Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land
Soil organic matter (SOM) is vital for assessing the quality of arable land. A fast and reliable estimation of SOM is important to predict the soil carbon stock in cropland. In this study, we aimed to explore the potential of combining multitemporal Sentinel-2A imagery and random forest (RF) to impr...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/13/1/8 |
| _version_ | 1797447364666982400 |
|---|---|
| author | Li Wang Yong Zhou |
| author_facet | Li Wang Yong Zhou |
| author_sort | Li Wang |
| collection | DOAJ |
| description | Soil organic matter (SOM) is vital for assessing the quality of arable land. A fast and reliable estimation of SOM is important to predict the soil carbon stock in cropland. In this study, we aimed to explore the potential of combining multitemporal Sentinel-2A imagery and random forest (RF) to improve the accuracy of SOM estimates in the plough layer for cultivated land at a regional scale. The field data of SOM content were utilized along with multitemporal Sentinel-2A images acquired over three years during the bare soil period to develop spectral indices. The best bands and spectral indices were selected as prediction variables by using the RF algorithm. Partial least squares (PLS), geographically weighted regression (GWR), and RF were employed to calibrate spectral indices for the SOM content, and the optimal calibration model was used for the mapping of the SOM content in arable land at a regional scale. The results showed the following. (1) The multitemporal image estimation model outperformed the single-temporal image estimation model. The estimation model that utilized the optimal bands and spectral indices as prediction variables usually had better accuracy than the models based on full spectral data. (2) For the SOM content estimates, the performance was better with RF than with PLS and GWR in almost all cases. (3) The most accurate SOM estimation in the case area was achieved by using multitemporal images from 2018 and the RF calibration model based on the optimal bands and spectral indices as prediction variables, with <i>R</i><sup>2</sup><i><sub>val</sub></i> (coefficient of determination of the validation data set) = 0.67, <i>RMSE<sub>val</sub></i> (root mean square error of the validation dataset) = 2.05, and <i>RPIQ<sub>val</sub></i> (ratio of performance to interquartile range of the validation dataset) = 3.36. (4) The estimated SOM content in the plough layer for cultivated land throughout the study area ranged from 16.17 to 36.98 g kg<sup>−1</sup> and exhibited an increasing trend from north to south. In the current study, we developed a framework that combines multitemporal remote sensing imagery and RF for the SOM estimation, which can improve the accuracy of quantitative SOM estimations, provide a dynamic, rapid, and low-cost technique for understanding soil fertility, and offer an early warning of changes in soil quality. |
| first_indexed | 2024-03-09T13:54:59Z |
| format | Article |
| id | doaj.art-5f4267cfb4d14394bb2f07aa3fba410c |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-09T13:54:59Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-5f4267cfb4d14394bb2f07aa3fba410c2023-11-30T20:44:20ZengMDPI AGAgriculture2077-04722022-12-01131810.3390/agriculture13010008Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated LandLi Wang0Yong Zhou1Key Laboratory for Geographical Process Analysis & Simulation in Hubei Province, Central China Normal University, Wuhan 430079, ChinaKey Laboratory for Geographical Process Analysis & Simulation in Hubei Province, Central China Normal University, Wuhan 430079, ChinaSoil organic matter (SOM) is vital for assessing the quality of arable land. A fast and reliable estimation of SOM is important to predict the soil carbon stock in cropland. In this study, we aimed to explore the potential of combining multitemporal Sentinel-2A imagery and random forest (RF) to improve the accuracy of SOM estimates in the plough layer for cultivated land at a regional scale. The field data of SOM content were utilized along with multitemporal Sentinel-2A images acquired over three years during the bare soil period to develop spectral indices. The best bands and spectral indices were selected as prediction variables by using the RF algorithm. Partial least squares (PLS), geographically weighted regression (GWR), and RF were employed to calibrate spectral indices for the SOM content, and the optimal calibration model was used for the mapping of the SOM content in arable land at a regional scale. The results showed the following. (1) The multitemporal image estimation model outperformed the single-temporal image estimation model. The estimation model that utilized the optimal bands and spectral indices as prediction variables usually had better accuracy than the models based on full spectral data. (2) For the SOM content estimates, the performance was better with RF than with PLS and GWR in almost all cases. (3) The most accurate SOM estimation in the case area was achieved by using multitemporal images from 2018 and the RF calibration model based on the optimal bands and spectral indices as prediction variables, with <i>R</i><sup>2</sup><i><sub>val</sub></i> (coefficient of determination of the validation data set) = 0.67, <i>RMSE<sub>val</sub></i> (root mean square error of the validation dataset) = 2.05, and <i>RPIQ<sub>val</sub></i> (ratio of performance to interquartile range of the validation dataset) = 3.36. (4) The estimated SOM content in the plough layer for cultivated land throughout the study area ranged from 16.17 to 36.98 g kg<sup>−1</sup> and exhibited an increasing trend from north to south. In the current study, we developed a framework that combines multitemporal remote sensing imagery and RF for the SOM estimation, which can improve the accuracy of quantitative SOM estimations, provide a dynamic, rapid, and low-cost technique for understanding soil fertility, and offer an early warning of changes in soil quality.https://www.mdpi.com/2077-0472/13/1/8soil organic matterspectral indicesrandom forestcultivated landSentinel-2A |
| spellingShingle | Li Wang Yong Zhou Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land Agriculture soil organic matter spectral indices random forest cultivated land Sentinel-2A |
| title | Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land |
| title_full | Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land |
| title_fullStr | Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land |
| title_full_unstemmed | Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land |
| title_short | Combining Multitemporal Sentinel-2A Spectral Imaging and Random Forest to Improve the Accuracy of Soil Organic Matter Estimates in the Plough Layer for Cultivated Land |
| title_sort | combining multitemporal sentinel 2a spectral imaging and random forest to improve the accuracy of soil organic matter estimates in the plough layer for cultivated land |
| topic | soil organic matter spectral indices random forest cultivated land Sentinel-2A |
| url | https://www.mdpi.com/2077-0472/13/1/8 |
| work_keys_str_mv | AT liwang combiningmultitemporalsentinel2aspectralimagingandrandomforesttoimprovetheaccuracyofsoilorganicmatterestimatesintheploughlayerforcultivatedland AT yongzhou combiningmultitemporalsentinel2aspectralimagingandrandomforesttoimprovetheaccuracyofsoilorganicmatterestimatesintheploughlayerforcultivatedland |