A Spectral Transfer Function to Harmonize Existing Soil Spectral Libraries Generated by Different Protocols
Authors:
- Nicolas FrancosNFNicolas Francos
- Daniela Heller-PearlshtienDHDaniela Heller-Pearlshtien
- José A. M. DemattêJDJosé A. M. Demattê
- Bas Van WesemaelBWBas Van Wesemael
- Robert MilewskiRobert Milewski
- Sabine ChabrillatSabine Chabrillat
- Nikolaos TziolasNTNikolaos Tziolas
- Adrian Sanz DiazADAdrian Sanz Diaz
- María Julia Yagüe BallesterMBMaría Julia Yagüe Ballester
- Asa GholizadehAsa Gholizadeh
- Eyal Ben-DorEyal Ben-Dor
Open Access
- 20 January 2023
- journal article
- research article
- Published by Wiley in Applied and Environmental Soil Science
- Vol. 2023, 1-17
Abstract
Soil spectral libraries (SSLs) are important big-data archives (spectra associated with soil properties) that are analyzed via machine-learning algorithms to estimate soil attributes. Since different spectral measurement protocols are applied when constructing SSLs, it is necessary to examine harmonization techniques to merge the data. In recent years, several techniques for harmonization have been proposed, among which the internal soil standard (ISS) protocol is the most largely applied and has demonstrated its capacity to rectify systematic effects during spectral measurements. Here, we postulate that a spectral transfer function (TF) can be extracted between existing (old) SSLs if a subset of samples from two (or more) different SSLs are remeasured using the ISS protocol. A machine-learning TF strategy was developed, assembling random forest (RF) spectral-based models to predict the ISS spectral condition using soil samples from two existing SSLs. These SSLs had already been measured using different protocols without any ISS treatment the Brazilian (BSSL, generated in 2019) and the European (LUCAS, generated in 20092012) SSLs. To verify the TFs ability to improve the spectral assessment of soil attributes after harmonizing the different SSLs protocols, RF spectral-based models for estimating organic carbon (OC) in soil were developed. The results showed high spectral similarities between the ISS and the ISSTF spectral observations, indicating that post-ISS rectification is possible. Furthermore, after merging the SSLs with the TFs, the spectral-based assessment of OC was considerably improved, from R2=0.61, RMSE (g/kg)=12.46 to R2=0.69, RMSE (g/kg)=11.13. Given our results, this paper enhances the importance of soil spectroscopy by contributing to analyses in remote sensing, soil surveys, and digital soil mapping.Keywords
Funding Information
- European Space Agency
- H2020 European Joint Programme
This publication has 26 references indexed in Scilit:
- Performance of Three Identical Spectrometers in Retrieving Soil Reflectance under Laboratory ConditionsSoil Science Society of America Journal, 2011
- Comparison of soil reflectance spectra and calibration models obtained using multiple spectrometersGeoderma, 2011
- Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopyTrAC Trends in Analytical Chemistry, 2010
- Improved analysis and modelling of soil diffuse reflectance spectra using waveletsEuropean Journal of Soil Science, 2009
- Spectral reflectance based indices for soil organic carbon quantificationGeoderma, 2008
- Global soil characterization with VNIR diffuse reflectance spectroscopyGeoderma, 2006
- Quality assessment of several methods to recover surface reflectance using synthetic imaging spectroscopy dataRemote Sensing of Environment, 2004
- Development of Reflectance Spectral Libraries for Characterization of Soil PropertiesSoil Science Society of America Journal, 2002
- The spectral image processing system (SIPS)—interactive visualization and analysis of imaging spectrometer dataRemote Sensing of Environment, 1993
- Characteristic Variations in Reflectance of Surface SoilsSoil Science Society of America Journal, 1981