Estimation of Soil Heavy Metal Content Using Hyperspectral Data

Liu, Zhenhua; Lü, Ying; Peng, Yuanyuan; Zhao, Li; Wang, Guangxing; Hu, Yueming

doi:10.3390/rs11121464

Cited by 54 publications

(38 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the goodness-of-fit of soil heavy metal inversion obtained using hyperspectral remote sensing of approximately 0.8 [7,13,18,45], the goodness-of-fit in this experiment was relatively low. The main reason is that the hyperspectral remote sensing image contained higher spectral resolution than the multi-band spectral resolution.…”

Section: Discussioncontrasting

confidence: 63%

“…However, owing to the low spatial resolution of hyperspectral images, the majority are mixed pixels. Although more accurate statistical results can be obtained, it is difficult to study and analyze the regional spatial content [45]; thus, most previous experiments have focused on exploring the feasibility of each regression method and improving the accuracy of the statistical model. However, it is not possible to carry out a more detailed spatial analysis according to specific actual needs, which has many practical application limitations.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation and Spatial Analysis of Heavy Metals in Metal Tailing Pond Based on Improved PLS With Multiple Factors

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

With the exploitation of mineral resources, pollution of the ecological environment in mines has garnered public attention. Particularly,erosion of the surrounding ecological environment re-sulting from heavy metals in tailings pond could be highly concerning. Instead of traditional field sampling and laboratory analysis method, remote sensing can be used to high-precisi es-timation soil heavy metal with less time and effort. soil heavy metal content is generally low, the spectral sensitivities of various heavy metals are insignificant, and the surface landscape is complex, there exist difficulties associated with heavy metal content estimation. Therefore, herein, we propose optimization of the commonly used partial least-square regression (PLS) method. In the optimized method, a variety of remote sensing indices and the modeled heavy metals were added as modeling factors to indirect estimation soil heavy metal. The method was validated via inversion experiments of heavy metals (Ni, Cu, and Zn) in the tailing pond and its surrounding environment,it improve the goodness-of-fit of Ni, Cu, and Zn by 0.0852,0.2291, and 0.2919 compared with traditional PLS. Spatia l analysis was then conducted on the entire studied area using the estimation model of the three heavy metals. It was shown that the results were essentially consistent with the actual heavy metal distribution in the area. Therefore, the indirect PLS model with multiple factors proves effective for the estimation of soil heavy metals. It also provides technical support for treatment and evaluation of ecological environments in mining areas.INDEX TERMS Multi-spectral remote sensing image, heavy metals in soil, partial least-squares regression, fusion of multiple factors, spatial evolution analysis, GF-2.

show abstract

Section: Discussioncontrasting

confidence: 63%

Section: Discussionmentioning

confidence: 99%

Estimation and Spatial Analysis of Heavy Metals in Metal Tailing Pond Based on Improved PLS With Multiple Factors

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…R ni is the ith growth stage of the nth CLQ sample, R i is the average of the CLQ sample values in the ith growth stage, and y is the nth CLQ, y is the average value of CLQ. Moreover, the Variance Inflation Factor (VIF) was applied to mitigate the collinearity among the GPP predictors, which is calculated as [37,38]:…”

Section: Selecting the Phases Of Gppmentioning

confidence: 99%

Crop Growth Stage GPP-Driven Spectral Model for Evaluation of Cultivated Land Quality Using GA-BPNN

et al. 2020

Self Cite

View full text Add to dashboard Cite

Rapid and accurate evaluation of cultivated land quality (CLQ) using remotely sensed images plays an important role for national food security and social stability. Current approaches for evaluating CLQ do not consider spectral response relationships between CLQ and spectral indicators based on crop growth stages. This study aimed to propose an accurate spectral model to evaluate CLQ based on late rice phenology. In order to increase the accuracy of evaluation, the Empirical Bayes Kriging (EBK) interpolation was first performed to scale down gross primary production (GPP) products from a 500 m spatial resolution to 30 m. As an indicator, the ability of MODIS-GPPs from critical growth stages (tillering, jointing, heading, and maturity stages) was then investigated by combining Pearson correlation analysis and variance inflation factor (VIF) to select the phases of CLQ evaluation. Finally, a linear Partial Least Squares Regression (PLSR) and two nonlinear models, including Support Vector Regression (SVR) and Genetic Algorithm-Based Back Propagation Neural Network (GA-BPNN), were driven to develop an accurate spectral model of evaluating CLQ based on MODIS-GPPs. The models were tested and compared in the Conghua and Zengcheng districts of Guangzhou City, Guangdong, China. The results showed that based on field measured GPP data, the validation accuracy of 30 m spatial resolution MODIS GPP products with a root mean square error (RMSE) of 7.43 and normalized RMSE (NRMSE) of 1.59% was higher than that of the 500 m MODIS GPP products, indicating that the downscaled 30 m MODIS GPP products by EBK were more appropriate than the 500 m products. Compared with PLSR (R2 = 0.38 and RMSE = 87.97) and SVR (R2 = 0.64 and RMSE = 64.38), the GA-BPNN model (R2 = 0.69 and RMSE = 60.12) was more accurate to evaluate CLQ, implying a non-linear relationship of CLQ with the GPP spectral indicator. This is the first study to improve the accuracy of estimating CLQ using the rice growth stage GPP-driven spectral model by GA-BPNN and can thus advance the literature in this field.

show abstract

“…This leads to 20 combinations of the vegetation indices and empirical models at each of five growth stages. As standard statistical metrics to measure model performance, RMSE and ratio of performance to deviation (RPD) are used to select the most relevant image-derived vegetation index [45]. RMSE=∑i=1n(yi−trueyi^)2n RPD=STDRMSE where yi is the measured value of the ith sample; trueyi^ is the estimated value of the ith sample; n is the number of samples, STD is the standard deviation of the measured CLQ.…”

Section: Methodsmentioning

confidence: 99%

The Optimal Image Date Selection for Evaluating Cultivated Land Quality Based on Gaofen-1 Images

Xia

Peng

Liu

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

This study proposes a method for determining the optimal image date to improve the evaluation of cultivated land quality (CLQ). Five vegetation indices: leaf area index (LAI), difference vegetation index (DVI), enhanced vegetation index (EVI), normalized difference vegetation index (NDVI), and ratio vegetation index (RVI) are first retrieved using the PROSAIL model and Gaofen-1 (GF-1) images. The indices are then introduced into four regression models at different growth stages for assessing CLQ. The optimal image date of CLQ evaluation is finally determined according to the root mean square error (RMSE). This method is tested and validated in a rice growth area of Southern China based on 115 sample plots and five GF-1 images acquired at the tillering, jointing, booting, heading to flowering, and milk ripe and maturity stage of rice in 2015, respectively. The results show that the RMSEs between the measured and estimated CLQ from four vegetation index-based regression models at the heading to flowering stage are smaller than those at the other growth stages, indicating that the image date corresponding with the heading to flowering stage is optimal for CLQ evaluation. Compared with other vegetation index-based models, the LAI-based logarithm model provides the most accurate estimates of CLQ. The optimal model is also driven using the GF-1 image at the heading to flowering stage to map CLQ of the study area, leading to a relative RMSE of 14.09% at the regional scale. This further implies that the heading to flowering stage is the optimal image time for evaluating CLQ. This study is the first effort to provide an applicable method of selecting the optimal image date to improve the estimation of CLQ and thus advanced the literature in this field.

show abstract

Estimation of Soil Heavy Metal Content Using Hyperspectral Data

Cited by 54 publications

References 45 publications

Estimation and Spatial Analysis of Heavy Metals in Metal Tailing Pond Based on Improved PLS With Multiple Factors

Estimation and Spatial Analysis of Heavy Metals in Metal Tailing Pond Based on Improved PLS With Multiple Factors

Crop Growth Stage GPP-Driven Spectral Model for Evaluation of Cultivated Land Quality Using GA-BPNN

The Optimal Image Date Selection for Evaluating Cultivated Land Quality Based on Gaofen-1 Images

Contact Info

Product

Resources

About