Abstract
The successful estimation of soil organic matter (SOM) and soil total nitrogen (TN) contents with mid-infrared (MIR) reflectance spectroscopy depends on selecting appropriate variable selection techniques and multivariate methods for regression analysis. This study aimed to explore the potential of combining a multivariate method and spectral variable selection for soil SOM and TN estimation using MIR spectroscopy. Five hundred and ten topsoil samples were collected from Quzhou County, Hebei Province, China, and their SOM and TN contents and reflectance spectra were measured using DRIFT-MIR spectroscopy (diffuse reflectance infrared Fourier transform in the mid-infrared range, MIR, wavenumber: 4000–400 cm−1; wavelength: 2500–25,000 nm). Two multivariate methods (partial least-squares regression, PLSR; multiple linear regression, MLR) combined with two variable selection techniques (stability competitive adaptive reweighted sampling, sCARS; bootstrapping soft shrinkage approach, BOSS) were used for model calibration. The MLR model combined with the sCARS method yielded the most accurate estimation result for both SOM (Rp2 = 0.72 and RPD = 1.89) and TN (Rp2 = 0.84 and RPD = 2.50). Out of the 2382 wavenumbers in a full spectrum, sCARS determined that only 31 variables were important for SOM estimation (accounting for 1.30% of all variables) and 27 variables were important for TN estimation (accounting for 1.13% of all variables). The results demonstrated that sCARS was a highly efficient approach for extracting information on wavenumbers and mitigating redundant wavenumbers. In addition, the current study indicated that MLR, which is simpler than PLSR, when combined with spectral variable selection, can achieve high-precision prediction of SOM and TN content. As such, DRIFT-MIR spectroscopy coupled with MLR and sCARS is a good alternative for estimating the SOM and TN of soils.
Highlights
Monitoring the soil status is in great demand in precision agriculture to adjust practices such as tillage, fertilization, and irrigation [1]
mid-infrared spectroscopy (MIR) detects the fundamental vibrations of minerals and organic matter, which have strong absorptions, whereas visible and near-infrared spectroscopy (Vis-near-infrared spectroscopy (NIR)) spectroscopy detects their overtones and combinations of overtones, which are much weaker and greatly overlap [28]
The Rp2 and residual prediction deviation of prediction (RPD) of Soil organic matter (SOM) estimation models based on the Bootstrapping soft shrinkage (BOSS) and Stability competitive adaptive reweighted sampling (sCARS) variables selection methods were equal to or higher than that of the full MIR spectrum model
Summary
Monitoring the soil status is in great demand in precision agriculture to adjust practices such as tillage, fertilization, and irrigation [1]. Soil organic matter (SOM) and total nitrogen (TN) are essential elements in agricultural soil and play an important role in many biological and chemical activities for plant growth. As effective alternatives to traditional chemical analysis, visible and near-infrared spectroscopy (Vis-NIR), mid-infrared spectroscopy (MIR), and combined diffuse reflectance spectroscopy have the potential to predict various soil properties simultaneously [5–8]. Diffuse reflectance spectroscopy in the Vis-NIR spectral range has been used widely to characterize SOM [9–14] and TN [13–19]. MIR has been demonstrated to predict SOM and TN, often with better accuracy than Vis-NIR-derived models [20–27]. MIR detects the fundamental vibrations of minerals and organic matter, which have strong absorptions, whereas Vis-NIR spectroscopy detects their overtones and combinations of overtones, which are much weaker and greatly overlap [28]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
