Transferability of Vis‐NIR models for Soil Organic Carbon Estimation between Two Study Areas by using Spiking

Authors:
Publisher website
Google Scholar
Abstract
Core Ideas: Vis‐NIR spectroscopy was applied to estimate soil organic carbon in two different study areas. Model developed in one study area couldn't be transferred in the other area. We used spiking strategy to adapt the calibration models to target area characteristics. | s 2 –σ 2 | could be used to identify the optimal spiking samples to improve model transferability. Visible and near infrared (Vis‐NIR) spectroscopy technique has been shown to be a cost‐effective alternative for rapidly analyzing soil organic carbon (SOC). However, great challenges remain when applying a Vis‐NIR model for SOC estimation developed in one study area to other study areas without further calibration. The scope of this study was to use spiking strategy to improve the transferability of Vis‐NIR models between two study areas. Specifically, we explored the optimal spiking subset by adding different quantities of spiking samples to construct different‐sized models, and the strategy of spiking with extra‐weighting was used for comparison. Soil data was acquired in two independent study areas (WH area and HH area) in Hubei Province, Central China. The reflectance spectra and SOC contents were measured in the laboratory. Partial least squares regression (PLSR) was used for model calibration. The representativeness of the spiking samples was assessed through the absolute difference between the selected sample variance (s 2 ) and the original variance (σ 2 ) in the principal component space derived from soil spectra. Results showed that the initial models yielded successful SOC predictions for the soil samples from the same area as the calibration samples, but failed in those samples from the other area. Spiking improved the model transferability between these two study areas. Approximately 33%/48% of the HH/WH calibration set was required as spiking samples in model calibrations and applications in the other area. Spiking with extra‐weighting was of limited use in small‐sized spectral libraries. The use of | s 2 –σ 2 | is potentially effective in identifying the optimal spiking samples to improve model transferability between different small‐sized study areas in the Vis‐NIR assessments of SOC.
Funding Information
  • National Natural Science Foundation of China (41771440, 41501444)

This publication has 50 references indexed in Scilit: