Reflectance spectroscopy in the visible-infrared and shortwave infrared (450–2500 nm) wavelength region is a rapid, cost-effective and non-destructive method that can be used to monitor heavy metal (PTE, potential toxic elements) contaminated areas. Due to the PTE pollution that has accumulated in the course of wastewater treatment, the existence of Technosols presents an environmental problem, a potential source for PTE uptake by vegetation, or even the release of PTEs into groundwater. In this study, multivariate procedures using Partial Least Squares Regression (PLSR) and Random Forest Regression (RFR) are applied to quantify relationships between soil heavy metal concentration (Cr, Cu, Ni, Zn) and reflectance data of highly contaminated Technosols from a former sewage farm near Berlin, Germany. Laboratory measurements of 110 soil samples in four different preparation steps were acquired with HySpex hyperspectral cameras. The impact of the different preparation steps, namely “oven-dried”, “sieved”, “ground”, “LOI”, was evaluated for its potential to enhance the method performance or to reduce the time-consuming soil sample preparation. Furthermore, different spectral pre-processing methods were evaluated regarding improvements of spectral modelling performance and their ability to minimise noise and multiple scattering effects. Considering the optimal coefficient of determination (R²), PLSR shows an improving performance and accuracy with increasing preparation steps such as ground or LOI for all metals of interest (R²_Cr: 0.52–0.78; R²_Cu: 0.36–0.73; R²_Ni: 0.19–0.42 and R²_Zn: 0.41–0.74). RFR shows a weaker estimation performance for all metals, even when using higher sample preparation levels (R²_Cr: 0.36–0.62; R²_Cu: 0.17–0.72; R²_Ni: 0.20–0.35 and R²_Zn: 0.26–0.67). The results show that an application of methods such as PLSR for the prediction of PTE concentration in Technosols is still a challenge but provides more robust estimations than the user-friendly RFR method. Additionally, this study shows that PTE estimation performance in heterogeneous soil samples can be improved by increased laboratory soil preparation steps and further spectral pre-processing steps.

可见红外和短波红外（450-2500 nm）波长区域的反射光谱是一种快速、经济且无损的方法，可用于监测重金属（PTE，潜在有毒元素）污染区域。由于在废水处理过程中积累了 PTE 污染，Technosols 的存在带来了环境问题，是植被吸收 PTE 的潜在来源，甚至是 PTE 释放到地下水中。在这项研究中，使用偏最小二乘回归 (PLSR) 和随机森林回归 (RFR) 的多变量程序被应用于量化土壤重金属浓度（Cr、Cu、Ni、Zn）与来自前一个高污染 Technosols 的反射数据之间的关系。德国柏林附近的污水处理厂。使用 HySpex 高光谱相机在四个不同的制备步骤中对 110 个土壤样品进行了实验室测量。评估了不同制备步骤的影响，即“烘箱干燥”、“筛分”、“研磨”、“LOI”，以评估其提高方法性能或减少耗时的土壤样品制备的潜力。此外，还评估了不同光谱预处理方法对光谱建模性能的改进及其将噪声和多重散射效应降至最低的能力。考虑最佳决定系数 (R 评估了其提高方法性能或减少耗时的土壤样品制备的潜力。此外，还评估了不同光谱预处理方法对光谱建模性能的改进及其将噪声和多重散射效应降至最低的能力。考虑最佳决定系数 (R 评估了其提高方法性能或减少耗时的土壤样品制备的潜力。此外，还评估了不同光谱预处理方法对光谱建模性能的改进及其将噪声和多重散射效应降至最低的能力。考虑最佳决定系数 (R² )，PLSR 表现出提高的性能和准确性，随着准备步骤的增加，例如所有感兴趣的金属的研磨或 LOI (R ² _Cr: 0.52–0.78; R ² _Cu: 0.36–0.73; R ² _Ni: 0.19–0.42 和 R ² _Zn：0.41–0.74)。即使使用更高的样品制备水平（R ² _Cr：0.36-0.62；R ² _Cu：0.17-0.72；R ² _Ni：0.20-0.35 和 R ²_Zn：0.26–0.67）。结果表明，应用 PLSR 等方法来预测 Technosols 中的 PTE 浓度仍然是一个挑战，但提供了比用户友好的 RFR 方法更可靠的估计。此外，这项研究表明，通过增加实验室土壤准备步骤和进一步的光谱预处理步骤，可以提高异质土壤样品的 PTE 估计性能。