Retrieving zinc concentrations in topsoil with reflectance spectroscopy at Opencast Coal Mine sites

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 (R-2), 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 R-2 between Zn contents and the soil spectral reflectance achieved the highest (R-2 = 0.71) by using CWT; (4) the RF combined with CWT exhibited the best performance than other methods in the current study (R-2 = 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.

Automated summary

This study evaluated zinc concentrations in soil using random forest and partial least squares regression models based on ground data and soil spectral reflectance. The results showed that the random forest model combined with continuous wavelet transform was the most effective in predicting zinc concentrations in contaminated areas like coal mines and metallic mineral deposits, providing valuable insight for environmental monitoring and reclamation efforts.