Prediction of soil organic matter by VIS-NIR spectroscopy using normalized soil moisture index as a proxy of soil moisture

Abstract

Soil organic matter (SOM) is an important parameter of soil fertility, and visible and near-infrared (VIS-NIR) spectroscopy combined with multivariate modeling techniques have provided new possibilities to estimate SOM. However, the spectral signal is strongly influenced by soil moisture (SM) in the field. Interest in using spectral classification to predict soils in themoist conditions tominimize the influence of SMis growing. The objective of this study was to investigate the transferability of two approaches, SM-based clustermethod with known SM(classifying the VIS-NIR spectra into different SM clusters to develop models separately), the normalized soil moisture index (NSMI)-based cluster method with unknown SM(utilizing NSMI to indicate the SMand establish models separately), to predict SOM directly inmoist soil spectra. One hundred and twenty one soil sampleswere collected fromCentral China, and eight SM levels were obtained for each sample through rewetting experiments. Their reflectance spectra and SOMconcentrations were measured in the laboratory. Partial least square-support vector machine (PLS-SVM) was employed to construct SOMprediction models. Specifically, prediction models were developed for NSMI-based clusters with unknown SMdata. The models were assessed through three statistics in the processes of calibration and validation: the coefficient of determination (R2), root mean square error (RMSE) and the ratio of the performance to deviation (RPD). Results showed that the variable SMled to reduced VIS-NIR reflectance nonlinearly across the entire spectral range. NSMI was an effective spectral index to indicate the SM. Classifying the VIS-NIR spectra into different SMclusters in known SMstates could improve the performance of PLS-SVMmodels to acceptable prediction accuracies (R2cv = 0.69-0.77, RPD = 1.79-2.08). The estimation of SOM, when using the NSMI-based cluster method with unknown SM(RPD = 1.95-2.04), was similar to the use of the SM-based cluster method with known SM (RPD = 1.79-2.08). The predictive results (RPD = 1.87-2.06) demonstrated that the NSMI-based cluster method has potential for application outside the laboratory for SOMprediction without knowing the SMexplicitly, and this method is also easy to carry out and only requires spectral information.