Monitoring of water quality through accurate predictions provides adequate information about water management. In the present study, three different modelling approaches: Gaussian process regression (GPR), backpropagation neural network (BPNN) and principal component regression (PCR) models were used to predict the total dissolved solids (TDS) as water quality indicator for the water quality management. The performance of each model was evaluated based on three different sets of inputs from groundwater (GW), surface water (SW) and drinking water (DW). The GPR, BPNN and PCR models used in this study gave an accurate prediction of the observed data (TDS) in GW, SW and DW, with the R² consistently greater than 0.850. The GPR model gave a better prediction of TDS concentration, with an average R², MAE and RMSE of 0.987, 4.090 and 7.910, respectively. For the BPNN, an average R², MAE and RMSE of 0.913, 9.720 and 19.137, respectively, were achieved, while the PCR gave an average R², MAE and RMSE of 0.888, 11.327 and 25.032, respectively. The performance of each model was assessed using efficiency based indicators such as the Nash and Sutcliffe coefficient of efficiency (E_NS) and the index of agreement (d). The GPR, BPNN and PCR models, respectively, gave an E_NS of (0.967, 0.915, 0.874) and d of (0.992, 0.977, 0.965). It is understood from this study that advanced machine learning approaches (e.g. GPR and BPNN) are appropriate for the prediction of water quality indices and would be useful for future prediction and management of water quality parameters of various water supply systems in mining communities where artificial intelligence technology is yet to be fully explored.

通过准确的预测监测水​​质可提供有关水管理的足够信息。在本研究中，使用三种不同的建模方法：高斯过程回归（GPR），反向传播神经网络（BPNN）和主成分回归（PCR）模型来预测总溶解固体（TDS）作为水质的水质指标管理。根据来自地下水（GW），地表水（SW）和饮用水（DW）的三组不同输入评估了每个模型的性能。本研究中使用的GPR，BPNN和PCR模型给出了GW，SW和DW中观测数据（TDS）的准确预测，R ²始终大于0.850。GPR模型可以更好地预测TDS浓度，平均R ²，MAE和RMSE分别为0.987、4.090和7.910。对于BPNN，获得的平均R ²，MAE和RMSE分别为0.913、9.720和19.137，而PCR给出的平均R ²，MAE和RMSE分别为0.888、11.327和25.032。使用基于效率的指标（例如Nash和Sutcliffe效率系数（E _NS）和一致性指数（d））评估每个模型的性能。GPR，BPNN和PCR模型分别给出了E _NS（0.967，0.915，0.874）的d和（0.992，0.977，0.965）的d。从这项研究中可以了解到，先进的机器学习方法（例如GPR和BPNN）适用于水质指数的预测，并且对于未来在人工智能中的采矿社区的各种供水系统的水质参数的预测和管理将是有用的技术尚待充分探索。