Department of Soil Science and Soil Protection, Faculty of Agrobiology, Food and NaturalResources, Czech University of Life Sciences Prague, 16500 Prague, Czech Republic.
Department of Geosciences, Chair of Soil Science and Geomorphology, University Of Tübingen, Rümelinstr. 19-23, Tübingen, Germany; DFG Cluster of Excellence "Machine Learning", University of Tübingen, AI Research Building, Maria-von-Linden-Str. 6, 72076, Tübingen, Germany.
J Environ Manage. 2023 Jan 15;326(Pt A):116701. doi: 10.1016/j.jenvman.2022.116701. Epub 2022 Nov 14.
Zinc (Zn) is a vital element required by all living creatures for optimal health and ecosystem functioning. Therefore, several researchers have modeled and mapped its occurrence and distribution in soils. Nonetheless, leveraging model predictive performances while coupling information derived from visible near-infrared (Vis-NIR) and soils (i.e. chemical properties) to estimate potential toxic elements (PTEs) like Zn in agricultural soils is largely untapped. This study applies two methods to rapidly monitor Zn concentration in agricultural soil. Firstly, employing Vis-NIR and machine learning algorithms (MLAs) (Context 1) and secondly, applying Vis-NIR, soil chemical properties (SCP), and MLAs (Context 2). For the Vis-NIR information, single and combined pretreatment methods were applied. The following MLAs were used: conditional inference forest (CIF), partial least squares regression (PLSR), M5 tree model (M5), extreme gradient boosting (EGB), and support vector machine regression (SVMR) respectively. For context 1, the results indicated that M5-MSC (M5 tree model-multiplicative scatter correction) with coefficient of determination (R) = 0.72, root mean square error (RMSE) = 21.08 (mg/kg), median absolute error (MdAE) = 13.69 and ratio of performance to interquartile range (RPIQ) = 1.63 was promising. Regarding context 2, CIF with spectral pretreatment and soil properties [CIF-DWTLOGMSC + SCP (conditional inference forest-discrete wavelet transformation-logarithmic transformation-multiplicative scatter correction-soil chemical properties)] yielded the best performance of R = 0.86, RMSE = 14.52 (mg/kg), MdAE = 6.25 and RPIQ = 1.78. Altogether, for contexts 1 and 2, the CIF-DWTLOGMSC + SCP approach (context 2) was the best Zn model outcome for the agricultural soil. The uncertainty map revealed a low to high error distribution in context 1, and a low to moderate distribution in context 2 for all models except CIF, which had some patches with high uncertainty. We conclude that a multiple optimization approach for modeling Zn levels in agricultural soils is invaluable and may provide fast and reliable information needed for area-specific decision-making.
锌（Zn）是所有生物维持最佳健康和生态系统功能所必需的重要元素。因此，许多研究人员已经对其在土壤中的存在和分布进行了建模和绘图。然而，利用模型预测性能，同时结合来自可见近红外（Vis-NIR）和土壤（即化学性质）的信息来估计农业土壤中的潜在有毒元素（PTE），如锌，在很大程度上尚未开发。本研究应用两种方法快速监测农业土壤中的锌浓度。首先，采用 Vis-NIR 和机器学习算法（MLAs）（上下文 1），其次，采用 Vis-NIR、土壤化学性质（SCP）和 MLAs（上下文 2）。对于 Vis-NIR 信息，应用了单一和组合预处理方法。分别使用了以下 MLAs：条件推断森林（CIF）、偏最小二乘回归（PLSR）、M5 树模型（M5）、极端梯度提升（EGB）和支持向量机回归（SVMR）。对于上下文 1，结果表明，具有决定系数（R）=0.72、均方根误差（RMSE）=21.08（mg/kg）、中值绝对误差（MdAE）=13.69 和性能与四分位距比（RPIQ）=1.63 的 M5-MSC（M5 树模型-乘法散射校正）很有前途。对于上下文 2，具有光谱预处理和土壤特性的 CIF [CIF-DWTLOGMSC+SCP（条件推断森林-离散小波变换-对数变换-乘法散射校正-土壤化学特性）] 产生了最佳性能，R=0.86、RMSE=14.52（mg/kg）、MdAE=6.25 和 RPIQ=1.78。总的来说，对于上下文 1 和 2，CIF-DWTLOGMSC+SCP 方法（上下文 2）是农业土壤中 Zn 最佳模型结果。不确定性图显示，在上下文 1 中，除了 CIF 之外，所有模型的误差分布从低到高，而在上下文 2 中，误差分布从低到中，CIF 有一些具有高不确定性的斑块。我们得出的结论是，对农业土壤中 Zn 水平进行建模的多种优化方法是无价的，并且可以为特定区域的决策提供快速可靠的信息。
Zotero 插件