Search

Groundwater resources constitute one of the primary sources of freshwater in semi-arid and arid climates. Monitoring the groundwater quality is an essential component of environmental management. In this study, a comprehensive comparison was conducted to analyze the performance of nine ensembles and regular machine learning (ML) methods in predicting two water quality parameters including total dissolved solids (TDS) and pH, in an area with semi-arid climate conditions. The study area under consideration is an aquifer located in the Sirjan plain, Kerman, Iran. The developed models include standard multilayer perceptron neural network (MLPNN), classification and regression trees (CART), Chi-square automatic interaction detection (CHAID), and their ensemble versions in bagging (BG) and boosting (BT) ensemble structures. The analysis revealed that standard MLs yield comparable results in predicting TDS. The MLPNN, exhibiting a standard root mean square error (SRMSE) of 0.085, demonstrated superior accuracy in predicting TDS when contrasted with CART and CHAID models. Predicting pH poses a greater challenge for the models. Ensemble techniques significantly enhanced the accuracy of regular models. On average, the bagging and boosting techniques resulted in a 22.68% improvement in the accuracy of regular models, which represents a statistically significant enhancement. The boosting method, with an average SRMSE of 0.0602, is more accurate than bagging. Based on the results, the CHAID-BT with SRMSE of 0.0790 and CHAID-BG with SRMSE of 0.0330 are ranked the most accurate models for predicting TDS and pH, respectively. The performance of ensemble techniques in predicting TDS is more remarkable. In practical implementation, ensemble techniques can be considered an alternative method with high accuracy for sustainable water resources management in semi-arid regions, helping to address water shortages, climate change, water pollution, etc., Competing Interests: Declarations. Ethical approval: Not applicable. Consent to participate: Not applicable. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests., (© 2025. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Biochemical oxygen demand (BOD) is one of the most important parameters used for water quality assessment. Alternative methods are essential for accurately prediction of this parameter because the traditional method in predicting the BOD is time-consuming and it is inaccurate due to inconstancies in microbial multiplicity. In this study, the applicability of four hybrid neuro-fuzzy (ANFIS) methods, ANFIS with genetic algorithm (GA), ANFIS with particle swarm optimization (PSO), ANFIS with sine cosine algorithm (SCA), and ANFIS with marine predators algorithm (MPA), was investigated in predicting BOD using distinct input combinations such as potential of hydrogen (pH), dissolved oxygen (DO), electrical conductivity (EC), water temperature (WT), suspended solids (SS), chemical oxygen demand (COD), total nitrogen (TN), and total phosphorus (T-P) acquired from two river stations, Gongreung and Gyeongan, South Korea. The applicability of multi-variate adaptive regression spline (MARS) in determination of the best input combination was examined. The ANFIS-MPA was found to be the best model with the lowest root mean square error and mean absolute error and the highest determination coefficient. It improved the root mean square error of ANFIS-PSO, ANFIS-GA, and ANFIS-SCA models by 13.8%, 12.1%, and 6.3% for Gongreung Station and by 33%, 25%, and 6.3% for Gyeongan Station in the test stage, respectively., (© 2023. The Author(s).)

Lake water quality plays a vital role in the lake ecosystem, including biotic (for living creatures, such as plants, animals, and micro-organisms) and abiotic interactions. In this research, various types of machine learning (ML) methodologies, such as classification and regression tree (CART), chi-squared automatic interaction detector (CHAID), C5 tree, quick, unbiased, and efficient statistical tree (QUEST), along with multilayer perceptron (MLP) neural network, and radial basis function (RBF) neural network, are employed to predict the concentration of water quality parameters (P, EC, TDS, pH, DO, NH3, SO4, and θ). Lake Erie is situated at the international border of the USA and Canada. The C5 tree and QUEST tree are used to classify data and predict the number of groups, while the other methods are used to predict the concentration of water quality parameters in the form of a 3-year moving average. The greater matching between the observed and predicted data of dissolved oxygen (NSE = 0.978, bias = 0.126) shows that the CART decision tree has higher accuracy in correctly detecting the concentration of this parameter. The C5 tree could identify 33 groups correctly out of 36 total groups, which shows better accuracy for the C5 tree in classifying the data for this parameter., (© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Machines learning models have recently been proposed for predicting rivers water temperature (T w ) using only air temperature (T a ). The proposed models relied on a nonlinear relationship between the T w and T a and they have proven to be robust modelling tools. The main motivation for this study was to evaluate how the variational mode decomposition (VMD) contributed to the improvement of machines learning performances for river T w modelling. Measured data collected at five stations located in Poland from 1987 to 2014 were acquired and used for the analysis. Six machines learning models were used and compared namely, K-nearest neighbor's regression (KNNR), least square support vector machine (LSSVM), generalized regression neural network (GRNN), cascade correlation artificial neural networks (CCNN), relevance vector machine (RVM), and locally weighted polynomials regression (LWPR). The six models were developed according to three scenarios. First, the models were calibrated using only the T a as input and obtained results show that the models were able to predict consistently water temperature, showing a high determination coefficient (R 2 ) and Nash-Sutcliffe efficiency (NSE) with values near or above 0.910 and 0.915, respectively, and in overall the six models worked equally without clear superiority of one above another. Second, the air temperature was combined with the periodicity (i.e., day, month and year number) as input variable and a significant improvement was achieved. Both models show their ability to accurately predict river T w with an overall accuracy of 0.956 for R 2 and 0.955 for NSE values, but the LSSVM2 have some advantages such as a small errors metrics, and high fitting capabilities and it slightly surpasses the others models. Thirdly, air temperature was decomposed into several intrinsic mode functions (IMF) using the VMD method and the performances of the models were evaluated. The VMD parameters appeared to cause much influence on the prediction accuracy, exhibiting an improvement of about 40.50% and 39.12% in terms of RMSE and MAE between the first and the third scenarios, however, some models, i.e., GRNN and KNNR have not benefited from the VMD. This research has demonstrated the high capability of the VMD algorithm as a preprocessing approach in improving the accuracies of the machine learning models for river water temperature prediction., (© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

This study evaluates the potential of kriging-based (kriging and kriging-logistic) and machine learning models (MARS, GBRT, and ANN) in predicting the effluent arsenic concentration of a wastewater treatment plant. Two distinct input combination scenarios were established, using seven quantitative and qualitative independent influent variables. In the first scenario, all of the seven independent variables were taken into account for constructing the data-driven models. For the second input scenario, the forward selection k-fold cross-validation method was employed to select effective explanatory influent parameters. The results obtained from both input scenarios show that the kriging-logistic and machine learning models are effective and robust. However, using the feature selection procedure in the second scenario not only made the architecture of the model simpler and more effective, but also enhanced the performance of the developed models (e.g., around 7.8% performance enhancement of the RMSE). Although the standard kriging method provided the least good predictive results (RMSE = 0.18 ug/l and NSE=0.75), it was revealed that the kriging-logistic method gave the best performance among the applied models (RMSE = 0.11 ug/l and NSE=0.90)., (© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)