In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil Investigation
Visible and near-infrared (VIS-NIR) spectroscopy is extensively used in the field of soil science to predict several soil properties, mostly in laboratory conditions. When measured in situ, contact probes are used, and, very often, time-consuming methods are applied to generate better spectra. Unfor...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/12/5495 |
| _version_ | 1797592738124791808 |
|---|---|
| author | Guillaume Debaene Piotr Bartmiński Marcin Siłuch |
| author_facet | Guillaume Debaene Piotr Bartmiński Marcin Siłuch |
| author_sort | Guillaume Debaene |
| collection | DOAJ |
| description | Visible and near-infrared (VIS-NIR) spectroscopy is extensively used in the field of soil science to predict several soil properties, mostly in laboratory conditions. When measured in situ, contact probes are used, and, very often, time-consuming methods are applied to generate better spectra. Unfortunately, spectra obtained by these methods differ greatly from spectra remotely acquired. This study tried to address this issue by measuring reflectance spectra directly with a fibre optic or a 4° lens on bare untouched soils. C, N content and soil texture (sand, silt, and clay) prediction models were established using partial least-square (PLS) and support vector machine (SVM) regression. With spectral pre-processing, some satisfactory models were obtained, i.e., for C content (R<sup>2</sup> = 0.57; RMSE = 0.09%) and for N content (R<sup>2</sup> = 0.53; RMSE = 0.02%). Some models were improved when using moisture and temperature as auxiliary data for the modelling. Maps of C, N and clay content generated with laboratory and predicted values were presented. Based on this study, VIS-NIR spectra acquired with bare fibre optic and/or a 4° lens could be used to build prediction models in order to obtain basic preliminary information on soil composition at the field scale. The predicting maps seem suitable for a fast but rough field screening. |
| first_indexed | 2024-03-11T01:57:25Z |
| format | Article |
| id | doaj.art-d0962ae08dc34dfcb7836df82ef05172 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:57:25Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d0962ae08dc34dfcb7836df82ef051722023-11-18T12:31:52ZengMDPI AGSensors1424-82202023-06-012312549510.3390/s23125495In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil InvestigationGuillaume Debaene0Piotr Bartmiński1Marcin Siłuch2Department of Soil Science Erosion and Land Protection, Institute of Soil Science and Plant Cultivation, State Research Institute, ul. Czartoryskich 8, 24-100 Puławy, PolandDepartment of Geology, Soil Science and Geoinformation, Institute of Earth and Environmental Sciences, Maria Curie-Skłodowska University, ul. Kraśnicka 2cd, 20-718 Lublin, PolandDepartment of Geology, Soil Science and Geoinformation, Institute of Earth and Environmental Sciences, Maria Curie-Skłodowska University, ul. Kraśnicka 2cd, 20-718 Lublin, PolandVisible and near-infrared (VIS-NIR) spectroscopy is extensively used in the field of soil science to predict several soil properties, mostly in laboratory conditions. When measured in situ, contact probes are used, and, very often, time-consuming methods are applied to generate better spectra. Unfortunately, spectra obtained by these methods differ greatly from spectra remotely acquired. This study tried to address this issue by measuring reflectance spectra directly with a fibre optic or a 4° lens on bare untouched soils. C, N content and soil texture (sand, silt, and clay) prediction models were established using partial least-square (PLS) and support vector machine (SVM) regression. With spectral pre-processing, some satisfactory models were obtained, i.e., for C content (R<sup>2</sup> = 0.57; RMSE = 0.09%) and for N content (R<sup>2</sup> = 0.53; RMSE = 0.02%). Some models were improved when using moisture and temperature as auxiliary data for the modelling. Maps of C, N and clay content generated with laboratory and predicted values were presented. Based on this study, VIS-NIR spectra acquired with bare fibre optic and/or a 4° lens could be used to build prediction models in order to obtain basic preliminary information on soil composition at the field scale. The predicting maps seem suitable for a fast but rough field screening.https://www.mdpi.com/1424-8220/23/12/5495field measurementsnear-infrared spectroscopyPLSSVMsoil propertiessoil mapping |
| spellingShingle | Guillaume Debaene Piotr Bartmiński Marcin Siłuch In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil Investigation Sensors field measurements near-infrared spectroscopy PLS SVM soil properties soil mapping |
| title | In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil Investigation |
| title_full | In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil Investigation |
| title_fullStr | In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil Investigation |
| title_full_unstemmed | In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil Investigation |
| title_short | In Situ VIS-NIR Spectroscopy for a Basic and Rapid Soil Investigation |
| title_sort | in situ vis nir spectroscopy for a basic and rapid soil investigation |
| topic | field measurements near-infrared spectroscopy PLS SVM soil properties soil mapping |
| url | https://www.mdpi.com/1424-8220/23/12/5495 |
| work_keys_str_mv | AT guillaumedebaene insituvisnirspectroscopyforabasicandrapidsoilinvestigation AT piotrbartminski insituvisnirspectroscopyforabasicandrapidsoilinvestigation AT marcinsiłuch insituvisnirspectroscopyforabasicandrapidsoilinvestigation |