nitrogen detection in agricultural fields,the canopy spectra of winter wheat were used as a research object to quantify the accuracy of four data reduction methods(neighborhood preserving embedding(NPE),t-distribution stochastic neighbor embedding(t-SNE),Laplacian eigenmaps(LE)and locally linear embedding(LLE))in canopy spectral feature extraction and crop and soil total nitrogen content detection.The canopy spectral reflectance and the corresponding crop and soil total N contents of four varieties of winter wheat,namely Yumai 49-198,Zhoumai 27,Aikang 58 and Xinong 509,were collected at four levels of N application,respectively.The NPE,t-SNE,LE and LLE were used to downscale the data in the visible and partial near-infrared bands from 400 nm to 900 nm,and subsequently,a random forest regression model was developed based on the four sets of downscaled features.Comparison of the full-spectrum information and the prediction performance of the four sets of downscaled features for crop and soil total nitrogen content showed that the hybrid LLE-RF method achieved the best nitrogen prediction results with an R^(2)_(v) value of 0.9150 for the coefficient of determination of crop total nitrogen content prediction and a root mean square error(RMSEP)of 0.2212 mg/kg for crop total nitrogen prediction.The coefficient of determination R^(2)_(v) for prediction of total soil nitrogen content was 0.8009.The RMSEP was only 0.0085 mg/kg,which were all better than that of the original full-spectrum data as well as the other three sets of downscaled features.The experimental results showed that the LLE downscaled spectral information can effectively characterize the crop total nitrogen content and soil total nitrogen content.