Abstract
In situ, diffuse reflectance spectroscopy (DRS) profile soil sensors have the potential to provide both rapid and high-resolution prediction of multiple soil properties for precision agriculture, soil health assessment, and other applications related to environmental protection and agronomic sustainability. However, the effects of soil moisture, other environmental factors, and artefacts of the in-field spectral data collection process often hamper the utility of in situ DRS data. Various processing and modeling techniques have been developed to overcome these challenges, including external parameter orthogonalization (EPO) transformation of the spectra. In addition, Bayesian modeling approaches may improve prediction over traditional partial least squares (PLS) regression. The objectives of this study were to predict soil organic carbon (SOC), total nitrogen (TN), and texture fractions using a large, regional dataset of in situ profile DRS spectra and compare the performance of (1) traditional PLS analysis, (2) PLS on EPO-transformed spectra (PLS-EPO), (3) PLS-EPO with the Bayesian Lasso (PLS-EPO-BL), and (4) covariate-assisted PLS-EPO-BL models. In this study, soil cores and in situ profile DRS spectrometer scans were obtained to ~1 m depth from 22 fields across Missouri and Indiana, USA. In the laboratory, soil cores were split by horizon, air-dried, and sieved (<2 mm) for a total of 708 samples. Soil properties were measured and DRS spectra were collected on these air-dried soil samples. The data were randomly split into training (n = 308), testing (n = 200), and EPO calibration (n = 200) sets, and soil textural class was used as the categorical covariate in the Bayesian models. Model performance was evaluated using the root mean square error of prediction (RMSEP). For the prediction of soil properties using a model trained on dry spectra and tested on field moist spectra, the PLS-EPO transformation dramatically improved model performance relative to PLS alone, reducing RMSEP by 66% and 53% for SOC and TN, respectively, and by 76%, 91%, and 87% for clay, silt, and sand, respectively. The addition of the Bayesian Lasso further reduced RMSEP by 4–11% across soil properties, and the categorical covariate reduced RMSEP by another 2–9%. Overall, this study illustrates the strength of the combination of EPO spectral transformation paired with Bayesian modeling techniques to overcome environmental factors and in-field data collection artefacts when using in situ DRS data, and highlights the potential for in-field DRS spectroscopy as a tool for rapid, high-resolution prediction of soil properties.
Highlights
On-the-go diffuse reflectance spectroscopy (DRS) sensors in the visible (VIS; 400–700 nm) and near-infrared (NIR; 700–2500 nm) range have the potential to provide high-resolution spatial data quickly at low cost
For the prediction of soil properties using a model trained on dry spectra and tested on field moist spectra, the partial least squares (PLS)-external parameter orthogonalization (EPO) transformation dramatically improved model performance relative to PLS alone, reducing root mean square error of prediction (RMSEP) by 66% and 53% for soil organic carbon (SOC) and total nitrogen (TN), respectively, and by 76%, 91%, and
This study demonstrated the potential for in situ profile DRS spectral data to predict soil properties under variable field conditions, using the EPO transformation in conjunction with the Bayesian Lasso along with additional covariate information using models developed on dry spectra
Summary
On-the-go diffuse reflectance spectroscopy (DRS) sensors in the visible (VIS; 400–700 nm) and near-infrared (NIR; 700–2500 nm) range have the potential to provide high-resolution spatial data quickly at low cost. Prediction of multiple soil properties using DRS has been successful on air-dried surface samples [1,2,3], air-dried whole-profile soil samples [4], and moist samples [1,3,5] scanned in the laboratory. Some studies have compared predictions obtained at different soil moisture levels, with some reporting better results with dry soil [3,6] and others reporting better results with moist soil [7,8]. In a field setting, spectra are sensitive to other environmental conditions (e.g., temperature and soil structure) along with soil moisture, decreasing prediction accuracy and the utility of spectra collected in the field [3,5,9,10,11,12]
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
