Strategies for the efficient estimation of soil organic carbon at the field scale with vis-NIR spectroscopy: Spectral libraries and spiking vs. local calibrations

Abstract

Soil spectroscopy in the visible-to-near-infrared (vis-NIR) range is a cost-effective alternative analysis technique to determine soil organic carbon (SOC). The development and provision of large-scale soil spectral libraries (SSLs) further facilitates the application of vis-NIR spectroscopy for the rapid assessment of SOC. However, optimal strategies to apply SOC calibrations from SSLs to independent field sites have yet to be established.We tested the predictive ability of SOC calibrations based on three external SSLs at the national, regional and field scale by applying them to two field sites in Germany. The national-scale SSL was comprised as a subset of the European LUCAS 2009 topsoil database. This subset was further classified into a randomly selected subset and target site-specific subsets based on similarity of spectral characteristics and soil parent material. A regional- and a field-scale legacy dataset were additionally used to predict SOC at the two field sites and to compare the results with the performance of the LUCAS based models. SSL-based predictive models adapted to the characteristics of the target sites by means of spiking were evaluated against purely local calibrations.Models calibrated with spectra from the LUCAS library and the regional-scale dataset predicted the SOC contents of the target field sites generally poorly (0.45 ≤ RPD ≤ 2.08), largely as a result of biased estimates. Spiking the models with only a few (~15) samples from the target sites reduced prediction bias drastically and thus yielded markedly improved SOC estimates for nearly all redeveloped models (1.30 ≤ RPD ≤ 3.69). Spiking the models based on the field-scale SSL with 15 samples produced better results than the spiked larger national and regional calibration sets, with RPD values of 5.66 and 4.14 for both target sites.Our results suggest that universal calibrations based exclusively on library spectra of larger scale are insufficient for accurate SOC assessments at the local scale even with pedogenetically or spectrally adapted calibration subsets. Spiking the vis-NIR models based on SSLs with a small number of target site samples allows a successful transfer of SOC calibrations, but does not necessarily yield more accurate predictions than local models developed exclusively with the spiking samples or calibrations based on field-scale SSL with similar characteristics, which may be preferable for model development if available.