Proximal Soil Sensing of Low Salinity in Southern Xinjiang, China
Measuring the soil salinity using visible and near-infrared (vis–NIR) reflectance spectra is considered a fast and cost-effective method. For monitoring purposes, estimating soils with low salinity measured as electrical conductivity (EC) using vis–NIR spectra is still understudied. In this research...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/18/4448 |
| _version_ | 1797482878810980352 |
|---|---|
| author | Jie Peng Shuo Li Randa S. Makar Hongyi Li Chunhui Feng Defang Luo Jiali Shen Ying Wang Qingsong Jiang Linchuan Fang |
| author_facet | Jie Peng Shuo Li Randa S. Makar Hongyi Li Chunhui Feng Defang Luo Jiali Shen Ying Wang Qingsong Jiang Linchuan Fang |
| author_sort | Jie Peng |
| collection | DOAJ |
| description | Measuring the soil salinity using visible and near-infrared (vis–NIR) reflectance spectra is considered a fast and cost-effective method. For monitoring purposes, estimating soils with low salinity measured as electrical conductivity (EC) using vis–NIR spectra is still understudied. In this research, 399 legacy soil samples from six regions of Southern Xinjiang, China with low EC values were used. Reflectance spectra were measured in the laboratory on dried and ground soil samples using a portable vis–NIR spectrometer. By using 10-fold cross-validation, three algorithms–partial least-squares regression (PLSR), random forest (RF), and <span style="font-variant: small-caps;">Cubist</span>–were employed to develop statistical models of EC. The model performance evaluation was obtained by the relative importance of variants. In terms of accuracy assessment of soil EC prediction, the results demonstrated that the <span style="font-variant: small-caps;">Cubist</span> model performed better (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> = 0.67, RMSE = 0.16 mS/cm, RPIQ = 2.28) than both PLSR and RF. Despite similar variants for modelling, the RF model performed somewhat better than that of the PLSR. Additionally, the 610 nm and 790 nm wavelengths only demonstrated significant promise for predicting low soil EC values when used in the <span style="font-variant: small-caps;">Cubist</span> mode. The current research recommends the use of <span style="font-variant: small-caps;">Cubist</span> to estimate the low soil salinity using the vis–NIR reflectance spectra. |
| first_indexed | 2024-03-09T22:39:51Z |
| format | Article |
| id | doaj.art-90a86a7f9dd84662a18a8be4f40207cd |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T22:39:51Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-90a86a7f9dd84662a18a8be4f40207cd2023-11-23T18:42:45ZengMDPI AGRemote Sensing2072-42922022-09-011418444810.3390/rs14184448Proximal Soil Sensing of Low Salinity in Southern Xinjiang, ChinaJie Peng0Shuo Li1Randa S. Makar2Hongyi Li3Chunhui Feng4Defang Luo5Jiali Shen6Ying Wang7Qingsong Jiang8Linchuan Fang9College of Agriculture, Tarim University, Alar 843300, ChinaKey Laboratory for Geographical Process Analysis & Simulation of Hubei Province, College of Urban & Environmental Sciences, Central China Normal University, Wuhan 430079, ChinaSoils & Water Use Department, Agricultural & Biological Research Institute, National Research Centre, Cairo 12622, EgyptDepartment of Land Resource Management, School of Tourism and Urban Management, Jiangxi University of Finance and Economics, Nanchang 330000, ChinaCollege of Agriculture, Tarim University, Alar 843300, ChinaCollege of Agriculture, Tarim University, Alar 843300, ChinaKey Laboratory for Geographical Process Analysis & Simulation of Hubei Province, College of Urban & Environmental Sciences, Central China Normal University, Wuhan 430079, ChinaKey Laboratory for Geographical Process Analysis & Simulation of Hubei Province, College of Urban & Environmental Sciences, Central China Normal University, Wuhan 430079, ChinaCollege of Agriculture, Tarim University, Alar 843300, ChinaKey Laboratory for Geographical Process Analysis & Simulation of Hubei Province, College of Urban & Environmental Sciences, Central China Normal University, Wuhan 430079, ChinaMeasuring the soil salinity using visible and near-infrared (vis–NIR) reflectance spectra is considered a fast and cost-effective method. For monitoring purposes, estimating soils with low salinity measured as electrical conductivity (EC) using vis–NIR spectra is still understudied. In this research, 399 legacy soil samples from six regions of Southern Xinjiang, China with low EC values were used. Reflectance spectra were measured in the laboratory on dried and ground soil samples using a portable vis–NIR spectrometer. By using 10-fold cross-validation, three algorithms–partial least-squares regression (PLSR), random forest (RF), and <span style="font-variant: small-caps;">Cubist</span>–were employed to develop statistical models of EC. The model performance evaluation was obtained by the relative importance of variants. In terms of accuracy assessment of soil EC prediction, the results demonstrated that the <span style="font-variant: small-caps;">Cubist</span> model performed better (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> = 0.67, RMSE = 0.16 mS/cm, RPIQ = 2.28) than both PLSR and RF. Despite similar variants for modelling, the RF model performed somewhat better than that of the PLSR. Additionally, the 610 nm and 790 nm wavelengths only demonstrated significant promise for predicting low soil EC values when used in the <span style="font-variant: small-caps;">Cubist</span> mode. The current research recommends the use of <span style="font-variant: small-caps;">Cubist</span> to estimate the low soil salinity using the vis–NIR reflectance spectra.https://www.mdpi.com/2072-4292/14/18/4448soil salinizationvis–NIR spectroscopymachine learning<span style="font-variant: small-caps">Cubist</span> |
| spellingShingle | Jie Peng Shuo Li Randa S. Makar Hongyi Li Chunhui Feng Defang Luo Jiali Shen Ying Wang Qingsong Jiang Linchuan Fang Proximal Soil Sensing of Low Salinity in Southern Xinjiang, China Remote Sensing soil salinization vis–NIR spectroscopy machine learning <span style="font-variant: small-caps">Cubist</span> |
| title | Proximal Soil Sensing of Low Salinity in Southern Xinjiang, China |
| title_full | Proximal Soil Sensing of Low Salinity in Southern Xinjiang, China |
| title_fullStr | Proximal Soil Sensing of Low Salinity in Southern Xinjiang, China |
| title_full_unstemmed | Proximal Soil Sensing of Low Salinity in Southern Xinjiang, China |
| title_short | Proximal Soil Sensing of Low Salinity in Southern Xinjiang, China |
| title_sort | proximal soil sensing of low salinity in southern xinjiang china |
| topic | soil salinization vis–NIR spectroscopy machine learning <span style="font-variant: small-caps">Cubist</span> |
| url | https://www.mdpi.com/2072-4292/14/18/4448 |
| work_keys_str_mv | AT jiepeng proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT shuoli proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT randasmakar proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT hongyili proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT chunhuifeng proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT defangluo proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT jialishen proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT yingwang proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT qingsongjiang proximalsoilsensingoflowsalinityinsouthernxinjiangchina AT linchuanfang proximalsoilsensingoflowsalinityinsouthernxinjiangchina |