Scientific and Technical Research Center on Arid Regions (CRSTRA), BP 1682 RP, 07000, Biskra, Algeria.
Faculty of Earth Sciences, Laboratory of Water Resource and Sustainable Development (REED), Badji Mokhtar University, BP 12, 23000, Annaba, Algeria.
Environ Sci Pollut Res Int. 2022 Jul;29(32):48491-48508. doi: 10.1007/s11356-022-18644-x. Epub 2022 Feb 22.
The water quality index is one of the prominent general indicators to assess and classify surface water quality, which plays a critical role in river water resources practices. This research constructs a hybrid artificial intelligence model namely sequential minimal optimization-support vector machine (SMO-SVM) along with random forest (RF) as a benchmark model for predicting water quality values at the Wadi Saf-Saf river basin in Algeria. The fifteen input water quality datasets such as biochemical oxygen demand (BOD), oxygen saturation (OS), the potential for hydrogen (pH), chemical oxygen demand (COD), chloride (Cl), dissolved oxygen (DO), electrical conductivity (EC), total dissolved solids (TDS), nitrate-nitrogen (NO-N), nitrite-nitrogen (NO-N), phosphate (PO), ammonium (NH), temperature (T), turbidity (NTU), and suspended solids (SS) were employed for constructing the predictive models. Different input data combinations are evaluated in terms of predictive performance, using a set of statistical metrics and graphical representation. Results show that less than 40% of samples were observed to be poor quality water during the dry season in downstream northeastern part of the basin. The findings also show that the RF model mostly generates more precise water quality index predictions than the SMO-SVM model for both training and testing stages. Although thirteen input parameters attain the optimal predictive performance (R testing = 0.82, RMSE testing = 5.17), a couple of five input parameters, e.g., only pH, EC, TDS, T, and saturation, gives the second optimal predictive precision (R test = 0.81, RMSE testing = 5.55). The sensitivity analysis results indicate a greater sensitivity by the all input variables chosen except NO of the predictive outcomes to the earlier influencing water quality parameters. Overall, the RF model reveals an improvement on earlier tools for predicting water quality index, according to predictive performance and reducing in the number of input variables.
水质指数是评估和分类地表水水质的突出综合指标之一，在河流水资源实践中起着关键作用。本研究构建了一个混合人工智能模型，即序贯最小优化-支持向量机（SMO-SVM）和随机森林（RF），作为预测阿尔及利亚瓦迪萨夫-萨夫河流域水质值的基准模型。十五个输入水质数据集，如生化需氧量（BOD）、氧饱和度（OS）、氢离子潜力（pH）、化学需氧量（COD）、氯（Cl）、溶解氧（DO）、电导率（EC）、总溶解固体（TDS）、硝酸盐氮（NO-N）、亚硝酸盐氮（NO-N）、磷酸盐（PO）、铵（NH）、温度（T）、浊度（NTU）和悬浮物（SS）被用于构建预测模型。使用一组统计指标和图形表示法，根据预测性能评估不同的输入数据组合。结果表明，在旱季，盆地东北部下游不到 40%的样本被观察为劣质水。研究结果还表明，在训练和测试阶段，RF 模型比 SMO-SVM 模型生成更精确的水质指数预测。尽管十三个输入参数达到了最佳的预测性能（R 测试=0.82，RMSE 测试=5.17），但几个五个输入参数，例如，只有 pH、EC、TDS、T 和饱和度，给出了第二个最佳的预测精度（R 测试=0.81，RMSE 测试=5.55）。敏感性分析结果表明，所有选择的输入变量（预测结果中除了 NO）对水质参数的早期影响都具有较高的敏感性。总的来说，根据预测性能和输入变量数量的减少，RF 模型显示出对预测水质指数的早期工具的改进。
