School of Geophysics and Geomatics, China University of Geosciences, Wuhan, 430074, China.
Henan Science and Technology Innovation Center of Natural Resources (Application Research of Information Perception Technology), Xinyang, 464000, Henan, China.
Environ Geochem Health. 2023 Dec;45(12):9103-9121. doi: 10.1007/s10653-023-01488-w. Epub 2023 Mar 4.
Soil contamination with heavy metals is a relatively serious issue in China. Traditional soil heavy metal survey methods cannot meet the demand for rapid and real-time large-scale area soil heavy metal surveys. We chose a typical mining area in Henan Province as the study area, collected 124 soil samples in the field and obtained their soil hyperspectral data indoors using a spectrometer. After different spectral transformations of the soil spectral curves, Pearson correlation coefficients (PCC) between them and the heavy metals Cd, Cr, Cu, and Ni were calculated, and after correlation evaluation, the best spectral transformations for each heavy metal were determined and preselected characteristic wavebands were obtained. Then the support vector machine recursive feature elimination cross-validation (SVM-RFECV) is used to select among the preselected feature wavebands to obtain the final modeled wavebands, and the Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), and Partial Least Squares (PLS) methods were used to establish the inversion model. The results showed that the PCC-SVM-RFECV can effectively select characteristic wavebands with high contribution to modeling from high-dimensional data. Spectral transformations methods can improve the correlation of spectra with heavy metals. The location and quantity of characteristic wavebands for the four heavy metals were different. The accuracy of AdaBoost was significantly better than that of GBDT, RF, and PLS (i.e., Ni: [Formula: see text]). This study can provide a technical reference for the use of hyperspectral inversion models for large-scale monitoring of soil heavy metal content.
土壤重金属污染在中国是一个较为严重的问题。传统的土壤重金属调查方法无法满足快速、实时的大面积土壤重金属调查的需求。我们选择了河南省的一个典型矿区作为研究区，在现场采集了 124 个土壤样本，并在室内使用光谱仪获得了它们的土壤高光谱数据。对土壤光谱曲线进行不同的光谱变换后，计算它们与重金属 Cd、Cr、Cu 和 Ni 之间的皮尔逊相关系数（PCC），并在相关评价后，确定了每种重金属的最佳光谱变换，得到了预选的特征波段。然后，使用支持向量机递归特征消除交叉验证（SVM-RFECV）在预选特征波段中进行选择，得到最终的建模波段，并使用自适应提升（AdaBoost）、梯度提升决策树（GBDT）、随机森林（RF）和偏最小二乘（PLS）方法建立反演模型。结果表明，PCC-SVM-RFECV 可以有效地从高维数据中选择对建模有高贡献的特征波段。光谱变换方法可以提高光谱与重金属的相关性。四种重金属特征波段的位置和数量不同。AdaBoost 的精度明显优于 GBDT、RF 和 PLS（即 Ni：[公式：见正文]）。本研究可为利用高光谱反演模型进行大面积土壤重金属含量监测提供技术参考。
