Environmental Systems Engineering, University of Regina, Regina, SK, S4S 0A2, Canada.
Environ Sci Pollut Res Int. 2019 Jan;26(2):1821-1833. doi: 10.1007/s11356-018-3751-y. Epub 2018 Nov 19.
TDS is modeled for an aquifer near an unlined landfill in Canada. Canadian Drinking Water Guidelines and other indices are used to evaluate TDS concentrations in 27 monitoring wells surrounding the landfill. This study aims to predict TDS concentrations using three different modeling approaches: dual-step multiple linear regression (MLR), hybrid principal component regression (PCR), and backpropagation neural networks (BPNN). An analysis of the bias and precision of each models follows, using performance evaluation metrics and statistical indices. TDS is one of the most important parameters in assessing suitability of water for irrigation, and for overall groundwater quality assessment. Good agreement was observed between the MLR1 model and field data, although multicollinearity issues exist. Percentage errors of hybrid PCR were comparable to the dual-step MLR method. Percentage error for hybrid PCR was found to be inversely proportional to TDS concentrations, which was not observed for dual-step MLR. Larger errors were obtained from the BPNN models, and higher percentage errors were observed in monitoring wells with lower TDS concentrations. All models in this study adequately describe the data in testing stage (R > 0.86). Generally, the dual-step MLR and hybrid PCR models fared better (R = 0.981 and 0.974, respectively), while BPNN models performed worse (R = 0.904). For this dataset, both regression and machine learning models are more suited to predict mid-range data compared to extreme values. Advanced regression methods (hybrid PCR and dual-step MLR) are more advantageous compared to BPNN.
在加拿大，对一个靠近无衬砌垃圾填埋场的含水层进行了总溶解固体（TDS）建模。使用加拿大饮用水准则和其他指标来评估围绕垃圾填埋场的 27 口监测井中的 TDS 浓度。本研究旨在使用三种不同的建模方法来预测 TDS 浓度：两步多重线性回归（MLR）、混合主成分回归（PCR）和反向传播神经网络（BPNN）。然后使用性能评估指标和统计指数对每个模型的偏差和精度进行分析。TDS 是评估水用于灌溉的适宜性以及地下水总体质量评估的最重要参数之一。MLR1 模型与现场数据吻合良好，尽管存在多重共线性问题。混合 PCR 的百分比误差与两步 MLR 方法相当。混合 PCR 的百分比误差与 TDS 浓度呈反比，而两步 MLR 则没有观察到这种情况。BPNN 模型得到的误差较大，TDS 浓度较低的监测井的百分比误差较高。本研究中的所有模型在测试阶段都能很好地描述数据（R>0.86）。一般来说，两步 MLR 和混合 PCR 模型的表现更好（R 分别为 0.981 和 0.974），而 BPNN 模型的表现更差（R 为 0.904）。对于该数据集，与极端值相比，回归和机器学习模型更适合预测中范围数据。与 BPNN 相比，高级回归方法（混合 PCR 和两步 MLR）更具优势。
