Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon
This study proposes a novel methodology to employ discrete point spectra as input variable for digital mapping of soil organic carbon (SOC). Accordingly, two SOC modeling approaches were used in three agricultural sites in Czech Republic: i) machine learning (ML) including partial least squares regr...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-03-01
|
| Series: | International Soil and Water Conservation Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095633924000716 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556964859969536 |
|---|---|
| author | Vahid Khosravi Asa Gholizadeh Radka Kodešová Prince Chapman Agyeman Mohammadmehdi Saberioon Luboš Borůvka |
| author_facet | Vahid Khosravi Asa Gholizadeh Radka Kodešová Prince Chapman Agyeman Mohammadmehdi Saberioon Luboš Borůvka |
| author_sort | Vahid Khosravi |
| collection | DOAJ |
| description | This study proposes a novel methodology to employ discrete point spectra as input variable for digital mapping of soil organic carbon (SOC). Accordingly, two SOC modeling approaches were used in three agricultural sites in Czech Republic: i) machine learning (ML) including partial least squares regression (PLSR), cubist, random forest (RF), and support vector regression (SVR), and ii) regression kriging (RK) by the combination of ordinary kriging (OK) and PLSR (PLSR-K), cubist (cubist-K), RF (RF-K), and SVR (SVR-K). Models were developed on environmental predictor covariates (EPCs) and thirty genetic algorithms (GA)-selected visible, near-infrared, and shortwave-infrared (VNIR–SWIR) wavelengths spectra, individually and combined. Thirty rasters were then created using interpolation of the selected spectra and served as the input variables – with and without EPCs – to test and compare the developed models and SOC predictive maps with each other and with those retrieved from the third approach: iii) kriging using OK of the measured and ML-predicted SOC. The impact of employing selected wavelengths’ spectra and EPCs on models' performance was investigated using independent test samples and the uncertainty associated with the produced maps. Using interpolated spectra as the only input variable yielded a relatively acceptable accuracy (Nová Ves: RMSE = 0.19%, Údrnice: RMSE = 0.12%, Klučov: RMSE = 0.13%). In comparison, the interpolated spectra coupled with EPCs enhanced the results. Regarding the uncertainty, however, the ML-based SOC maps were more reliable, than RK-based ones. Furthermore, maps produced using both spectra and EPCs showed less uncertainty than those constructed on the individual datasets. |
| format | Article |
| id | doaj-art-b327c360030c468a9d4746811d642292 |
| institution | Kabale University |
| issn | 2095-6339 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | International Soil and Water Conservation Research |
| spelling | doaj-art-b327c360030c468a9d4746811d6422922025-01-07T04:17:18ZengKeAi Communications Co., Ltd.International Soil and Water Conservation Research2095-63392025-03-01131203214Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbonVahid Khosravi0Asa Gholizadeh1Radka Kodešová2Prince Chapman Agyeman3Mohammadmehdi Saberioon4Luboš Borůvka5Department of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, Kamycka 129, Suchdol, Prague, 16500, Czech Republic; Corresponding author.Department of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, Kamycka 129, Suchdol, Prague, 16500, Czech RepublicDepartment of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, Kamycka 129, Suchdol, Prague, 16500, Czech RepublicDepartment of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, Kamycka 129, Suchdol, Prague, 16500, Czech RepublicHelmholtz Centre Potsdam GFZ German Research Centre for Geosciences, Section 1.4 Remote Sensing and Geoinformatics, Telegrafenberg, Potsdam, 14473, GermanyDepartment of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, Kamycka 129, Suchdol, Prague, 16500, Czech RepublicThis study proposes a novel methodology to employ discrete point spectra as input variable for digital mapping of soil organic carbon (SOC). Accordingly, two SOC modeling approaches were used in three agricultural sites in Czech Republic: i) machine learning (ML) including partial least squares regression (PLSR), cubist, random forest (RF), and support vector regression (SVR), and ii) regression kriging (RK) by the combination of ordinary kriging (OK) and PLSR (PLSR-K), cubist (cubist-K), RF (RF-K), and SVR (SVR-K). Models were developed on environmental predictor covariates (EPCs) and thirty genetic algorithms (GA)-selected visible, near-infrared, and shortwave-infrared (VNIR–SWIR) wavelengths spectra, individually and combined. Thirty rasters were then created using interpolation of the selected spectra and served as the input variables – with and without EPCs – to test and compare the developed models and SOC predictive maps with each other and with those retrieved from the third approach: iii) kriging using OK of the measured and ML-predicted SOC. The impact of employing selected wavelengths’ spectra and EPCs on models' performance was investigated using independent test samples and the uncertainty associated with the produced maps. Using interpolated spectra as the only input variable yielded a relatively acceptable accuracy (Nová Ves: RMSE = 0.19%, Údrnice: RMSE = 0.12%, Klučov: RMSE = 0.13%). In comparison, the interpolated spectra coupled with EPCs enhanced the results. Regarding the uncertainty, however, the ML-based SOC maps were more reliable, than RK-based ones. Furthermore, maps produced using both spectra and EPCs showed less uncertainty than those constructed on the individual datasets.http://www.sciencedirect.com/science/article/pii/S2095633924000716SOC modeling and mappingInterpolated spectraMachine learningRegression krigingUncertainty |
| spellingShingle | Vahid Khosravi Asa Gholizadeh Radka Kodešová Prince Chapman Agyeman Mohammadmehdi Saberioon Luboš Borůvka Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon International Soil and Water Conservation Research SOC modeling and mapping Interpolated spectra Machine learning Regression kriging Uncertainty |
| title | Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon |
| title_full | Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon |
| title_fullStr | Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon |
| title_full_unstemmed | Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon |
| title_short | Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon |
| title_sort | visible near infrared and shortwave infrared spectra as an input variable for digital mapping of soil organic carbon |
| topic | SOC modeling and mapping Interpolated spectra Machine learning Regression kriging Uncertainty |
| url | http://www.sciencedirect.com/science/article/pii/S2095633924000716 |
| work_keys_str_mv | AT vahidkhosravi visiblenearinfraredandshortwaveinfraredspectraasaninputvariablefordigitalmappingofsoilorganiccarbon AT asagholizadeh visiblenearinfraredandshortwaveinfraredspectraasaninputvariablefordigitalmappingofsoilorganiccarbon AT radkakodesova visiblenearinfraredandshortwaveinfraredspectraasaninputvariablefordigitalmappingofsoilorganiccarbon AT princechapmanagyeman visiblenearinfraredandshortwaveinfraredspectraasaninputvariablefordigitalmappingofsoilorganiccarbon AT mohammadmehdisaberioon visiblenearinfraredandshortwaveinfraredspectraasaninputvariablefordigitalmappingofsoilorganiccarbon AT lubosboruvka visiblenearinfraredandshortwaveinfraredspectraasaninputvariablefordigitalmappingofsoilorganiccarbon |