Infrared spectroscopy is increasingly being adopted as a technology for soil analysis. However, laboratories worldwide are equipped with different infrared spectrometers, leading to variations that hinder the global application of soil spectroscopy. This study evaluates the transferability of soil spectra from a global dataset collected using four mid-infrared spectrometers. To evaluate the efficacy of five spectral transfer functions (direct standardization, piecewise direct standardization, spectral space transformation [SST], principal components-canonical correlation analysis [PC-CCA], and domain-invariant partial least square [DIPLS] regression), two datasets were used: dataset A (n = 224; standardized samples) was scanned using one primary spectrometer and three secondary spectrometers; dataset B (n = 1904; legacy samples) was scanned only using the primary spectrometer. The first set of chemometrics models was developed using dataset A to compare the performance of different spectrometers. The second set of models was developed using dataset B to evaluate the effectiveness of spectral transfer functions. Both models were developed using partial least squares regression. Spectral transfer functions developed using dataset A indicate that the PC-CCA method was the best in converging spectra collected from four instruments into a similar space projected using Uniform Manifold Approximation and Projection. Spectral transfer did not result in consistent improvement in the prediction of soil properties compared to the direct use of spectra collected from different spectrometers. These findings carry significant implications for the utilization of legacy models, enabling laboratories to concentrate on acquiring new samples and spectral measurements using established protocols without the need for spectral transfer.
This work is licensed under CC-BY 4.0
This work is licensed under CC-BY 4.0
DOI:
https://doi.org/10.1002/saj2.20697Altmetric score:
Dimensions Citation Count:
Export citation:
RIS (.ris)
TI - Exploring mid-infrared spectral transfer functions for the prediction of multiple soil properties using a global dataset
AU - Ng, W.
AU - Winowiecki, L.A.
AU - Karari, V.
AU - Weullow, E.
AU - Ateku, D.A.
AU - Vågen, T-G.
AU - Pittaki, Z.
AU - Minasny, B.
AB - Infrared spectroscopy is increasingly being adopted as a technology for soil analysis. However, laboratories worldwide are equipped with different infrared spectrometers, leading to variations that hinder the global application of soil spectroscopy. This study evaluates the transferability of soil spectra from a global dataset collected using four mid-infrared spectrometers. To evaluate the efficacy of five spectral transfer functions (direct standardization, piecewise direct standardization, spectral space transformation [SST], principal components-canonical correlation analysis [PC-CCA], and domain-invariant partial least square [DIPLS] regression), two datasets were used: dataset A (n = 224; standardized samples) was scanned using one primary spectrometer and three secondary spectrometers; dataset B (n = 1904; legacy samples) was scanned only using the primary spectrometer. The first set of chemometrics models was developed using dataset A to compare the performance of different spectrometers. The second set of models was developed using dataset B to evaluate the effectiveness of spectral transfer functions. Both models were developed using partial least squares regression. Spectral transfer functions developed using dataset A indicate that the PC-CCA method was the best in converging spectra collected from four instruments into a similar space projected using Uniform Manifold Approximation and Projection. Spectral transfer did not result in consistent improvement in the prediction of soil properties compared to the direct use of spectra collected from different spectrometers. These findings carry significant implications for the utilization of legacy models, enabling laboratories to concentrate on acquiring new samples and spectral measurements using established protocols without the need for spectral transfer.
PY - 2024
UR - https://www.cifor-icraf.org/knowledge/publication/36085/
DO - https://doi.org/10.1002/saj2.20697
KW - calibration, soil carbon, soil properties, spectrometry, spectroscopy
ER -Endnote (.ciw)
%T Exploring mid-infrared spectral transfer functions for the prediction of multiple soil properties using a global dataset
%A Ng, W.
%A Winowiecki, L.A.
%A Karari, V.
%A Weullow, E.
%A Ateku, D.A.
%A Vågen, T-G.
%A Pittaki, Z.
%A Minasny, B.
%D 2024
%U https://www.cifor-icraf.org/knowledge/publication/36085/
%R https://doi.org/10.1002/saj2.20697
%X Infrared spectroscopy is increasingly being adopted as a technology for soil analysis. However, laboratories worldwide are equipped with different infrared spectrometers, leading to variations that hinder the global application of soil spectroscopy. This study evaluates the transferability of soil spectra from a global dataset collected using four mid-infrared spectrometers. To evaluate the efficacy of five spectral transfer functions (direct standardization, piecewise direct standardization, spectral space transformation [SST], principal components-canonical correlation analysis [PC-CCA], and domain-invariant partial least square [DIPLS] regression), two datasets were used: dataset A (n = 224; standardized samples) was scanned using one primary spectrometer and three secondary spectrometers; dataset B (n = 1904; legacy samples) was scanned only using the primary spectrometer. The first set of chemometrics models was developed using dataset A to compare the performance of different spectrometers. The second set of models was developed using dataset B to evaluate the effectiveness of spectral transfer functions. Both models were developed using partial least squares regression. Spectral transfer functions developed using dataset A indicate that the PC-CCA method was the best in converging spectra collected from four instruments into a similar space projected using Uniform Manifold Approximation and Projection. Spectral transfer did not result in consistent improvement in the prediction of soil properties compared to the direct use of spectra collected from different spectrometers. These findings carry significant implications for the utilization of legacy models, enabling laboratories to concentrate on acquiring new samples and spectral measurements using established protocols without the need for spectral transfer.
%K calibration
%K soil carbon
%K soil properties
%K spectrometry
%K spectroscopy
Publication year
2024
ISSN
1435-0661
Authors
Ng, W.; Winowiecki, L.A.; Karari, V.; Weullow, E.; Ateku, D.A.; Vågen, T-G.; Pittaki, Z.; Minasny, B.
Language
English
Keywords
calibration, soil carbon, soil properties, spectrometry, spectroscopy
Source
Soil Science Society of America Journal. :
