Estimation of Soil Salt Content and Organic Matter on Arable Land in the Yellow River Delta by Combining UAV Hyperspectral and Landsat-8 Multispectral Imagery

Sun, Minghan; Li, Qian; Jiang, Xuzi; Ye, Tiantian; Li, Xinju; Niu, Beibei

doi:10.3390/s22113990

Cited by 8 publications

(5 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cao et al [37] proposed a multiple linear regression (MLR)-based hyperspectral estimation model based on the gray correlation for overcoming the interference of abnormal soil samples on the constructing of linear regression models. Wang et al [38] and Sun et al [39] reported that MLR was the best multivariate technique to predict SOM content of soil. However, the above-mentioned research has regarded that there are differences in the optimum hyperspectral estimation models for different soil types and different regions, but the results of PLSR and MLR are preferable and more stable.…”

Section: Discussionmentioning

confidence: 99%

Hyperspectral Estimation Model of Organic Matter Content in Farmland Soil in the Arid Zone

Subi,

Eziz,

Zhong

2023

Sustainability

View full text Add to dashboard Cite

Soil organic matter (SOM) is one of the most important indicators of soil quality. Hyperspectral remote sensing technology has been recognized as an effective method to rapidly estimate SOM content. In this study, 173 samples (0–20 cm) were collected from farmland soils in the northwestern arid zones of China. Partial least squares regression (PLSR), support vector machine regression (SVMR), and random forests regression (RFR), based on 15 types of mathematical transformations of the original spectral data of soil, were applied for identifying the optimal estimation method. Distribution of SOM content was mapped using both ground-measured values and predicted values estimated based on the optimum models. Obtained results indicated that the important spectral wavebands with the highest correlation were identified as 421 nm, 441 nm, 1014 nm, 1045 nm, and 2351 nm for SOM in the soil. Spectral transformations had obvious effects on the spectral characteristics of SOM. The optimal estimation was obtained when RFR was combined with the reciprocal logarithmic first-order differential (RLFD) (R2 = 0.884, RMSE = 2.817%, MAE = 2.222) for SOM contents. Finally, the RFR-RLFD method had much better performance compared with the PLSR and SVMR models. Results of this study can provide an alternative to the application of the hyperspectral estimation of SOM in farmland soils in arid zones.

show abstract

Section: Discussionmentioning

confidence: 99%

Hyperspectral Estimation Model of Organic Matter Content in Farmland Soil in the Arid Zone

Subi,

Eziz,

Zhong

2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…Therefore, multitemporal satellite remote sensing images may be an important way to rapidly estimate the content of SOM over a large area, particularly where the land surface is temporarily or permanently exposed [12]. In recent years, scholars worldwide have made progress in the use of satellite remote sensing images to predict the SOM content [15,17]. However, many studies have used only spectral data from single-period images to predict SOM, which limits the accuracy of the estimation models [58].…”

Section: Discussionmentioning

confidence: 99%

“…In recent years, hyperspectral techniques that involve continuous high-resolution bands have been employed to estimate SOM [13,14]. Many previous studies have shown that hyperspectral imagery is superior to multispectral data for SOM estimation due to the rich spectral information that it provides [15,16]. However, surface-covered vegetation prevents a direct observation of bare soil features to obtain hyperspectral information.…”

Section: Introductionmentioning

confidence: 99%

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

“…Accurate estimation of soil composition is essential for soil testing, and hyperspectral can achieve rapid detection of soil composition, but there are many hyperspectral bands, and selection of effective spectral bands is the key to ensure the estimation accuracy. Usually, the selection of characteristic bands is performed by correlation analysis, but there are many material components in soil, and only by correlation analysis, it can cause duplication of information among hyperspectral bands, and for some substances that have a greater influence on spectral reflectance, such as water and organic matter (Ge, 2021;Sun et al, 2022), the inversion accuracy is higher because they are less influenced by other substances when estimation with characteristic bands, but for spectral substances with relatively small influence on the reflectance, such as copper, etc., some of the characteristic bands selected by using only Pearson correlation coefficients will overlap with those of substances such as iron, and the influence of iron on the spectral reflectance is greater than that of copper, resulting in lower accuracy in the direct estimation of copper content. In this study, the original feature band selection method and interaction were combined to select the feature band with the greatest influence of copper and the least influence of iron for the estimation, and the accuracy of the estimation of copper content was better improved.…”

Section: Discussionmentioning

confidence: 99%

Iron-copper interaction in soil spectra and its effect on the estimation of copper content

Zhao

Zhang

Yang

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

It is important to clarify the iron-copper interaction pattern to effectively extract the characteristic bands and improve the inversion accuracy of copper content in soil. In this study, based on experimental samples, spectral feature analysis and analysis of variance (ANOVA) were used to deeply uncover the iron-copper interaction pattern. And used natural samples to build a random forest model to analyze the effect of interaction patterns on inversion accuracy. The results of the study showed that the effect of iron content in soil on spectral reflectance varied with copper content in soil, and similarly, the effect of copper content in soil on spectral reflectance varied with iron content in soil. The effect of iron, copper and their interaction on the spectral reflectance of soil varied with the wavelength. In the wavelength from 400 to 2,500 nm, the effect of iron on the spectral features was more than copper, and in the characteristic wavelength of iron (600–700 nm), even more than 5 times that of copper, the effect of iron on the spectral reflectance played a major role, and the iron content in soil must be considered in the inversion of copper content in soil. The Pearson correlation coefficient method was used as the selected characteristic wavelength, the selected wavelength was used as the independent variable, and the copper content in the soil was the dependent variable. Inversion model was built by the random forest algorithm, and the determination coefficient was 0.73. Under the condition of considering the interaction, the coefficient of determination was 0.87. It was shown that the characteristic wavelength was selected by considering the iron-copper interaction, which can better characterize the response signal of copper in soil. This paper provided a new idea for the accurate inversion of copper content in soil, which can provide technical support for the rapid detection of copper content in soil.

show abstract

Estimation of Soil Salt Content and Organic Matter on Arable Land in the Yellow River Delta by Combining UAV Hyperspectral and Landsat-8 Multispectral Imagery

Cited by 8 publications

References 60 publications

Hyperspectral Estimation Model of Organic Matter Content in Farmland Soil in the Arid Zone

Hyperspectral Estimation Model of Organic Matter Content in Farmland Soil in the Arid Zone

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

Iron-copper interaction in soil spectra and its effect on the estimation of copper content

Contact Info

Product

Resources

About