Estimating coefficient of linear extensibility using Vis–NIR reflectance spectral data: Comparison of model validation approaches

Abstract

The coefficient of linear extensibility (COLE) is used to classify soils according to their swell-shrink potential, and its estimation is crucial for engineering and agronomic applications. The aims of the study were (a) to develop a visible-nearinfrared spectroscopy (Vis-NIRS, 400-2,500 nm) calibration model to estimate COLE, (b) to compare two model validation approaches (mixed data and countrywise), and (c) to test if a variable selection method improves the estimation accuracy of the calibration models. For this purpose, partial least square regression (PLSR) was used on the spectra of 53 soil samples from Slovakia and 24 samples from the United States. First, a calibration model based on 70% of the entire dataset (including samples from both locations) was developed and validated with the remaining 30% (mixed data approach). Second, a calibration model based on the Slovakian samples was validated with the U.S. samples (countrywise approach). Higher predictability for COLE with standardized root mean square error (SMRSE) of 0.099 was obtained for the mixed data approach than for the country-wise validation with SRMSE of 0.279. Furthermore, using interval PLSR (iPLSR) as a variable selection method did not improve the estimation accuracy of the mixed data approach (SRMSE of 0.099), and rather resulted in a twofold increase in SRMSE (0.560) for the country-wise validation approach. Overall, the good estimation of COLE from Vis-NIRS was attributed to the high correlation of COLE with clay content and spectrally active clay minerals. Abbreviations: COLE, coefficient of linear extensibility; iPLSR, interval partial least squares regression; OC, organic carbon; OM, organic matter; PLSR, partial least squares regression; RMSECV, root mean square error of cross-validation; RMSEP, root mean square error of prediction; SRMSE, standardized root mean square error; Vis-NIRS, visible-near-infrared spectroscopy. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Linking marginal soil to sugarcane productivity in Takalar, Indonesia

“…If the COLE value is high, the soil will crack easily (Yan et al, 2022) and be dangerous for plant roots (Vaught et al, 2006). The COLE value can describe soil physical changes such as soil shrinkage and swelling due to variations in water content (Rehman et al, 2020;Vaught et al, 2006;Yan et al, 2022).…”

Coefficient of linear extensibility of soil can be estimated from hygroscopic water content or clay and organic carbon contents

“…Soil shrinkage and swelling processes are common in soils with appreciable amounts of expandable clay minerals. These processes create movement in the vertical direction and cracks in the horizontal direction during wetting and drying cycles and significantly impact civil engineering applications (Gray & Allbrook, 2002; Rehman et al, 2020). Knowledge of the soil shrinkage‐swelling potential is important to avoid damage to buildings, bridges and roads when they are built on expansive soil.…”