Jiang Xueqin, Luo Shanjun, Fang Shenghui, Cai Bowen, Xiong Qiang, Wang Yanyan, Huang Xia, Liu Xiaojuan
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, 430079, China.
Lab of Remote Sensing for Precision Phenomics of Hybrid Rice, Wuhan University, Wuhan, 430079, China.
Plant Methods. 2021 Nov 12;17(1):116. doi: 10.1186/s13007-021-00812-8.
The estimation of total iron content at the regional scale is of much significance as iron deficiency has become a routine problem for many crops.
In this study, a novel method for estimating total iron content in soil (TICS) was proposed using harmonic analysis (HA) and back propagation (BP) neural network model. Several data preprocessing methods of first derivative (FD), wavelet packet transform (WPT), and HA were conducted to improve the correlation between the soil spectra and TICS. The principal component analysis (PCA) was exploited to obtained three kinds of characteristic variables (FD, WPT-FD, and WPT-FD-HA) for TICS estimation. Furthermore, the estimated accuracy of three BP models based on these variables was compared.
The results showed that the BP models of different soil types based on WPT-FD-HA had better estimation accuracy, with the highest R value of 0.95, and the RMSE of 0.68 for the loessial soil. It was proved that the characteristic variable obtained by harmonic decomposition improved the validity of the input variables and the estimation accuracy of the TICS models. Meanwhile, it was identified that the WPT-FD-HA-BP model can not only estimate the total iron content of a single soil type with high accuracy but also demonstrate a good effect on the estimation of TICS of mixed soil.
The HA method and BP neural network combined with WPT and FD have great potential in TICS estimation under the conditions of single soil and mixed soil. This method can be expected to be applied to the prediction of crop biochemical parameters.
由于缺铁已成为许多作物的常见问题，区域尺度上总铁含量的估算具有重要意义。
本研究提出了一种利用谐波分析（HA）和反向传播（BP）神经网络模型估算土壤总铁含量（TICS）的新方法。采用一阶导数（FD）、小波包变换（WPT）和HA等几种数据预处理方法来提高土壤光谱与TICS之间的相关性。利用主成分分析（PCA）获得三种特征变量（FD、WPT-FD和WPT-FD-HA）用于TICS估算。此外，比较了基于这些变量的三个BP模型的估算精度。
结果表明，基于WPT-FD-HA的不同土壤类型的BP模型具有更好的估算精度，黄土的最高R值为0.95，RMSE为0.68。证明了谐波分解得到的特征变量提高了输入变量的有效性和TICS模型的估算精度。同时，确定WPT-FD-HA-BP模型不仅能高精度估算单一土壤类型的总铁含量，而且对混合土壤TICS的估算也有良好效果。
HA方法和BP神经网络结合WPT和FD在单一土壤和混合土壤条件下的TICS估算中具有很大潜力。该方法有望应用于作物生化参数的预测。
