A significant problem in the sustainable management of water resources is the lack of funding and long-term monitoring. Today, this problem has been greatly reduced by innovative, adaptive, and sustainable learning methods. Therefore, in this study, a sample river was selected and 14 variables observed at 5 different points for 12 months, traditionally reference values, were calculated by multivariate statistical analysis methods to obtain the water quality index (WQI). The WQI index was estimated using different algorithms including the innovatively used multiple linear regression (MLR), multilayer perceptron artificial neural networks (MLP-ANN) and various machine learning estimation algorithms including neural networks (NN), support vector machine (SVM), gaussian process regression (GPR), ensemble and decision tree approach. By comparing the results, the most appropriate method was selected. The determination of water quality was best estimated by the multiple linear regression (MLR) model. As a result of this MLR modeling, high prediction performance was obtained with accuracy values of R ² = 1.0, RMSE = 0.0025, and MAPE = 0.0296. The root mean square error (RMSE), percent mean absolute error (MAE), and coefficient of determination (R ² ) were used to determine the accuracy of the models. These results confirm that both MLR model can be used to predict WQI with very high accuracy. It seems that it can contribute to strengthening water quality management. As a result, as with the powerful results of the innovative approaches (MLR and MLP-ANN) and other assessments, it was found that the presence of intense anthropogenic pressure in the study area and the current situation needs immediate remediation.

Identifying and measuring potential sources of pollution is essential for water management and pollution control. Using a range of artificial intelligence models to analyze water quality (WQ) is one of the most effective techniques for estimating water quality index (WQI). In this context, machine learning–based models are introduced to predict the WQ factors of Southeastern Black Sea Basin. The data comprising monthly samples of different WQ factors were collected for 12 months at eight locations of the Türkiye region in Southeastern Black Sea. The traditional evaluation with WQI of surface water was calculated as average (i.e. good WQ). Single multiplicative neuron (SMN) model, multilayer perceptron (MLP) and pi-sigma artificial neural networks (PS-ANNs) were used to predict WQI, and the accuracy of the proposed algorithms were compared. SMN model and PS-ANNs were used for WQ prediction modeling for the first time in the literature. According to the results obtained from the proposed ANN models, it was found to provide a highly reliable modeling approach that allows capturing the nonlinear structure of complex time series and thus to generate more accurate predictions. The results of the analyses demonstrate the applicability of the proposed pi-sigma model instead of using other computational methods to predict WQ both in particular and other surface water resources in general.