This study delves into the environmental impact of inland aquaculture on estuarine ecosystems by examining the water quality of four estuarine streams within the key inland aquaculture zone of South India. In this region, extensive and intensive aquaculture practices are common, posing potential challenges to estuarine health. The research explores the predictive capabilities of the Gaussian elimination method (GEM) and machine learning techniques, specifically multi-linear regression (MLR) and support vector regressor (SVR), in forecasting the water quality index of these streams. Through comprehensive evaluation using performance metrics such as coefficient of determination (R2) and average mean absolute percentage error (MAPE), MLR and SVR demonstrate higher prediction efficiency. Notably, employing key water parameters as inputs in machine learning models is also more effective. Biochemical oxygen demand (BOD) emerges as a critical water parameter, identified by both MLR and SVR, exhibiting high specificity in predicting water quality. This suggests that MLR and SVR, incorporating key water parameters, should be prioritized for future water quality monitoring in intensive aquaculture zones, facilitating timely warnings and interventions to safeguard water quality.

Water plays a significant role in sustaining the lives of humans and other living organisms. Groundwater quality analysis has become inevitable, because of increased contamination of water resources and global warming. This study used machine learning (ML) models to predict the water quality index (WQI) and water quality classification (WQC). Forty groundwater samples were collected near the Ranipet industrial corridor, and the hydrogeochemistry and heavy metal contamination were analyzed. WQC prediction employed random forest (RF), gradient boosting (GB), decision tree (DT), and K-nearest neighbor (KNN) models, and WQI prediction used extreme gradient boosting (XGBoost), support vector regressor (SVR), RF, and multi-layer perceptron (MLP) models. The grid search method is used to evaluate the ML model by F1 score, accuracy, recall, precision, and Matthews correlation coefficient (MCC) for WQC and the coefficient of determination (R2), mean absolute error (MAE), mean square error (MSE), and median absolute percentage error (MAPE) for WQI. The WQI results indicate that the groundwater quality of the study area is very poor and unsuitable for drinking or irrigation purposes. The performance metrics of the RF model excelled in predicting both WQC (accuracy = 97%) and WQI (R2 = 91.0%), outperforming other models and emphasizing ML\'s superiority in groundwater quality assessment. The findings suggest that ML models perform well and yield better accuracy than conventional techniques used in groundwater quality assessment studies.

Understanding seasonal variations in water quality is crucial for effective management of freshwater rivers amidst changing environmental conditions. This study employed water quality index (WQI), metal index (MI), and pollution indices (PI) to comprehensively assess water quality and pollution levels in Nyabarongo River of Rwanda. A dynamic driver-pressure-state-impact-response model was used to identify factors influencing quality management. Over 4 years (2018-2021), 69 samples were collected on a monthly basis from each of the six monitoring stations across the Nyabarongo River throughout the four different seasons. Maximum WQI values were observed during dry long (52.90), dry short (21.478), long rain (93.66), and short rain (37.4) seasons, classified according to CCME 2001 guidelines. Ion concentrations exceeded WHO standards, with dominant ions being HCO 3 - and Mg 2 + . Variations in water quality were influenced by factors such as calcium bicarbonate dominance in dry seasons and sodium sulfate dominance in rainy seasons. Evaporation and precipitation processes primarily influenced ionic composition. Metal indices (MI) exhibited wide ranges: long dry (0.2-433.0), short dry (0.1-174.3), long rain (0.1-223.7), and short rain (0.3-252.5). The hazard index values for Cu2+, Mn4+, Zn2+, and Cr3+ were below 1, ranging from 8.89E - 08 to 7.68E - 07 for adults and 2.30E - 07 to 5.02E - 06 for children through oral ingestion, and from 6.68E - 10 to 5.07E - 07 for adults and 6.61E - 09 to 2.54E - 06 for children through dermal contact. With a total carcinogenic risk of less than 1 for both ingestion and dermal contact, indicating no significant health risks yet send strong signals to Governmental management of the Nyabarongo River. Overall water quality was classified as marginal in long dry, poor in short dry, good in long rain, and poor again in short rain seasons.

Assessing water quality in arid regions is vital due to scarce resources, impacting health and sustainable management.This study examines groundwater quality in Assuit Governorate, Egypt, using Principal Component Analysis, GIS, and Machine Learning Techniques. Data from 217 wells across 12 parameters were analyzed, including TDS, EC, Cl-, Fe++, Ca++, Mg++, Na+, SO4--, Mn++, HCO3-, K+, and pH. The Water Quality Index (WQI) was calculated, and ArcGIS mapped its spatial distribution. Machine learning algorithms, including Ridge Regression, XGBoost, Decision Tree, Random Forest, and K-Nearest Neighbors, were used for predictive analysis. Higher concentrations of Na, K, Ca, Mg, Mn, and Fe were correlated with industrial and densely populated areas. Most samples exhibited excellent or good quality, with a small percentage unsuitable for consumption. Ridge Regression showed the lowest MAPE rates (0.22 % training, 0.26 % in testing). This research highlights the importance of advanced machine learning for sustainable groundwater management in arid regions. Thus, our results could provide valuable assistance to both national and local authorities involved in water management decisions, particularly for water resource managers and decision-makers. This information can aid in the development of regulations aimed at safeguarding and sustainably managing groundwater resources, which are essential for the overall prosperity of the country.

Many urban water bodies grapple with low flow flux and weak hydrodynamics. To address these issues, projects have been implemented to form integrated urban water bodies via interconnecting artificial lake or ponds with rivers, but causing pollution accumulation downstream and eutrophication. Despite it is crucial to assess eutrophication, research on this topic in urban interconnected water bodies is limited, particularly regarding variability and feasible strategies for remediation. This study focused on the Loucun river in Shenzhen, comprising an pond, river and artificial lake, evaluating water quality changes pre-(post-)ecological remediation and establishing a new method for evaluating the water quality index (WQI). The underwater forest project, involving basement improvement, vegetation restoration, and aquatic augmentation, in the artificial lake significantly reduced total nitrogen (by 43.58%), total phosphorus (by 79.17%) and algae density (by 36.90%) compared to pre-remediation, effectively controlling algal bloom. Rainfall, acting as a variable factor, exacerbated downstream nutrient accumulation, increasing total phosphorus by 4.56 times and ammonia nitrogen by 1.30 times compared to the dry season, and leading to algal blooms in the non-restoration pond. The improved WQI method effectively assesses water quality status. The interconnected water body exhibits obvious nutrient accumulation in downstream regions. A combined strategy that reducing nutrient and augmenting flux was verified to alleviate accumulation of nutrients downstream. This study provides valuable insights into pollution management strategies for interconnected pond-river-lake water bodies, offering significant reference for nutrient mitigation in such urban water bodies.

The Gidabo River and its tributaries are the main sources of water for more than 1,584,646 inhabitants. It is an important source of water for the surrounding rural communities for various uses such as domestic, irrigation, livestock watering, fishing, and recreation. The river is the main tributary of Lake Abaya. The present study was designed to investigate the water quality status of the Gidabo River and its tributaries for domestic and aquatic life. To assess the water quality status, water samples were collected in monthly intervals for a period of 3 months from September to November (coffee processing time), 2022. Arc GIS 9.3, 3 DEM, and spreadsheet were used to analyze the data collected from SRTM (Shuttle Radar Thematic Mapper, 90 m) and field observation. Of all the water quality parameters analyzed; turbidity, BOD5, DO, COD, pH, Ni, Fe, NO3 -, and PO4 3- were higher than the recommended limits of national and international standards for aquatic life. Based on the Weighted Arithmetic Mean (WAM), Water Quality Index (WQI) calculations of the River, WQI value of the river ranges between 34.83 and 54.31 in different reaches of the watershed which is classified under bad category. The wet coffee processing industry which is the main sources of contamination in the watershed uses 63 L of processing water to produce 1 kg of green coffee beans. Traditional lagoons, with an average hydraulic retention time (HRT) of 1.99 days, are the most common methods of treating wastewater. The river is at higher risk from harmful anthropogenic activities in the watershed and requires urgent monitoring and mitigation to prevent further degradation.

Self-supply water sources, particularly groundwater sources, play key roles in the water supply ecosystem of developing countries. Recent studies indicate that groundwater sources in coastal communities in Ghana are under threat from improper waste management practices, seawater intrusion and atmospheric aerosol deposition. In this study, Water Quality Index (WQI) and Nemerow\'s Pollution Index (NPI) were employed to assess groundwater quality in four coastal communities of Ghana. The health risks associated with metal pollution of groundwater were investigated using incremental life cancer risk and hazard quotient. pH of groundwater in all the studied communities were acidic during the rainy season. Electrical conductivity ranged from 0.44 to 2.61 mS/cm in the rainy season and from 0.43 to 2.45 mS/cm in the dry season for the four studied locations. Results also showed brackish conditions and mineralization of groundwater in Winneba, Accra, and Keta. Mean nitrate concentrations in Winneba and Accra were higher than the WHO standards for both the rainy and the dry season. Arsenic was higher than the acceptable level in Accra and Keta during the dry season, while iron was higher than the acceptable levels in Accra in both the rainy and dry seasons. Principal Component Analyses showed that Pb, As, and Fe had the highest loading in the first component in Essiama, while PO4 3-and Pb had the highest loading in the second component in Accra. WQI showed that the quality of groundwater in all the studied communities ranged from marginal to poor indicating that groundwater in the coastal communities often or usually departs from desirable quality. NPI revealed that NO3- , As, and Fe contribute to groundwater deterioration. Health risk assessment showed that As posed a high cancer risk in Accra and potential cancer risk in Essiama, Winneba, and Keta during the dry season. As also posed potential cancer risk in Accra during the rainy season. Non-cancer health risk was observed for As in Accra and Keta. The findings of this study suggest urgent regulations and monitoring strategies to improve groundwater quality in the coastal communities of Ghana.

The aim of the present study was to assess the drinking water quality in the selected urban areas of Lahore and to comprehend the public health status by addressing the basic drinking water quality parameters. Total 50 tap water samples were collected from groundwater in the two selected areas of district Lahore i.e., Gulshan-e-Ravi (site 1) and Samanabad (site 2). Water samples were analyzed in the laboratory to elucidate physico-chemical parameters including pH, turbidity, temperature, total dissolved solids (TDS), electrical conductivity (EC), dissolved oxygen (DO), total hardness, magnesium hardness, and calcium hardness. These physico-chemical parameters were used to examine the Water Quality Index (WQI) and Synthetic Pollution Index (SPI) in order to characterize the water quality. Results of th selected physico-chemical parameters were compared with World Health Organization (WHO) guidelines to determine the quality of drinking water. A GIS-based approach was used for mapping water quality, WQI, and SPI. Results of the present study revealed that the average value of temperature, pH, and DO of both study sites were within the WHO guidelines of 23.5 °C, 7.7, and 6.9 mg/L, respectively. The TDS level of site 1 was 192.56 mg/L (within WHO guidelines) and whereas, in site 2 it was found 612.84 mg/L (higher than WHO guidelines), respectively. Calcium hardness of site 1 and site 2 was observed within the range from 25.04 to 65.732 mg/L but, magnesium hardness values were higher than WHO guidelines. The major reason for poor water quality is old, worn-out water supply pipelines and improper waste disposal in the selected areas. The average WQI was found as 59.66 for site 1 and 77.30 for site 2. Results showed that the quality of the water was classified as \"poor\" for site 1 and \"very poor \" for site 2. There is a need to address the problem of poor water quality and also raise the public awareness about the quality of drinking water and its associated health impacts.

The determination of water quality heavily depends on the selection of parameters recorded from water samples for the water quality index (WQI). Data-driven methods, including machine learning models and statistical approaches, are frequently used to refine the parameter set for four main reasons: reducing cost and uncertainty, addressing the eclipsing problem, and enhancing the performance of models predicting the WQI. Despite their widespread use, there is a noticeable gap in comprehensive reviews that systematically examine previous studies in this area. Such reviews are essential to assess the validity of these objectives and to demonstrate the effectiveness of data-driven methods in achieving these goals. This paper sets out with two primary aims: first, to provide a review of the existing literature on methods for selecting parameters. Second, it seeks to delineate and evaluate the four principal motivations for parameter selection identified in the literature. This manuscript categorizes existing studies into two methodological groups for refining parameters: one focuses on preserving information within the dataset, and another ensures consistent prediction using the full set of parameters. It characterizes each group and evaluates how effectively each approach meets the four predefined objectives. The study presents that the minimal WQI approach, common to both categories, is the only approach that has successfully reduced recording costs. Nonetheless, it notes that simply reducing the number of parameters does not guarantee cost savings. Furthermore, the group of studies classified as preserving information within the dataset has demonstrated potential to decrease the eclipsing problem, whereas studies in the consistent prediction group have not been able to mitigate this issue. Additionally, since data-driven approaches still rely on the initial parameters chosen by experts, they do not eliminate the need for expert judgment. The study further points out that the WQI formula is a straightforward and expedient tool for assessing water quality. Consequently, the paper argues that employing machine learning solely to reduce the number of parameters to enhance WQI prediction is not a standalone solution. Rather, this objective should be integrated with a more comprehensive set of research goals. The critical analysis of research objectives and the characterization of previous studies lay the groundwork for future research. This groundwork will enable subsequent studies to evaluate how their proposed methods can effectively achieve these objectives.

The water crisis may be solved by utilizing reclaimed water. Three reclaimed water sources have restored the lower sections of the Licun River, forming a landscaped river. In this paper, the river\'s water quality was monitored for a year, and the ecological concerns were analyzed using luminescent bacteria, chlorella, and zebrafish. The results indicated that although basic water quality indicators like COD and ammonia fluctuated along the river, the classification of water quality was primarily affected by factors such as flow rate and water depth. Under experimental conditions, the toxic inhibitory effect of river water on luminescent bacteria, chlorella, and zebrafish was related to the treatment process of reclaimed water. It was found that the reclaimed water produced by the MBR, along with the UV disinfection process, showed no detectable toxicity. In contrast, the MBBR process, when combined with coagulation, sedimentation, filtration, ozonation, and chlorination, seemed to be the source of this toxicity. Along the river, the results of water quality assessments and ecological risk assessments were different, indicating that both should be conducted to evaluate rivers replenished with reclaimed water.