Combining Fractional Order Derivative and Spectral Variable Selection for Organic Matter Estimation of Homogeneous Soil Samples by VIS–NIR Spectroscopy

Abstract

Visible and near-infrared (VIS-NIR) spectroscopy has been extensively applied to estimate soil organic matter (SOM) in the laboratory. However, if field/moist VIS-NIR spectra can be directly applied to estimate SOM, then much of the time and labor would be avoided. Spectral derivative plays an important role in eliminating unwanted interference and optimizing the estimation model. Nonetheless, the conventional integer order derivatives (i.e., the first and second derivatives) may neglect some detailed information related to SOM. Besides, the full-spectrum generally contains redundant spectral variables, which would affect the model accuracy. This study aimed to investigate different combinations of fractional order derivative (FOD) and spectral variable selection techniques (i.e., competitive adaptive reweighted sampling (CARS), elastic net (ENET) and genetic algorithm (GA)) to optimize the VIS-NIR spectral model of moist soil. Ninety-one soil samples were collected from Central China, with their SOM contents and reflectance spectra measured. Support vector machine (SVM) was applied to estimate SOM. Results indicated that moist spectra differed greatly from dried ground spectra. With increasing order of derivative, the spectral resolution improved gradually, but the spectral strength decreased simultaneously. FOD could provide a better tool to counterbalance the contradiction between spectral resolution and spectral strength. In full-spectrum SVM models, the most accurate estimation was achieved by SVM model based on 1.5-order derivative spectra, with validation R 2 = 0.79 and ratio of the performance to deviation (RPD) = 2.20. Of all models studied (different combinations of FOD and variable selection techniques), the highest validation model accuracy for SOM was achieved when applying 1.5 derivative spectra and GA method (validation R 2 = 0.88 and RPD = 2.89). Among the three variable selection techniques, overall, the GA method yielded the optimal predictability. However, due to its long computation time, one alternative was to use CARS method. The results of this study confirm that a suitable combination of FOD and variable selection can effectively improve the model performance of SOM in moist soil.

Impact of Fractional Calculus on Correlation Coefficient between Available Potassium and Spectrum Data in Ground Hyperspectral and Landsat 8 Image

“…Fractional derivative also raises the correlation coefficient between electricity conductivity and soil reflectance spectra for some bands. Hong et al [33] applied the fractional derivative to analyze the relationship of soil organic matter content and visible and near-infrared spectroscopy. The results show that the highest validation model appears in the 1.5-order derivative combined genetic algorithm.…”

Toward Quantifying Oil Contamination in Vegetated Areas Using Very High Spatial and Spectral Resolution Imagery

“…Several approaches have been proposed in previous studies aiming to quantify heavy metals from vegetation reflectance in the field, especially partial least square regression (PLSR) [66,68]. PLSR is not suitable for TPH quantification [43], therefore, in this study, we proposed another regression approach, the elastic net (ENET [69]), which shows multiple advantages but remains underexploited in remote sensing of vegetation [70,71]. ENET is a penalized least squared approach that allows efficient variable selection under multicollinearity, which is a major limitation of other multiple regression approaches when dealing with hyperspectral data.…”

Peer Review #1 of "Quantitative estimation of wastewater quality parameters by hyperspectral band screening using GC, VIP and SPA (v0.1)"

“…Each water sample was measured twice vertically, and at each of which the spectral data were gathered ten times. Altogether there were 20 spectrum curves for each sample (Hong et al, 2018). From the 20 curves the raw spectral reflectance (R raw ), namely, arithmetic mean, were obtained by using ViewSpecPro software (6.0 version).…”