REVIEW PAPER ON PREDICTION OF WATER QUALITY PARAMETER USING MACHINE LEARNING

In recent decades, machine learning (ML) artificial intelligence has found wide application in water quality monitoring and prediction due to the increasing complexity of water quality data. This complexity has been attributed to the global upsurge in anthropogenic activities and climatic variations. It is therefore critical to identify the most accurate and suitable ML model for water quality prediction. In this study, a systematic literature review (SLR) was carried out to explore the trend and progress in the application of ML models in water quality monitoring and prediction in Nigeria from 2003-2024. A comprehensive review of the effectiveness of advanced ML models as well as the gaps in their application in the area of water quality assessment and monitoring was also carried out using the PRISMA-P meta-analysis technique. Forty publications were used to perform bibliographic analysis and visualization using the VOS viewer software. The study found that globally, the use of hybrid ML models in water quality prediction has not been well explored; a majority of the prediction has been based on the use of artificial neural networks (ANN). Among the ANN algorithms, the adaptive neuro-fuzzy inference system (ANFIS), and Wavelet-Adaptive Neural Fuzzy Interference System (W-ANFIS) hybrid models are the most accurate in prediction; with temperature, dissolved oxygen (DO), pH, electrical conductivity (EC), and total dissolved solids (TDS) among the most frequently predicted parameters. Nigeria is grossly lagging in the application of ML in water quality prediction. This limitation is largely attributed to inadequate data on environmental monitoring. It is critical therefore for future water quality monitoring and prediction studies in Nigeria to take advantage of the rapidly evolving field of machine learning; with more emphasis placed on the hybridized machine learning algorithms

Machine learning （ML） possesses a deep network structure and powerful fitting capabilities， enabling the prediction of contaminant concentrations without complete physical and chemical mechanisms. Therefore， ML has become an important research tool for pollution early warning and water quality assessment in rivers and lakes. This review aimed to investigate the application scenarios， methodological focus， impact factors， bottlenecks， and future directions of ML in water quality assessment of water ecosystems. A specialized information database was established by searching the keywords "machine learning" ， "water quality assessment" ， "rivers" ， and "lakes" in the Web of Science （WOS） and China National Knowledge Infrastructure （CNKI）. There were 309 relevant literatures in this field， and the volume has increased sharply in recent years. The directions and predictive goals of the literature were analyzed by using feature selection and clustering validation techniques. It was found that water quality prediction was the main purpose for machine learning applications in the water ecosystems， which can generally be subdivided into two directions， i.e.， a specific time and the time series prediction of water quality. This study further investigated the effects of input factors and ML methods on the prediction accuracy of nutrients， chlorophyll-a （Chla）， and organic matter concentrations. The results showed that dissolved oxygen （DO）， water temperature （WT）， and pH were the top three high-frequency inputs of ML models for predicting pollutant concentrations. Internal and external sources， as well as parameters of hydraulic conditions such as flow， velocity， and water level， were also the core driving factors in ML models. It is suggested that the factors of internal and external sources and hydraulic conditions have great potential to improve the prediction accuracy of the ML model. Additionally， data missing， overfitting， and insufficient interpretability were the dominant limitations for the application of ML in the water quality assessment. Methods such as mechanistic model-ML coupling and interpretable machine learning （XML） have become the main focus of ML research in the current stage of research. The findings provided important reference information for water quality assessment and pollutant concentration prediction.

In North America, the Great Lakes contain approximately 20% of the available surface fresh water in the world. As a result, the Great Lakes Basin (GLB) is a well-known region for its extensive agricultural and food production activities. Such agricultural activities are considered one of the most significant non-point sources of nutrient transport, particularly nitrogen and phosphorus, to surface water and groundwater. This is mainly because of the application of synthetic fertilizers and manure for enhanced crop productivity and soil fertility. Such elevated nutrient concentrations can disrupt aquatic ecosystems, degrade surface and groundwater quality, and harm both human and aquatic life. However, quantification of nutrient concentrations in agricultural watersheds is challenging because it is influenced by different process parameters including soil type, climate, and land use conditions. These parameters are highly non-linear and uncertain which hinders the applicability of typical mathematical models in nutrient transport applications in surface water and groundwater quality. Therefore, data-driven models using machine learning (ML) algorithms have been extensively applied to unravel the complexities of nutrient transport in surface water and groundwater, tackling the main challenges associated with the mathematical models. This is mainly because ML algorithms can deal with complex datasets with high uncertainty and non-linearity while considering the interdependence between the process parameters. By leveraging historical datasets, ML algorithms can model the explain the cause-result and intricate interdependencies between process parameters, making them well-suited for simulating nutrient transport processes in surface and sub-surface water applications. In the current study, different ML algorithms were adopted to predict nutrient concentrations in surface water and groundwater in a sand plain agricultural watershed within the GLB in Ontario, Canada. These ML algorithms included regression (e.g., artificial neural network) and classification (e.g., decision trees) techniques to better simulate nutrient concentrations in surface water and groundwater. The ML input variables involved meteorological (e.g., precipitation), hydrogeological (e.g., groundwater levels), and water physico-chemical (e.g., pH) conditions. The performance of these ML algorithms was evaluated using different evaluation metrics such as root-mean squared error and F1-score for regression and classification models, respectively. The optimal ML models were selected according to the outcomes of these evaluation metrics. In addition, the interdependence between the involved process parameters (e.g., land use and precipitation) and nutrient concentrations was interpreted to determine the governing parameters on the nutrient transport process in surface and sub-surface water. The main outcomes of this study can help decision-makers in assessing the most effective management efforts to protect and improve surface water and groundwater quality in agricultural watersheds. In addition, these insights enable the interpolation of nutrient concentrations from discrete sampling points, facilitating predictions at unmonitored locations across the watersheds.

The global decline of water quality in rivers and streams has resulted in a pressing need to design new watershed management strategies. Water quality can be affected by multiple stressors including population growth, land use change, global warming, and extreme events, with repercussions on human and ecosystem health. A scientific understanding of factors affecting riverine water quality and predictions at local to regional scales, and at sub‐daily to decadal timescales are needed for optimal management of watersheds and river basins. Here, we discuss how machine learning (ML) can enable development of more accurate, computationally tractable, and scalable models for analysis and predictions of river water quality. We review relevant state‐of‐the art applications of ML for water quality models and discuss opportunities to improve the use of ML with emerging computational and mathematical methods for model selection, hyperparameter optimization, incorporating process knowledge into ML models, improving explainablity, uncertainty quantification, and model‐data integration. We then present considerations for using ML to address water quality problems given their scale and complexity, available data and computational resources, and stakeholder needs. When combined with decades of process understanding, interdisciplinary advances in knowledge‐guided ML, information theory, data integration, and analytics can help address fundamental science questions and enable decision‐relevant predictions of riverine water quality.

Various pollutants have had a substantial impact on the quality of water in recent years. The quality of water directly impacts human health and the environment. The water quality index (WQI) is an indicator of effective water management. Water quality modelling and prediction have become essential in the fight against water pollution. The research aims to build an efficient prediction model for river water quality and to categorize the index value according to the water quality standards. The data has been collected from eleven sampling stations located in various locations across the Bhavani River, which flows through Kerala and Tamilnadu. The water quality index is determined by 27different parameters affecting water quality like dissolved oxygen, temperature, pH, alkalinity, hardness, chloride, coliform, etc. Data normalization and feature selection are done to construct the dataset to develop machine learning models. Machine learning algorithms such as linear regression, MLP regressor, support vector regressor and random forest has been employed to build a water quality prediction model. Support vector machines (SVM), naïve bayes, decision trees, MLP classifiers, have been used to develop a classification model for classifying water quality index. The experimental results revealed that the MLP regressor efficiently predicts the water Quality index with root mean squared error as 2.432, MLP classifier classifies the water quality index with 81% accuracy. The developed models show promising output concerning water quality index prediction and classification.

For effective management of water quantity and quality, it is absolutely essential to estimate the pollution level of the existing surface water. This case study aims to evaluate the performance of twelve machine learning (ML) models, including five boosting-based algorithms (adaptive boosting, gradient boosting, histogram-based gradient boosting, light gradient boosting, and extreme gradient boosting), three decision tree-based algorithms (decision tree, extra trees, and random forest), and four ANN-based algorithms (multilayer perceptron, radial basis function, deep feed-forward neural network, and convolutional neural network), in estimating the surface water quality of the La Buong River in Vietnam. Water quality data at four monitoring stations alongside the La Buong River for the period 2010–2017 were utilized to calculate the water quality index (WQI). Prediction performance of the ML models was evaluated by using two efficiency statistics (i.e., R2 and RMSE). The results indicated that all twelve ML models have good performance in predicting the WQI but that extreme gradient boosting (XGBoost) has the best performance with the highest accuracy (R2 = 0.989 and RMSE = 0.107). The findings strengthen the argument that ML models, especially XGBoost, may be employed for WQI prediction with a high level of accuracy, which will further improve water quality management.

Water quality is essential for human health and ecosystem stability, as pollution can cause serious health issues and harm wildlife. Large-scale and on-going monitoring is difficult using traditional methods of water quality assessment since they are frequently costly, time-consuming, and labour-intensive. This paper suggests a prediction framework that uses machine learning approaches to effectively assess water potability in order to get beyond these restrictions. To assess whether water is safe to drink, the system looks at important water quality factors such pH, organic carbon, chloramines, hardness, sulphate, tri-halo-methane, particulates, conductivity, and turbidity. For classification, a Random Forest classifier is used, which is renowned for its excellent accuracy, resilience, and capacity to manage intricate datasets. The program can more accurately forecast the potability of water because it was trained on a large amount of water quality data. Furthermore, a web-based interface is created to offer real-time forecasts, allowing users to enter water quality criteria and get prompt feedback on the water's safety. Because of this, the system is very useful for government organizations, businesses, and rural communities with restricted access to laboratory testing. In addition to improving the effectiveness of current water testing techniques, the suggested framework provides a quick and affordable substitute for extensive water quality monitoring. This strategy can assist reduce health risks, enhance water resource management, and promote sustainable environmental policies by facilitating on-going assessment and early detection of contaminants. The findings of this study show that by offering an automated and scalable solution for real-time water assessment, machine learning-based water quality prediction can greatly improve ecological conservation and public health. Keywords – Water Quality Prediction, Machine Learning, Random Forest, Water potability, Environmental Monitoring

In order to maintain and improve the water quality in European rivers, the Water Framework Directive (WFD) requires an integrated approach for assessing water quality in a river basin. Although the WFD aims at a holistic understanding of ecosystem functioning, it does not explicitly establish cause-effect relationships between stressors and changes in aquatic communities. To overcome this limitation, the present study combines the typical WFD physicochemical and biological approaches with an ecotoxicological approach. The main goal was to assess river water quality through an integrated manner, while identifying potential risk situations for aquatic communities in the Cértima river basin (Portugal). To achieve this goal, surface water samples and macroinvertebrate specimens were collected under contrasting hydrological conditions (autumn and spring seasons) at three river sites exposed to distinct pollution levels defined according to the WFD (low, moderate and highly polluted). Physicochemical water quality status was defined according to the Portuguese classification for multipurpose surface waters, whereas biological water quality was assessed in accordance with the South Invertebrate Portuguese Index. Ecotoxicological assays included four standard species, a bacterial species (Vibrio fischeri), a unicellular algae (Pseudokirchneriella subcapitata), a macrophyte (Lemna minor) and a crustacean (Daphnia magna), which were exposed to different river water concentrations. The study sites represented a clear and pronounced gradient of pollution, from the unpolluted reference site to the sites under moderate to high anthropogenic pressure. In the latter sites, clear signs of organic pollution were found, such as low dissolved oxygen concentrations, high nutrient loads and prevalence of highly tolerant macroinvertebrate species. Despite the evident signs of pollution, no clear evidence of toxicity was observed in test species, suggesting that ecotoxicological assays using standard laboratory species and methodologies might not be suitable for assessing the effects of organic pollution. Nevertheless, the integrated methodology presented in this study provided important additional information on the Cértima's water quality status. Its wider use could contribute to a more comprehensive assessment of the effects of anthropogenic pollution on the status and functioning of aquatic ecosystems under the WFD and, thereby, improve the scientific foundations for the sustainable future management of surface water resources.

Forecasting water quality through machine learning and hyperparameter optimization is a research endeavor aimed at enhancing the water quality prediction process. The primary goal of this study is to employ various machine learning algorithms for water quality prediction and to refine existing models from previous research. The paper encompasses a comprehensive literature review of previous water quality prediction studies and introduces novel theoretical insights. The research employs a classic machine learning problem-solving approach, predominantly utilizing the extreme gradient boost (XGBoost) algorithm. Additionally, it evaluates other machine learning algorithms, including the random forest (RF) classifier, decision tree (DT) classifier, adaptive boosting (AdaBoost) classifier, support vector machine (SVM), Naïve Bayes, and extra tree classifier for comparison. The evaluation process utilizes a classification report, providing insights into the precision, recall, f1-score, and accuracy of each machine learning model. Notably, the XGBoost model exhibits superior performance, achieving an impressive 97.06% accuracy. Precision stands at 94.22%, recall at 81.5%, and F1-score at 87.4%. These results represent a significant advancement over prior water quality prediction models, emphasizing the potential of machine learning and hyperparameter optimization to enhance water quality forecasting in environmental monitoring.

Water quality in terms of nitrogen transport and transformations in surface water has been presented in both spatial and temporal distributions. The paper is concentrated on the analysis for the Lake Nasser, the main Nile with the two branches, the drains, irrigation canals and rayahs. The spatial variation of the sampled water quality parameters is presented with the comparison to the recommended standard (Law 48/1982). Further temporal analysis considering the previous campaign (September 2000) results is presented. The study concluded that the nitrate problem has been found in the drains where agricultural land is the main source of nitrate in the surface water in Egypt. The research also concluded that the problems of understanding the different relations between the water quality evolution, estimating the effect of river flow and water quality management projects, etc. be solved by analysis of monitoring results and simulation models can have a significant and decisive role. Furthermore, the study indicated that the water quality models are the tools for analyzing, extrapolating and predicting water quality. To reduce groundwater and surface water pollution and control the environmental cost to remove nitrate-nitrogen from water, it is essential to understand fully the nitrate leaching from agricultural fields. Finally, it is recommended to build up a conceptual simplified model for the point-sources locations to be able to propose different scenarios for improving the current state of the river and drains quality conditions.

Identifying spatiotemporal variation patterns and predicting future water quality are critical for rational and effective surface water management. In this study, an exploratory analysis and forecast workflow for water quality in Pearl River, Guangzhou, China, was established based on the 4-h interval dataset selected from 10 stations for water quality monitoring from 2019 to 2021. The multiple statistical techniques, such as cluster analysis (CA), principal component analysis (PCA), correlation analysis (CoA), and redundancy analysis (RDA), as well as data-driven model (i.e., gated recurrent unit (GRU)), were applied for assessing and predicting the water quality in the basin. The investigated sampling stations were classified into 3 categories based on differences in water quality, i.e., low, moderate, and high pollution regions. The average water quality indexes (WQI) values ranged from 38.43 to 92.63. Nitrogen was the most dominant pollutant, with high TN concentrations of 0.81-7.67mg/L. Surface runoff, atmospheric deposition, and anthropogenic activities were the major contributors affecting the spatiotemporal variations in water quality. The decline in river water quality during the wet season was mainly attributed to increased surface runoff and extensive human activities. Furthermore, the short-term prediction of river water quality was achieved using the GRU model. The result indicated that for both DLCK and DTJ stations, the WQI for the 5-day lead time were predicted with accuracies of 0.82; for the LXH station, the WQI for the 3-day lead time was forecasted with an accuracy of 0.83. The finding of this study will shed a light on an effective reference and systematic support for spatio-seasonal variation and prediction patterns of water quality.

Machine learning-based water quality prediction using octennial in-situ Daphnia magna biological early warning system data

The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most (27 [63%]) focused on cardiovascular diseases and diabetes. Most (35 [81%]) were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19% and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45% vs 29%). The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms' quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.

Artificial intelligence and spine: rise of the machines

The actuality of this article is in the implementation of a systematic approach to the study of natural water quality of the river Lopan (within Kharkiv region).Assessment of water quality in the rivers has been studied by such scholars as O.O. Alexin, A.M. Gorev, V.M. Zhukynsky, F.F. Kirkov, A.M. Nikanorov, A.V. Ogievsky, O.P. Oksijuk, N.P. Puzyrevsky, V.D.Romanenko, V.K. Khilchevsky, A.P. Yatsyk, et al. But they all studied mainly large river basins, and we propose to investigate changes in the chemical composition of an average river that flows in the industrialized region.The research has been conducted on the methodology of environmental assessment of surface water quality according to the respective categories, in three blocks: salt, trophy-saprobiological, and the block of specific toxic action substances.The results of the research have shown that according to the salt block water in the river is saline; according to the trophy-saprobiological block water in the rivers is the most heavily polluted with phosphate phosphorus, which often leads to significant eutrophication of the reservoirs, nitrite and nitrate nitrogen, low water clarity; according to the block of specific substances – with phenols; according to the environmental index surface water quality of the river Lopan virtually did not change during 1980-2014, 2-3 grade (water is quite clean, slightly contaminated), but in recent years there has been no improvement in water quality of the river.In previous years industry was the main source of water pollution of the river Lopan, but in recent years it is municipal services, industrial enterprises and agriculture. The river Lopan was the most polluted in 1990, the least - in 2010. The biggest pollutants in the river Lopan were nitrite nitrogen, nitrate nitrogen, phosphorus and phosphate phenols.The actuality of this article is in the implementation of a systematic approach to the study of natural water quality of the river Lopan (within Kharkiv region).Assessment of water quality in the rivers has been studied by such scholars as O.O. Alexin, A.M. Gorev, V.M. Zhukynsky, F.F. Kirkov, A.M. Nikanorov, A.V. Ogievsky, O.P. Oksijuk, N.P. Puzyrevsky, V.D.Romanenko, V.K. Khilchevsky, A.P. Yatsyk, et al. But they all studied mainly large river basins, and we propose to investigate changes in the chemical composition of an average river that flows in the industrialized region. The research has been conducted on the methodology of environmental assessment of surface water quality according to the respective categories, in three blocks: salt, trophy-saprobiological, and the block of specific toxic action substances.The results of the research have shown that according to the salt block water in the river is saline; according to the trophy-saprobiological block water in the rivers is the most heavily polluted with phosphate phosphorus, which often leads to significant eutrophication of the reservoirs, nitrite and nitrate nitrogen, low water clarity; according to the block of specific substances – with phenols; according to the environmental index surface water quality of the river Lopan virtually did not change during 1980-2014, 2-3 grade (water is quite clean, slightly contaminated), but in recent years there has been no improvement in water quality of the river. In previous years industry was the main source of water pollution of the river Lopan, but in recent years it is municipal services, industrial enterprises and agriculture. The river Lopan was the most polluted in 1990, the least - in 2010. The biggest pollutants in the river Lopan were nitrite nitrogen, nitrate nitrogen, phosphorus and phosphate phenols.