Prediction of soil organic matter content based on characteristic band selection method

Xie, Shugang; Ding, Fangjun; Chen, Shigeng; Xi, Wang; Li, Yuhuan; Ma, Keping

doi:10.1016/j.saa.2022.120949

Cited by 32 publications

(18 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For Shajiang black soil, the accuracy of LR-CARS-PLSR and FDR-CARS-PLSR was slightly better than that of R-CARS-PLSR. Overall, this study showed that LR and FDR transformation improved the modeling accuracy, which was consistent with other research results [23,35,36,38].…”

Section: Plsr Modeling Based On Characteristic Wavelengthssupporting

confidence: 92%

“…FDR transformation showed better model performance than the second derivative transformation for SOM estimations in several modeling methods [36]. Some research has also explored the prediction effect of SOM content using characteristic wavelength screening combined with different spectral transformation techniques [38,39]. As shown above, characteristic wavelength screening, spectral transformation and combinations of two means have been widely applied to improve the accuracy of SOM spectral modeling.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Modeling of Soil Organic Matter Based on Characteristic Wavelength in East China

et al. 2022

View full text Add to dashboard Cite

Soil organic matter (SOM) is a key index of soil fertility. Visible and near-infrared (VNIR, 350–2500 nm) reflectance spectroscopy is an effective method for modeling SOM content. Characteristic wavelength screening and spectral transformation may improve the performance of SOM prediction. This study aimed to explore the optimal combination of characteristic wavelength selection and spectral transformation for hyperspectral modeling of SOM. A total of 219 topsoil (0–20 cm) samples were collected from two soil types in the East China. VNIR reflectance spectra were measured in the laboratory. Firstly, after spectral transformation (inverse-log reflectance (LR), continuum removal (CR) and first-order derivative reflectance (FDR)) of VNIR spectra, characteristic wavelengths were selected by competitive adaptive reweighted sampling (CARS) and uninformative variables elimination (UVE) algorithms. Secondly, the SOM prediction models were constructed based on the partial least squares regression (PLSR), random forest (RF) and support vector regression (SVR) methods using the full spectra and selected wavelengths, respectively. Finally, optimal SOM prediction models were selected for two soil types. The results were as follows: (1) The CARS algorithm screened 40–125 characteristic wavelengths from the full spectra. The UVE algorithm screened 105–884 characteristic wavelengths. (2) For two soil types and full spectra, CARS and UVE improved the SOM modeling precision based on the PLSR and SVR methods. The coefficient of determination (R2) value in the validation of the CARS-PLSR (PLSR model combined with CARS) and CARS-SVR (SVR model combined CARS) models ranged from 0.69 to 0.95, and the relative percent deviation (RPD) value ranged from 1.74 to 4.31. Lin’s concordance correlation coefficient (LCCC) values ranged from 0.83 to 0.97. The UVE-PLSR and UVE-SVR models showed moderate precision. (3) The PLSR and SVR modeling accuracies of Paddy soil were better than those for Shajiang black soil. RF models performed worse for both soil types, with the R2 values of validation ranging from 0.22 to 0.68 and RPD values ranging from 1.01 to 1.60. (4) For Paddy soil, the optimal SOM prediction models (highest R2 and RPD, lowest root mean square error (RMSE)) were CR-CARS-PLSR (R2 and RMSE: 0.97 and 1.21 g/kg in calibration sets, 0.95 and 1.72 g/kg in validation sets, RPD: 4.31) and CR-CARS-SVR (R2 and RMSE: 0.98 and 1.04 g/kg in calibration sets, 0.91 and 2.24 g/kg in validation sets, RPD: 3.37). For Shajiang black soil, the optimal SOM prediction models were LR-CARS-PLSR (R2 and RMSE: 0.95 and 0.93 g/kg in calibration sets, 0.86 and 1.44 g/kg in validation sets, RPD: 2.62) and FDR-CARS-SVR (R2 and RMSE: 0.99 and 0.45 g/kg in calibration sets, 0.83 and 1.58 g/kg in validation sets, RPD: 2.38). The results suggested that the CARS algorithm combined CR and FDR can significantly improve the modeling accuracy of SOM content.

show abstract

Section: Plsr Modeling Based On Characteristic Wavelengthssupporting

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Hyperspectral Modeling of Soil Organic Matter Based on Characteristic Wavelength in East China

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In this study, we employed the RF model to select the best bands to construct spectral indices, which can reduce the highly redundant spectral data. Our results showed that the SOM spectrum was especially sensitive throughout the visible, near-infrared, and shortwave infrared regions (400 to 2500 nm), with unique spectral response bands that are consistent with previous studies [61,62]. Among them, the spectral data were dominated by the darkness of soil chromophores and humic acids [19,58].…”

Section: Discussionsupporting

confidence: 90%

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

Wang

Yong

2022

Agriculture

View full text Add to dashboard Cite

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 R2val (coefficient of determination of the validation data set) = 0.67, RMSEval (root mean square error of the validation dataset) = 2.05, and RPIQval(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−1 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.

show abstract

“…PLSR compresses the input data matrix by choosing consecutive orthogonal elements to maximize the covariance between Y (water body parameters) and X (spectral bands) (Zhu et al, 2022). It successfully addresses the issue of multicollinearity between spectral data and maintains accurate predictions even with few samples (Xie et al, 2022).…”

Section: Plsr Modelmentioning

confidence: 99%

Mineral content estimation for salt lakes on the Tibetan plateau based on the genetic algorithm-based feature selection method using Sentinel-2 imagery: A case study of the Bieruoze Co and Guopu Co lakes

et al. 2023

View full text Add to dashboard Cite

Salt lakes on the Tibetan Plateau (TP) are rich in lithium (Li), boron (B) and other mineral resources, and accurate assessment of the mineral content and spatial distribution of the brine in those salt lakes is important to guide the development and utilization of their mineral resources. There are few studies estimating the mineral content of salt lakes on the TP due to the lack of in situ investigation data. This study introduced an intelligent prediction model combining a feature selection algorithm with a machine learning algorithm using Sentinel-2 satellite data to estimate the Li, B, and TDS contents of Bieruoze Co and Guopu Co lakes on the TP. First, to enrich the spectral information, four mathematical transformations (reciprocal, logarithmic, reciprocal of logarithm, and first-order derivative) were applied to the original bands. Then, feature selection was performed using the genetic algorithm (GA) to select the optimal input variables for the model. Finally, prediction models were constructed by partial least squares regression (PLSR), multiple linear regression (MLR), and random forest (RF). The results showed that: 1) The spectral mathematical transformation provided rich spectral information for the mineral content estimation. 2) The performance of the estimation model constructed by the feature optimization method using GA was better than that of the estimation model constructed based on all spectral bands. Based on GA for feature optimization, the MAPE of GA-RF for estimating Li, B and TDS contents on the testing set was reduced by 77.52%, 28.54% and 36.79%, respectively. 3) Compared with the GA-MLR and GA-PLSR models, GA-RF estimated Li (R2=0.99, RMSE=1.15 mg L-1, MAPE=3.00%), B (R2=0.97, RMSE=10.65 mg L-1, MAPE=2.73%), and TDS (R2=0.93, RMSE=0.60 g L-1, MAPE=1.82%) all obtained the optimal performance. This study showed that the combination of the GA-based feature selection method and the RF model has excellent performance and applicability for monitoring the content of multiple minerals using Sentinel-2 imagery in salt lakes on the TP.

show abstract

Prediction of soil organic matter content based on characteristic band selection method

Cited by 32 publications

References 57 publications

Hyperspectral Modeling of Soil Organic Matter Based on Characteristic Wavelength in East China

Hyperspectral Modeling of Soil Organic Matter Based on Characteristic Wavelength in East China

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

Mineral content estimation for salt lakes on the Tibetan plateau based on the genetic algorithm-based feature selection method using Sentinel-2 imagery: A case study of the Bieruoze Co and Guopu Co lakes

Contact Info

Product

Resources

About