Abstract In recent years, several sediment fingerprinting studies have used ultraviolet–visible (UV–Vis), near-infrared (NIR) and middle-infrared (MIR) spectroscopy as a low cost, non-destructive and fast alternative to obtain tracer properties to estimate sediment source contributions. For this purpose, partial last square regression (PLSR) has often been used to build predictive parametric models. However, spectra preprocessing and more robust and non-parametric models such as support vector machines (SVM) has gained little attention in these studies. Accordingly, the objectives of the current research were to evaluate (i) the accuracy of two multivariate methods (PLSR and SVM), (ii) the effect of eight spectra preprocessing techniques, and (iii) the effect of using the information contained in the UV–Vis, NIR and MIR regions considered either separately or in combination on sediment source apportionment. The estimated source contribution was then compared with contributions obtained by the conventional fingerprinting approach based on geochemical tracers. This study was carried out in the Arvorezinha catchment (1.23 km2) located in southern Brazil. Forty soil samples were collected in three main potential source (cropland surface, unpaved roads and stream channels) and twenty-nine suspended sediment samples collected at the catchment outlet during nine rainfall-runoff events were used in this study. Both PLSR and SVM models showed a higher accuracy when calibrated and validated with the spectra submitted to spectral processing when compared to the direct use of the raw spectra. The best model results were obtained with PLSR and SVM mathematical models associated with the spectral preprocessing techniques 1st derivative Savitzky-Golay (SGD1), normalization (NOR) and combining NOR + SGD1 in the UV–Vis + NIR + MIR. The lowest errors were observed when the UV–Vis + NIR + MIR bands were combined due to the gain in information and, consequently, the increase in discriminant power achieved by the models. Despite the good accuracy of the models calibrated and validated with the artificial mixtures, significant errors remain when results of source contributions are compared to those obtained with the conventional sediment fingerprinting technique based on geochemical tracers. Nevertheless, the magnitude of the contributions calculated by the spectroscopy and geochemical approaches remains very similar for all sources, especially when using the SVM-UV–Vis + NIR + MIR model. Therefore, spectroscopy proved to be a fast, cheap and accurate technique, offering an alternative to the conventional geochemical approach for discriminating sediment source contributions in agricultural catchments located in subtropical regions.

中文翻译：

---

使用不同的数学模型和光谱预处理技术对紫外-可见光、近红外和中红外光谱的单独或组合光谱改进沉积物来源贡献的量化

摘要 近年来，一些沉积物指纹图谱研究使用紫外-可见光 (UV-Vis)、近红外 (NIR) 和中红外 (MIR) 光谱作为一种低成本、非破坏性和快速的替代方法来获得示踪特性，估计沉积物来源的贡献。为此，通常使用偏最后二乘回归 (PLSR) 来构建预测参数模型。然而，光谱预处理和更稳健的非参数模型，如支持向量机 (SVM) 在这些研究中很少受到关注。因此，当前研究的目标是评估 (i) 两种多元方法（PLSR 和 SVM）的准确性，(ii) 八种光谱预处理技术的效果，以及 (iii) 使用包含在紫外-可见，NIR 和 MIR 区域在沉积物来源分配中单独或组合考虑。然后将估计的源贡献与通过基于地球化学示踪剂的传统指纹识别方法获得的贡献进行比较。本研究在位于巴西南部的 Arvorezinha 流域（1.23 平方公里）进行。在三个主要潜在来源（农田表面、未铺砌的道路和河道）收集了 40 个土壤样品，本研究使用了在九次降雨径流事件期间在集水区出口收集的 29 个悬浮沉积物样品。与直接使用原始光谱相比，PLSR 和 SVM 模型在使用提交光谱处理的光谱进行校准和验证时都显示出更高的精度。最好的模型结果是使用与光谱预处理技术 1 阶导数 Savitzky-Golay (SGD1)、归一化 (NOR) 和在 UV-Vis + NIR + MIR 中结合 NOR + SGD1 相关的 PLSR 和 SVM 数学模型获得的。当 UV-Vis + NIR + MIR 波段组合时，由于信息的增益以及模型实现的判别能力的增加，观察到的误差最低。尽管使用人工混合物校准和验证的模型具有良好的准确性，但将源贡献的结果与基于地球化学示踪剂的传统沉积物指纹技术获得的结果进行比较时，仍然存在重大误差。然而，对于所有来源，光谱学和地球化学方法计算出的贡献量级仍然非常相似，特别是在使用 SVM-UV-Vis + NIR + MIR 模型时。因此，光谱学被证明是一种快速、廉价和准确的技术，为区分位于亚热带地区的农业集水区的沉积物来源贡献提供了一种替代传统地球化学方法的方法。