Remotely Sensed Estimation of Total Iron Content in Soil With Harmonic Analysis and BP Neural Network

Abstract

Background: The estimation of total iron content at the regional scale is much of significance as iron deficiency has become a routine problem for many crops. Methods: 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-PCA, WPT-FD-PCA, and WPT-FD-HA-PCA) for TICS estimation. Furthermore, the estimated accuracy of three BP models based on these variables was compared. Results: The results showed that the BP models of different soil types based on WPT-FD-HA-PCA had better estimation accuracy, with the highest R2 value of 0.95, and the RMSE of 0.68 of 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-PCA-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.Conclusion: 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.