Modeling soil organic carbon content using mid-infrared absorbance spectra and a nonnegative MCR-ALS analysis

Abstract

A new approach based on mid-IR absorbance spectra is proposed for modeling total organic carbon (TOC) content in soils. This approach involves a first-time bilinear decomposition of soil mid-IR absorbance spectra using nonnegative multivariate curve resolution (MCR) with an alternating least square (ALS) algorithm. An MCR-ALS-derived component signifies a chemically meaningful combination of soil constituents. This new mechanistic model has been developed to link the soil composition, expressed in terms of ratios of MCR-ALS-based concentration scores of the identified components, to soil TOC value. Nonnegative MCR-ALS decomposition, performed for 213 mid-IR absorbance spectra of soil samples collected in the north and south of Israel, yielded four components. Fitting the mechanistic model-derived TOC to the experimental TOC values exhibited a TOC content threshold that affected model performance. TOC content <1.0 % w w⁻¹ was represented by the root mean square deviation of 0.18% with 62% of the variance being explained, whereas for larger TOC values, a sharp decline in model performance was observed. The existence of this TOC threshold in determining model performance suggested that successful TOC modeling (below 1%) could be indirect and related to IR spectral fingerprints of minerals binding soil organic matter (SOM) and forming organo-mineral complexes. Thus, a SOM fraction having weak interactions with soil minerals was poorly accounted for in some soil samples. The dependency of the model performance on soil TOC contents suggests that it might be possible to differentiate between soil samples based on their different dominating SOM pools, mineral-associated ones and those having weak interactions with minerals. Further studies, especially in soils with high SOM content, are needed to validate our findings.