Abstract
In soil proximal sensing with visible and near-infrared spectroscopy, the currently available hyperspectral snapshot camera technique allows a rapid image data acquisition in a portable mode. This study describes how readings of a hyperspectral camera in the 450–950 nm region could be utilised for estimating soil parameters, which were soil organic carbon (OC), hot-water extractable-C, total nitrogen and clay content; readings were performed in the lab for raw samples without any crushing. As multivariate methods, we used PLSR with full spectra (FS) and also combined with two conceptually different methods of spectral variable selection (CARS, “competitive adaptive reweighted sampling” and IRIV, “iteratively retaining informative variables”). For the accuracy of obtained estimates, it was beneficial to use segmented images instead of image mean spectra, for which we applied a regular decomposing in sub-images all of the same size and k-means clustering. Based on FS-PLSR with image mean spectra, obtained estimates were not useful with RPD values less than 1.50 and R2 values being 0.51 in the best case. With segmented images, improvements were marked for all soil properties; RPD reached values ≥ 1.68 and R2 ≥ 0.66. For all image data and variables, IRIV-PLSR slightly outperformed CARS-PLSR.
Highlights
The demand for out-of-the-lab inventories initiated the early field spectroscopic experiments with non-imaging point measurements, which originated from laboratory spectroscopy and required respective developments in photonics and portable platform techniques, for example
Estimates obtained with full spectra (FS)-partial least squares regression (PLSR), CARS-PLSR and informative variables (IRIV)-PLSR in the cross-validation and from model application to segmented images are summarised for N, hot water-extractable carbon (HWE-C) and CL in Table 2; for organic carbon (OC), that is intrinsically coupled to soil organic matter and usually highly correlated with N
In case of averaged image spectra, we found for all constituents an order of obtained accuracies that was IRIV-PLSR > CARS-PLSR > FS-PLSR
Summary
The demand for out-of-the-lab inventories initiated the early field spectroscopic experiments with non-imaging point measurements, which originated from laboratory spectroscopy and required respective developments in photonics and portable platform techniques, for example. Portable or hand-held field spectroradiometers were very popular in soil spectroscopy [1,2,3] as they assured flexible and rapid data acquisition. Non-imaging field spectroradiometers provide the highest available spectral resolution and high information content for estimating soil properties with multivariate methods. Campaigns with portable field spectroscopy are often complemented by data of air- or spaceborne imaging spectrometers to cover larger areas; large area coverage in flight campaigns often leads to decreased accuracies of estimated soil properties compared to point measurements (due to a lower signal-to-noise ratio and disturbing atmospheric influences, for example). Variable soil and surface properties (as moisture content, roughness, crusting or texture) induce spectral variability that is critical for large-scale calibration approaches and may be met by stratified approaches [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.
