Can we use a mid-infrared fine-ground soil spectral library to predict non-fine-ground spectra?

Abstract

Mid-infrared (MIR) reflectance spectroscopy is a promising and rapid technology to accurately infer soil properties from a single scan. Fine-grinding is an expensive and time-consuming sample processing step in soil MIR spectroscopy that can have a major impact on spectral features and subsequent multivariate model calibrations. The use of existing fine-ground spectral libraries to predict soil properties of new samples (without fine-grinding) can reduce the cost and time in soil analysis. Calibration transfer studies between different grinding states of soil samples (using existing fine-ground spectral libraries to predict non-fine-ground spectra) are not available to the best of our knowledge. To address this research gap, this study investigated different calibration transfer and pre-processing techniques to link the MIR fine-ground spectral models and non-fine-ground soil spectra. Four calibration transfer techniques (direct standardization, external parameter orthogonalization, slope/bias correction, and spiking with extra weight) and four pre-processing techniques (first derivative, detrending, multiplicative signal correction, and standard normal variate) were investigated in this study. The United States Department of Agriculture National Soil Survey Center Kellogg Soil Survey Laboratory’s MIR spectral library (n > 72,000) and a randomly selected subset from the library (n = 519) were used as spectral datasets. Spiking (with extra weight) calibration transfer technique performed well for pH, clay, and sand when using the library (mean R2 = 0.70) and for organic carbon, cation exchange capacity, pH, clay, and sand when using the subset from the library (mean R2 = 0.66). Standard normal variate pre-processing technique performed well with organic carbon, cation exchange capacity, and sand when using the library (mean R2 = 0.67). Overall, spiking (with extra weight) enables the use of existing MIR fine-ground soil spectral libraries to predict those soil properties of new samples without fine-grinding, saving the cost and time.