摘要:SO42-是盐渍土阴离子中的主要离子，但目前针对不同人为干扰区域土壤中SO42-反演研究却鲜有报道。土壤高光谱与土壤某元素间的关系表现为非线性，传统线性偏最小二乘模型（PLSR）对土壤元素的反演精度有限。本文以新疆昌吉回族自治州境内不同人为干扰区域的盐渍化土壤为研究对象，以土壤的野外高光谱和SO42-含量为数据源，对原始（R）和对数（LogR）变换后的高光谱分别进行0阶、一阶和二阶微分预处理，选择通过0.05显著性水平的波段为敏感波段，将敏感波段对应的高光谱反射率作为非线性BP神经网络模型的输入变量，并设定BP的隐藏节点为300，学习速率为0.01，最大迭代次数为1 000，训练函数为trainscg。从SO42-的真实值与预测值的散点图、拟合效果图和BP训练过程3个方面，定量分析无人为干扰（A区）和有人为干扰（B区）土壤SO42-含量，并与PLSR对比预测精度。仿真显示，A区二阶微分后的BP预测精度优于一阶微分，而B区一阶微分后的BP预测精度优于二阶微分。且不论在A区还是B区，LogR光谱变换的反演精度均优于R。最佳BP模型的相对预测性能（RPD）、决定系数（R2）、均方根误差（RMSE）和迭代次数，在A区分别为3.309、0.906、0.253和8次，在B区分别为2.234、0.844、0.786和45次，表明BP对A区SO42-的预测能力非常强（RPD>2.5），对B区SO42-的预测能力较强（RPD为2.0~2.5）。而在A区和B区两种光谱变换的一阶和二阶微分中，PLSR的RPD值均在1.4与1.8之间，其预测性能一般；在B区的0阶微分中，PLSR的RPD值均小于1.0，其不能对SO42-进行预测。因此，BP模型能对不同人为干扰区域的SO42-进行有效的定量分析。
关键词:盐渍土/
人为干扰区域/
SO42-含量/
BP神经网络模型/
光谱变换
Abstract:SO42- is one of the main ions in saline soil, but the inversion of SO42- ion in soils under different levels of human disturbance has rarely been reported. Moreover, the relationship between soil hyperspectral and soil elements is nonlinear, and the traditional linear partial least squares model (PLSR) has limited inversion accuracy for soil elements. In order to quantitatively analyzed soil SO42- content in saline soil, this study selected the saline soils in areas undisturbed and human-disturbed in Changji Hui Autonomous Prefecture of Xinjiang, to predict SO42- contents based on soil hyperspectral by using BP Neural Network. The original (R) and logarithmic transformed (LogR) hyperspectral were subjected as 0-order, first-order and second-order differential preprocessing, respectively. The hyperspectral reflectivity corresponding to the sensitive band was taken as the input variable of the nonlinear BP neural network model, and the hidden node, learning rate and maximum number of iterations of BP were set as 300, 0.01, and 1 000. The training function was trainscg. The SO42- contents of saline soil in undisturbed area (Area A) and human-disturbed area (Area B) were determined by using the scatter plot of measured and predicted SO42- contents, the fitting effect map, and the BP training process. The prediction accuracy was tested by comparison with PLSR results. The simulation showed that the BP prediction accuracy after the second-order differentiation in the Area A was better than the first-order differential, while it was opposite for the Area B. The inversion accuracy of LogR spectral transformation was better than R for both Area A and Area B. The relative prediction performance (RPD), determination coefficient (R2), root mean square error (RMSE) and iteration number of the optimal BP model were 3.309, 0.906, 0.253 and 8 times in the Area A; and 2.234, 0.844, 0.786 and 45 times in the Area B. It indicated that BP predictive ability was strong for SO42- content in Area A and Area B. However, for the first- and second-order differentials of spectral in the Area A and Area B, the RPD values of the PLSR were 1.4-1.8, and the prediction performance was normal; in the 0-order differential of the Area B, the RPD of PLSR were all less than 1.0, which could not predict SO42- content. Therefore, the BP model can perform effectively quantitative analysis of SO42- in different undisturbed or human-disturbed regions.
Key words:Saline soil/
Human-disturbed area/
SO42- content/
BP neural network model/
Spectral transformation
PDF全文下载地址:
http://www.ecoagri.ac.cn/article/exportPdf?id=392f052f-5e70-448a-ab73-1a9bf49b964c
