Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian Soils
In contrast with classic bench-top hyperspectral (multispectral)-sensor-based instruments (spectrophotometers), the portable ones are rugged, relatively inexpensive, and simple to use; therefore, they are suitable for field implementation to more closely examine various soil properties on the spot....
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/7/2556 |
| _version_ | 1827622516135297024 |
|---|---|
| author | Nandkishor M. Dhawale Viacheslav I. Adamchuk Shiv O. Prasher Raphael A. Viscarra Rossel Ashraf A. Ismail |
| author_facet | Nandkishor M. Dhawale Viacheslav I. Adamchuk Shiv O. Prasher Raphael A. Viscarra Rossel Ashraf A. Ismail |
| author_sort | Nandkishor M. Dhawale |
| collection | DOAJ |
| description | In contrast with classic bench-top hyperspectral (multispectral)-sensor-based instruments (spectrophotometers), the portable ones are rugged, relatively inexpensive, and simple to use; therefore, they are suitable for field implementation to more closely examine various soil properties on the spot. The purpose of this study was to evaluate two portable spectrophotometers to predict key soil properties such as texture and soil organic carbon (SOC) in 282 soil samples collected from proportional fields in four Canadian provinces. Of the two instruments, one was the first of its kind (prototype) and was a mid-infrared (mid-IR) spectrophotometer operating between ~5500 and ~11,000 nm. The other instrument was a readily available dual-type spectrophotometer having a spectral range in both visible (vis) and near-infrared (NIR) regions with wavelengths ranging between ~400 and ~2220 nm. A large number of soil samples (<i>n</i> = 282) were used to represent a wide variety of soil textures, from clay loam to sandy soils, with a considerable range of SOC. These samples were subjected to routine laboratory soil analysis before both spectrophotometers were used to collect diffuse reflectance spectroscopy (DRS) measurements. After data collection, the mid-IR and vis-NIR spectra were randomly divided into calibration (70%) and validation (30%) sets. Partial least squares regression (PLSR) was used with leave one out cross-validation techniques to derive the spectral calibrations to predict SOC, sand, and clay content. The performances of the calibration models were reevaluated on the validation set. It was found that sand content can be predicted more accurately using the portable mid-IR spectrophotometer and clay content is better predicted using the readily available dual-type vis-NIR spectrophotometer. The coefficients of determination (R<sup>2</sup>) and root mean squared error (RMSE) were determined to be most favorable for clay (0.82 and 78 g kg<sup>−1</sup>) and sand (0.82 and 103 g kg<sup>−1</sup>), respectively. The ability to predict SOC content precisely was not particularly good for the dataset of soils used in this study with an R<sup>2</sup> and RMSE of 0.54 and 4.1 g kg<sup>−1</sup>. The tested method demonstrated that both portable mid-IR and vis-NIR spectrophotometers were comparable in predicting soil texture on a large soil dataset collected from agricultural fields in four Canadian provinces. |
| first_indexed | 2024-03-09T11:26:51Z |
| format | Article |
| id | doaj.art-b245e46c9c464831a7febd17216cfbea |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T11:26:51Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b245e46c9c464831a7febd17216cfbea2023-12-01T00:00:47ZengMDPI AGSensors1424-82202022-03-01227255610.3390/s22072556Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian SoilsNandkishor M. Dhawale0Viacheslav I. Adamchuk1Shiv O. Prasher2Raphael A. Viscarra Rossel3Ashraf A. Ismail4Department of Bioresource Engineering, McGill University, Sainte-Anne-de-Bellevue, QC H9X 3V9, CanadaDepartment of Bioresource Engineering, McGill University, Sainte-Anne-de-Bellevue, QC H9X 3V9, CanadaDepartment of Bioresource Engineering, McGill University, Sainte-Anne-de-Bellevue, QC H9X 3V9, CanadaDepartment of Soil and Landscape Science, Faculty of Science and Engineering, School of Molecular and Life Sciences, Curtin University, G.P.O. Box U1987, Perth, WA 6845, AustraliaDepartment of Food Science and Agricultural Chemistry, McGill University, Sainte-Anne-de-Bellevue, QC H9X 3V9, CanadaIn contrast with classic bench-top hyperspectral (multispectral)-sensor-based instruments (spectrophotometers), the portable ones are rugged, relatively inexpensive, and simple to use; therefore, they are suitable for field implementation to more closely examine various soil properties on the spot. The purpose of this study was to evaluate two portable spectrophotometers to predict key soil properties such as texture and soil organic carbon (SOC) in 282 soil samples collected from proportional fields in four Canadian provinces. Of the two instruments, one was the first of its kind (prototype) and was a mid-infrared (mid-IR) spectrophotometer operating between ~5500 and ~11,000 nm. The other instrument was a readily available dual-type spectrophotometer having a spectral range in both visible (vis) and near-infrared (NIR) regions with wavelengths ranging between ~400 and ~2220 nm. A large number of soil samples (<i>n</i> = 282) were used to represent a wide variety of soil textures, from clay loam to sandy soils, with a considerable range of SOC. These samples were subjected to routine laboratory soil analysis before both spectrophotometers were used to collect diffuse reflectance spectroscopy (DRS) measurements. After data collection, the mid-IR and vis-NIR spectra were randomly divided into calibration (70%) and validation (30%) sets. Partial least squares regression (PLSR) was used with leave one out cross-validation techniques to derive the spectral calibrations to predict SOC, sand, and clay content. The performances of the calibration models were reevaluated on the validation set. It was found that sand content can be predicted more accurately using the portable mid-IR spectrophotometer and clay content is better predicted using the readily available dual-type vis-NIR spectrophotometer. The coefficients of determination (R<sup>2</sup>) and root mean squared error (RMSE) were determined to be most favorable for clay (0.82 and 78 g kg<sup>−1</sup>) and sand (0.82 and 103 g kg<sup>−1</sup>), respectively. The ability to predict SOC content precisely was not particularly good for the dataset of soils used in this study with an R<sup>2</sup> and RMSE of 0.54 and 4.1 g kg<sup>−1</sup>. The tested method demonstrated that both portable mid-IR and vis-NIR spectrophotometers were comparable in predicting soil texture on a large soil dataset collected from agricultural fields in four Canadian provinces.https://www.mdpi.com/1424-8220/22/7/2556chemometricshyperspectral sensor instrumentson-the-spot soil analyzersportable spectrophotometersproximal soil sensingsensors |
| spellingShingle | Nandkishor M. Dhawale Viacheslav I. Adamchuk Shiv O. Prasher Raphael A. Viscarra Rossel Ashraf A. Ismail Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian Soils Sensors chemometrics hyperspectral sensor instruments on-the-spot soil analyzers portable spectrophotometers proximal soil sensing sensors |
| title | Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian Soils |
| title_full | Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian Soils |
| title_fullStr | Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian Soils |
| title_full_unstemmed | Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian Soils |
| title_short | Evaluation of Two Portable Hyperspectral-Sensor-Based Instruments to Predict Key Soil Properties in Canadian Soils |
| title_sort | evaluation of two portable hyperspectral sensor based instruments to predict key soil properties in canadian soils |
| topic | chemometrics hyperspectral sensor instruments on-the-spot soil analyzers portable spectrophotometers proximal soil sensing sensors |
| url | https://www.mdpi.com/1424-8220/22/7/2556 |
| work_keys_str_mv | AT nandkishormdhawale evaluationoftwoportablehyperspectralsensorbasedinstrumentstopredictkeysoilpropertiesincanadiansoils AT viacheslaviadamchuk evaluationoftwoportablehyperspectralsensorbasedinstrumentstopredictkeysoilpropertiesincanadiansoils AT shivoprasher evaluationoftwoportablehyperspectralsensorbasedinstrumentstopredictkeysoilpropertiesincanadiansoils AT raphaelaviscarrarossel evaluationoftwoportablehyperspectralsensorbasedinstrumentstopredictkeysoilpropertiesincanadiansoils AT ashrafaismail evaluationoftwoportablehyperspectralsensorbasedinstrumentstopredictkeysoilpropertiesincanadiansoils |