Abstract
Heavy metals contaminations in mining areas aroused wide concerns globally. Efficient evaluation of its pollution status is a basis for further soil reclamation. Visible and near–infrared reflectance (Vis–NIR) spectroscopy has been diffusely used for retrieving heavy metals concentrations. However, the reliability and feasibility of calibrated models were still doubtful. The present study estimated zinc (Zn) concentrations via the random forest (RF) and partial least squares regression (PLSR) using ground in-situ Zn concentrations as well as soil spectral reflectance at an Opencast Coal Mine of Ordos, China in February 2020. The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and the ratio of performance to deviation (RPD) were selected to assess the robustness of the methods in estimating Zn contents. Moreover, the characteristic bands were chosen by Pearson correlation analysis and Boruta Algorithm. Finally, the comparison between RF and PLSR combined with eight spectral reflectance transformation methods was conducted for four concentration groups to determine the optimal model. The results indicated that: (1) Zn contents represented a skewed distribution (coefficient of variation (CV) = 33%); (2) the spectral reflectance tended to decrease with the increase of Zn contents during 580–1850 nm based on Savitzky–Golay smoothing (SG); (3) the continuous wavelet transform (CWT) demonstrated higher effectiveness than other spectral reflectance transformation methods in enhancing spectral responses, the R2 between Zn contents and the soil spectral reflectance achieved the highest (R2 = 0.71) by using CWT; (4) the RF combined with CWT exhibited the best performance than other methods in the current study (R2 = 0.97, RPD = 3.39, RMSE = 1.05 mg kg−1, MAE = 0.79 mg kg−1). The current study supplied a scientific scheme and theoretical support for predicting heavy metals concentrations via the Vis–NIR spectral method in possible contaminated areas such as coal mines and metallic mineral deposit areas.
Highlights
China is the world’s largest coal producer and consumer, and coal provides more than 70 percent of total energy in China[1]
The objectives of this study are to (1) measure Zn concentrations, and survey in-situ reflectance spectra, lab-based processed reflectance spectra, and lab-based unprocessed reflectance spectra of soil samples from an Opencast Coal Mine of Ordos, China; (2) select optimal characteristic bands based on Pearson correlation coefficient as well as the Boruta algorithm; (3) calibrate Zn concentrations using statistical analysis and random forest based on Zn contents and spectral reflectance data; (4) evaluate the performance of related models including partial least squares regression (PLSR) and RF combined with different spectral reflectance transformation methods, determining the optimal prediction method for Zn contents
The present study revealed that Vis–NIR spectroscopy can be used to calibrate Zn concentration in topsoils of open cast coal mining areas
Summary
China is the world’s largest coal producer and consumer, and coal provides more than 70 percent of total energy in China[1]. The necessity of the current study was to evaluate the feasibility and reliability of using the Vis–NIR spectroscopy in estimating heavy metals contents at an open-pit coal mine, to compare the effect of various spectral transformation methods on the accuracy of the estimation models, and to determine if the concentrations of soil samples generate effects on the accuracy in retrieving heavy metals contents or not. The objectives of this study are to (1) measure Zn concentrations, and survey in-situ reflectance spectra, lab-based processed reflectance spectra, and lab-based unprocessed reflectance spectra of soil samples from an Opencast Coal Mine of Ordos, China; (2) select optimal characteristic bands based on Pearson correlation coefficient as well as the Boruta algorithm; (3) calibrate Zn concentrations using statistical analysis and random forest based on Zn contents and spectral reflectance data; (4) evaluate the performance of related models including PLSR and RF combined with different spectral reflectance transformation methods, determining the optimal prediction method for Zn contents
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
