Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry Measurements
Spectroscopy has demonstrated the ability to predict specific soil properties. Consequently, it is a promising avenue to complement the traditional methods that are costly and time-consuming. In the visible-near infrared (Vis-NIR) region, spectroscopy has been widely used for the rapid determination...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/18/3082 |
| _version_ | 1797553142079946752 |
|---|---|
| author | James Kobina Mensah Biney Luboš Borůvka Prince Chapman Agyeman Karel Němeček Aleš Klement |
| author_facet | James Kobina Mensah Biney Luboš Borůvka Prince Chapman Agyeman Karel Němeček Aleš Klement |
| author_sort | James Kobina Mensah Biney |
| collection | DOAJ |
| description | Spectroscopy has demonstrated the ability to predict specific soil properties. Consequently, it is a promising avenue to complement the traditional methods that are costly and time-consuming. In the visible-near infrared (Vis-NIR) region, spectroscopy has been widely used for the rapid determination of organic components, especially soil organic carbon (SOC) using laboratory dry (lab-dry) measurement. However, steps such as collecting, grinding, sieving and soil drying at ambient (room) temperature and humidity for several days, which is a vital process, make the lab-dry preparation a bit slow compared to the field or laboratory wet (lab-wet) measurement. The use of soil spectra measured directly in the field or on a wet sample remains challenging due to uncontrolled soil moisture variations and other environmental conditions. However, for direct and timely prediction and mapping of soil properties, especially SOC, the field or lab-wet measurement could be an option in place of the lab-dry measurement. This study focuses on comparison of field and naturally acquired laboratory measurement of wet samples in Visible (VIS), Near-Infrared (NIR) and Vis-NIR range using several pretreatment approaches including orthogonal signal correction (OSC). The comparison was concluded with the development of validation models for SOC prediction based on partial least squares regression (PLSR) and support vector machine (SVMR). Nonetheless, for the OSC implementation, we use principal component regression (PCR) together with PLSR as SVMR is not appropriate under OSC. For SOC prediction, the field measurement was better in the VIS range with R<sup>2</sup><sub>CV</sub> = 0.47 and RMSEPcv = 0.24, while in Vis-NIR range the lab-wet measurement was better with R<sup>2</sup><sub>CV</sub> = 0.44 and RMSEPcv = 0.25, both using the SVMR algorithm. However, the prediction accuracy improves with the introduction of OSC on both samples. The highest prediction was obtained with the lab-wet dataset (using PLSR) in the NIR and Vis-NIR range with R<sup>2</sup><sub>CV</sub> = 0.54/0.55 and RMSEPcv = 0.24. This result indicates that the field and, in particular, lab-wet measurements, which are not commonly used, can also be useful for SOC prediction, just as the lab-dry method, with some adjustments. |
| first_indexed | 2024-03-10T16:12:12Z |
| format | Article |
| id | doaj.art-fdb5775d5a924b7291ebeb35e2f55e2a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T16:12:12Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-fdb5775d5a924b7291ebeb35e2f55e2a2023-11-20T14:26:04ZengMDPI AGRemote Sensing2072-42922020-09-011218308210.3390/rs12183082Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry MeasurementsJames Kobina Mensah Biney0Luboš Borůvka1Prince Chapman Agyeman2Karel Němeček3Aleš Klement4Department of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, 16500 Prague-Suchdol, Czech RepublicDepartment of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, 16500 Prague-Suchdol, Czech RepublicDepartment of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, 16500 Prague-Suchdol, Czech RepublicDepartment of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, 16500 Prague-Suchdol, Czech RepublicDepartment of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, 16500 Prague-Suchdol, Czech RepublicSpectroscopy has demonstrated the ability to predict specific soil properties. Consequently, it is a promising avenue to complement the traditional methods that are costly and time-consuming. In the visible-near infrared (Vis-NIR) region, spectroscopy has been widely used for the rapid determination of organic components, especially soil organic carbon (SOC) using laboratory dry (lab-dry) measurement. However, steps such as collecting, grinding, sieving and soil drying at ambient (room) temperature and humidity for several days, which is a vital process, make the lab-dry preparation a bit slow compared to the field or laboratory wet (lab-wet) measurement. The use of soil spectra measured directly in the field or on a wet sample remains challenging due to uncontrolled soil moisture variations and other environmental conditions. However, for direct and timely prediction and mapping of soil properties, especially SOC, the field or lab-wet measurement could be an option in place of the lab-dry measurement. This study focuses on comparison of field and naturally acquired laboratory measurement of wet samples in Visible (VIS), Near-Infrared (NIR) and Vis-NIR range using several pretreatment approaches including orthogonal signal correction (OSC). The comparison was concluded with the development of validation models for SOC prediction based on partial least squares regression (PLSR) and support vector machine (SVMR). Nonetheless, for the OSC implementation, we use principal component regression (PCR) together with PLSR as SVMR is not appropriate under OSC. For SOC prediction, the field measurement was better in the VIS range with R<sup>2</sup><sub>CV</sub> = 0.47 and RMSEPcv = 0.24, while in Vis-NIR range the lab-wet measurement was better with R<sup>2</sup><sub>CV</sub> = 0.44 and RMSEPcv = 0.25, both using the SVMR algorithm. However, the prediction accuracy improves with the introduction of OSC on both samples. The highest prediction was obtained with the lab-wet dataset (using PLSR) in the NIR and Vis-NIR range with R<sup>2</sup><sub>CV</sub> = 0.54/0.55 and RMSEPcv = 0.24. This result indicates that the field and, in particular, lab-wet measurements, which are not commonly used, can also be useful for SOC prediction, just as the lab-dry method, with some adjustments.https://www.mdpi.com/2072-4292/12/18/3082vis-NIR spectroscopysoil organic carbonproximal sensingmachine-learningpretreatment methodsspectral datasets (field-wet) |
| spellingShingle | James Kobina Mensah Biney Luboš Borůvka Prince Chapman Agyeman Karel Němeček Aleš Klement Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry Measurements Remote Sensing vis-NIR spectroscopy soil organic carbon proximal sensing machine-learning pretreatment methods spectral datasets (field-wet) |
| title | Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry Measurements |
| title_full | Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry Measurements |
| title_fullStr | Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry Measurements |
| title_full_unstemmed | Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry Measurements |
| title_short | Comparison of Field and Laboratory Wet Soil Spectra in the Vis-NIR Range for Soil Organic Carbon Prediction in the Absence of Laboratory Dry Measurements |
| title_sort | comparison of field and laboratory wet soil spectra in the vis nir range for soil organic carbon prediction in the absence of laboratory dry measurements |
| topic | vis-NIR spectroscopy soil organic carbon proximal sensing machine-learning pretreatment methods spectral datasets (field-wet) |
| url | https://www.mdpi.com/2072-4292/12/18/3082 |
| work_keys_str_mv | AT jameskobinamensahbiney comparisonoffieldandlaboratorywetsoilspectrainthevisnirrangeforsoilorganiccarbonpredictionintheabsenceoflaboratorydrymeasurements AT lubosboruvka comparisonoffieldandlaboratorywetsoilspectrainthevisnirrangeforsoilorganiccarbonpredictionintheabsenceoflaboratorydrymeasurements AT princechapmanagyeman comparisonoffieldandlaboratorywetsoilspectrainthevisnirrangeforsoilorganiccarbonpredictionintheabsenceoflaboratorydrymeasurements AT karelnemecek comparisonoffieldandlaboratorywetsoilspectrainthevisnirrangeforsoilorganiccarbonpredictionintheabsenceoflaboratorydrymeasurements AT alesklement comparisonoffieldandlaboratorywetsoilspectrainthevisnirrangeforsoilorganiccarbonpredictionintheabsenceoflaboratorydrymeasurements |