Estimating Pb concentration of soil in the mining tailing areas base on field spectroscopy and random forests

Heavy metal pollutions of soil is one of the serious problems in the mining tailing areas, therefore, it is significant to estimate heavy metal of soil in the mining tailing areas. This research take Jinduicheng Mo mining tailings, Huaxian, Shaanxi Province as the study area. A total number of 288 soil samples collected at the mining tailing areas. And the heavy metal concentrations of Pb in soil were determined through chemistry analysis in the laboratory. The original reflectance spectral measurements of soil were collected using an ASD field spectrometer for the solar reflective wavelengths (350-2500 nm) in the field. The hyperspectral prediction model of Pb concentration in soils yielded a correlation coefficient of 0.7703 and Root Mean Square Error of the prediction (RMSE) value of 249.9720. The research results provide theoretical basis for the exploration of soil heavy metal content estimation, and have important practical significance for the monitoring of heavy metal pollution in the mining tailing areas.