Rapid detection of total nitrogen content in soil based on hyperspectral technology

Abstract

Soil total nitrogen content (TN) is a crucial factor in boosting the growth of crops. Its surplus or scarcity will alter the quality and yield of crops to a certain extent. Traditional methods such as chemical analysis is complicated, laborious and time-consuming. A faster and more efficient method to detect TN should be explored to address this problem. The hyperspectral technology integrates conventional energy and spectroscopy which aids in the simultaneous collection of spatial and spectral information from an object. It has gradually proved its significance and gained popularity in the analysis of soil composition. This study discussed the possibility of using hyperspectral technology to detect TN, analyzed six spectral data preprocessing methods and five modeling methods: partial least squares (PLS), back-propagation (BP) neural network, radial basis function (RBF) neural network, extreme learning machine (ELM) and support vector regression (SVR) with evaluation index R² and RMSE. Setting the content of chemical analysis as the control and comparing the errors from spectral analysis. According to the results, all five models can be used for TN detection, and the SVR model with R² 0.912 1 and RMSE 0.758 1 turned to the best method. The study showed that the spectral model can detect TN quickly, providing a reference for the detection of elements in soil with favorable research significance.