Prediction of potentially toxic elements in water resources using MLP-NN, RBF-NN, and ANFIS: a comprehensive review.

Water resources are constantly threatened by pollution of potentially toxic elements (PTEs). In efforts to monitor and mitigate PTEs pollution in water resources, machine learning (ML) algorithms have been utilized to predict them. However, review studies have not paid attention to the suitability of input variables utilized for PTE prediction. Therefore, the present review analyzed studies that employed three ML algorithms: MLP-NN (multilayer perceptron neural network), RBF-NN (radial basis function neural network), and ANFIS (adaptive neuro-fuzzy inference system) to predict PTEs in water. A total of 139 models were analyzed to ascertain the input variables utilized, the suitability of the input variables, the trends of the ML model applications, and the comparison of their performances. The present study identified seven groups of input variables commonly used to predict PTEs in water. Group 1 comprised of physical parameters (P), chemical parameters (C), and metals (M). Group 2 contains only P and C; Group 3 contains only P and M; Group 4 contains only C and M; Group 5 contains only P; Group 6 contains only C; and Group 7 contains only M. Studies that employed the three algorithms proved that Groups 1, 2, 3, 5, and 7 parameters are suitable input variables for forecasting PTEs in water. The parameters of Groups 4 and 6 also proved to be suitable for the MLP-NN algorithm. However, their suitability with respect to the RBF-NN and ANFIS algorithms could not be ascertained. The most commonly predicted PTEs using the MLP-NN algorithm were Fe, Zn, and As. For the RBF-NN algorithm, they were NO3, Zn, and Pb, and for the ANFIS, they were NO3, Fe, and Mn. Based on correlation and determination coefficients (R, R2), the overall order of performance of the three ML algorithms was ANFIS > RBF-NN > MLP-NN, even though MLP-NN was the most commonly used algorithm.

Graphical, statistical and index-based techniques integrated for identifying the hydrochemical fingerprints and groundwater quality of In Salah, Algerian Sahara.

Groundwater, a predominant reservoir of freshwater, plays a critical role in providing a sustainable potable water and water for agricultural and industry uses in the In Salah desert region of Algeria. This research collected 82 underground water samples from Albian aquifers to assess water quality and identify hydrogeochemical processes influencing mineralization. To achieve this objective, various methods were employed to evaluate water quality based on its intended uses. The drinking water quality index utilized revealed the water potability status, while the indicators of irrigation potability were employed to evaluate its quality for agricultural purposes. Additionally, an assessment of groundwater susceptibility to corrosion and scaling in an industrial context was conducted using several indices, e.g., Langelier index, Larson-Skold index, Ryznar index, chloride-sulfate mass ratio, Puckorius index, aggressiveness index, and the Revelle index. The findings of this study revealed that the groundwater quality for consumption fell into four categories: good (2.44%), fair (29.27%), poor (65.85%), and non-potable (2.44%). Concerning agricultural irrigation, the indexical results indicated that 15.85% of the waters exhibited adequate quality, while 84.15% were questionable for irrigation. Calculations based on various corrosion and scaling evaluation indices showed that most wells were prone to corrosion, with a tendency for calcium bicarbonate deposit formation. Furthermore, the hydrochemical study identified three water types: Na-Cl (53.66%), Ca-Mg-Cl (37.80%), and Ca-Cl (8.54%) waters. Analyses of correlation matrices, R-type clustering, factor loadings, Gibbs diagrams, scatterplots, and chloro-alkaline indices highlighted that the chemistry of the Albian groundwater is fundamentally impacted by a number of processes such as silicate weathering, evaporite dissolution, ionic exchange, and anthropogenic inputs, that played impactful role in the aquifer's water chemistry.

More about making profits or providing safe drinking water? A state-of-the-art review on sachet water contamination in Nigeria.

Public health concerns on surface and groundwater contamination worldwide have increased. Sachet water contamination has also raised serious concerns across many developing countries. While previous studies attempted to address this issue, this review takes a different approach by utilizing a comprehensive analysis of physicochemical parameters, heavy metals, and microbial loads tested in sachet water across Nigeria's six geopolitical zones, within the period of 2020-2023. In this review study, over 50 articles were carefully analyzed. Collected data unveiled regional variations in the quality of sachet water across Nigeria. Noteworthy concerns revolve around levels of pH, total hardness, magnesium, calcium, nickel, iron, lead, mercury, arsenic, and cadmium. Fecal contamination was also identified as a significant issue, with the prevalence of several pathogens like Escherichia coli, Salmonella typhi, Enterobacter cloacae, Staphylococcus aureus, and Enterococcus faecalis. The manufacturing, delivery, storage, and final sale of sachet water, as well as poor environmental hygiene, were identified as potential contamination sources. The intake of contaminated sachet water exposes the citizens to waterborne and carcinogenic diseases. While the sachet water industry keeps growing and making profits, it is apparent that improvement calls made by previous studies, regarding the quality of water produced, have not been paid serious attention.

A review of the status, challenges, trends, and prospects of groundwater quality assessment in Nigeria: an evidence-based meta-analysis approach.

With the imminent industrial growth and population increase, Nigeria will continue to experience significant shifts in the quality of water, with a rise in emerging contaminants. This will increase the irregularity and complexity of the water quality information. Therefore, using the PRISMA meta-analysis approach, this review systematically identified the commonly used water quality assessment techniques in Nigeria, the drawback in the application of these techniques as well as the gaps in the area of water quality assessment and monitoring from 2003 to 2023. Recommendations were also made based on the evaluation of a new research direction; through the review of the effectiveness of advanced techniques for monitoring water quality in Nigeria. Sixty-eight published articles were chosen for the meta-analysis while the VOSviewer program was used to perform bibliographic coupling and visualization. The review revealed that the application of machine learning in water quality prediction has not been well explored in Nigeria. This is attributed to limited data availability and poor funding by the government. It was found that southwestern Nigeria has a greater amount of research on groundwater quality monitoring and evaluation than other regions. The variability was explained by variations in the underlying geology, aquifer features; variability in anthropogenic activities, and level of literacy among various geopolitical zones. Further studies should focus on the application of soft-computing and integrated biomonitoring techniques for effective prediction and monitoring of emerging contaminants for improved water quality. Effective collaboration between environmental stakeholders and government agencies is recommended for effective water resource sustainability.

Trace element pollution tracking in the complex multi-aquifer groundwater system of Al-Hassa oasis (Saudi Arabia) using spatial, chemometric and index-based techniques.

In a global context, trace element pollution assessment in complex multi-aquifer groundwater systems is important, considering the growing concerns about water resource quality and sustainability worldwide. This research addresses multiple objectives by integrating spatial, chemometric, and indexical study approaches, for assessing trace element pollution in the multi-aquifer groundwater system of the Al-Hassa Oasis, Saudi Arabia. Groundwater sampling and analysis followed standard methods. For this purpose, the research employed internationally recognized protocols for groundwater sampling and analysis, including standardized techniques outlined by regulatory bodies such as the United States Environmental Protection Agency (USEPA) and the World Health Organization (WHO). Average values revealed that Cr (0.041) and Fe (2.312) concentrations surpassed the recommended limits for drinking water quality, posing serious threats to groundwater usability by humans. The trace elemental concentrations were ranked as: Li < Mn < Co < As < Mo < Zn < Al < Ba < Se < V < Ni < Cr < Cu < B < Fe < Sr. Various metal(loid) pollution indices, including degree of contamination, heavy metal evaluation index, heavy metal pollution index, and modified heavy metal index, indicated low levels of groundwater pollution. Similarly, low values of water pollution index and weighted arithmetic water quality index were observed for all groundwater points, signifying excellent groundwater quality for drinking and domestic purposes. Spatial distribution analysis showed diverse groundwater quality across the study area, with the eastern and western parts displaying a less desirable quality, while the northern has the best, making water users in the former more vulnerable to potential pollution effects. Thus, the zonation maps hinted the necessity for groundwater quality enhancement from the western to the northern parts. Chemometric analysis identified both human activities and geogenic factors as contributors to groundwater pollution, with human activities found to have more significant impacts. This research provides the scientific basis and insights for protecting the groundwater system and ensuring efficient water management.

Seasonal variation of the quality of groundwater resources for human consumption and industrial purposes in the central plain zone of Punjab, India.

Due to environmental pollution, climate change, and anthropogenic activities, the judicious use and regular assessment of the quality of groundwater for industrial, agricultural, and drinking purposes had gained a lot of attention across the globe. To assess the seasonal suitability of groundwater based on hydrochemistry and different quality indices, groundwater samples were collected and analyzed for different physicochemical parameters. Our findings indicated that the pH, electrical conductivity (EC), total dissolved solids (TDS), total hardness (TH), and calcium ion (Ca2+) content of groundwater were within acceptable limits of WHO and Bureau of Indian Standards (BIS) guidelines for drinking water. However, chloride content exceeded the acceptable levels, accounting for about 29.1% during the pre-monsoon and 15.3% during the post-monsoon period. Based on the water quality index (WQI), none of the water samples were deemed unsuitable for drinking purposes. However, when considering the synthetic pollution index (SPI), 100% of the samples were categorized as moderately polluted during both the pre-monsoon and post-monsoon periods. For industrial purpose suitability, 39.8 and 30.6% of the water samples had high corrosion tendency for pre-monsoon and post-monsoon seasons, respectively. Additionally, 77.5-93.4% of the total water samples were slightly affected by salinization on the basis of Revelle index. Generally, the groundwater quality for drinking purposes meets the WHO and BIS guidelines, with high corrosion potential for industrial use and slight salinization concerns in the area.

Understanding the connections between climate change, air pollution, and human health in Africa: Insights from a literature review.

Climate change and air pollution are two interconnected global challenges that have profound impacts on human health. In Africa, a continent known for its rich biodiversity and diverse ecosystems, the adverse effects of climate change and air pollution are particularly concerning. This review study examines the implications of air pollution and climate change for human health and well-being in Africa. It explores the intersection of these two factors and their impact on various health outcomes, including cardiovascular disease, respiratory disorders, mental health, and vulnerable populations such as children and the elderly. The study highlights the disproportionate effects of air pollution on vulnerable groups and emphasizes the need for targeted interventions and policies to protect their health. Furthermore, it discusses the role of climate change in exacerbating air pollution and the potential long-term consequences for public health in Africa. The review also addresses the importance of considering temperature and precipitation changes as modifiers of the health effects of air pollution. By synthesizing existing research, this study aims to shed light on complex relationships and highlight the key findings, knowledge gaps, and potential solutions for mitigating the impacts of climate change and air pollution on human health in the region. The insights gained from this review can inform evidence-based policies and interventions to mitigate the adverse effects on human health and promote sustainable development in Africa.

Occurrences, sources and health hazard estimation of potentially toxic elements in the groundwater of Garhwal Himalaya, India.

High concentrations of potentially toxic elements (PTEs) in potable water can cause severe human health disorders. Present study examined the fitness of groundwater for drinking purpose based on the occurrence of nine PTEs in a heavy pilgrim and tourist influx region of the Garhwal Himalaya, India. The concentrations of analyzed PTEs in groundwater were observed in the order of Zn > Mn > As > Al > Cu > Cr > Se > Pb > Cd. Apart from Mn and As, other PTEs were within the corresponding guideline values. Spatial maps were produced to visualize the distribution of the PTEs in the area. Estimated water pollution indices and non-carcinogenic risk indicated that the investigated groundwater is safe for drinking purpose, as the hazard index was < 1 for all the water samples. Assessment of the cancer risk of Cr, As, Cd, and Pb also indicated low health risks associated with groundwater use, as the values were within the acceptable range of ≤ 1 × 10-6 to 1 × 10-4. Multivariate statistical analyses were used to describe the various possible geogenic and anthropogenic sources of the PTEs in the groundwater resources although the contamination levels of the PTEs were found to pose no serious health risk. However, the present study recommends to stop the discharge of untreated wastewater and also to establish cost-effective as well as efficient water treatment facility nearby the study area. Present work's findings are vital as they may protect the health of the massive population from contaminated water consumption. Moreover, it can help the researchers, governing authorities and water supplying agencies to take prompt and appropriate decisions for water security.

Fluoride and nitrate enrichment in coastal aquifers of the Eastern Province, Saudi Arabia: The influencing factors, toxicity, and human health risks.

Fluoride and nitrate contamination of groundwater is a major environmental issue in the world's arid and semiarid regions. This issue is severe in both developed and developing countries. This study aimed at assessing the concentration levels, contamination mechanisms, toxicity, and human health risks of NO3- and F- in the groundwater within the coastal aquifers of the eastern part of Saudi Arabia using a standard integrated approach. Most of the tested physicochemical properties of the groundwater exceeded their standard limits. The water quality index and synthetic pollution index evaluated the suitability of the groundwater and showed that all the samples have poor and unsuitable quality for drinking. The toxicity of F- was estimated to be higher than NO3-. Also, the health risk assessment revealed higher risks due to F- than NO3-. Younger populations had higher risks than elderly populations. For both F- and NO3-, the order of health risk was Infants > Children > Adults. Most of the samples posed medium to high chronic risks due to F- and NO3- ingestion. However, negligible health risks were obtained for potential dermal absorption of NO3-. Na-Cl and Ca-Mg-Cl water types predominate in the area. Pearson's correlation analysis, principal component analysis, regression models, and graphical plots were used to determine the possible sources of the water contaminants and their enrichment mechanisms. Geogenic and geochemical processes had greater impact he groundwater chemistry than anthropogenic activities. For the first time, these findings provide public knowledge on the overall water quality of the coastal aquifers and could help the inhabitants, water management authorities, and researchers to identify the groundwater sources that are most desirable for consumption and the human populations that are vulnerable to non-carcinogenic health risks.

Evaluation of oral and dermal health risk exposures of contaminants in groundwater resources for nine age groups in two densely populated districts, Nigeria.

Human health and the sustainability of the socioeconomic system are directly related to water quality. As anthropogenic activity becomes more intense, pollutants, particularly potentially harmful elements (PHEs), penetrate water systems and degrade water quality. The purpose of this study was to evaluate the safety of using groundwater for domestic and drinking purposes through oral and dermal exposure routes, as well as the potential health risks posed to humans in the Nnewi and Awka regions of Nigeria. The research involved the application of a combination of the National Sanitation Foundation Water Quality Index (NSFWQI), HERisk code, and hierarchical dendrograms. Additionally, we utilized the regulatory guidelines established by the World Health Organization and the Standard Organization of Nigeria to compare the elemental compositions of the samples. The physicochemical parameters and NSFWQI evaluation revealed that the majority of the samples were PHE-polluted. Based on the HERisk code, it was discovered that in both the Nnewi and Awka regions, risk levels are higher for people aged 1 to <11 and >65 than for people aged 16 to <65. Overall, it was shown that all age categories appeared to be more vulnerable to risks due to the consumption than absorption of PHEs, with Cd > Pb > Cu > Fe for Nnewi and Pb > Cd > Cu > Fe for water samples from Awka. Summarily, groups of middle age are less susceptible to possible health issues than children and elderly individuals. Hierarchical dendrograms and correlation analysis showed the spatio-temporal implications of the drinking groundwater quality and human health risks in the area. This research could help local government agencies make informed decisions on how to effectively safeguard the groundwater environment while also utilizing the groundwater resources sustainably.

A multi-model study for understanding the contamination mechanisms, toxicity and health risks of hardness, sulfate, and nitrate in natural water resources.

Several water quality contaminants have attracted the attention of numerous researchers globally, in recent times. Although the toxicity and health risk assessments of sulfate and water hardness have not received obvious attention, nitrate contamination has gained peculiar research interest globally. In the present paper, multiple data-driven indexical, graphical, and soft computational models were integrated for a detailed assessment and predictive modeling of the contamination mechanisms, toxicity, and human health risks of natural waters in Southeast Nigeria. Majority of the tested physicochemical parameters were within their satisfactory limits for drinking and other purposes. However, total hardness (TH), SO4, and NO3 were above stipulated limits in some locations. A nitrate health risk assessment revealed that certain areas present a chronic health risk to children, females, and males due to water intake. However, the dermal absorption route was found to have negligible health risks. SO4 in some locations was above the 100 mg/L Nigerian limit; thus, heightening the potential health effects due to intake of the contaminated water resources. Most samples had low TH values, which exposes users to health defects. There are mixed contamination mechanisms in the area, according to graphical plots, R-mode hierarchical dendrogram, factor analysis, and stoichiometry. However, geogenic mechanisms predominate over human-related mechanisms. Based on the results, a composite diagrammatic model was developed. Furthermore, predictive radial basis function (RBF) and multiple linear regression (MLR) models accurately predicted the TH, SO4, and NO3, with the RBF outperforming the MLR models. Insights from the RBF and MLR models were useful in validating the results of the hierarchical dendrogram, factor, stoichiometric, and graphical analyses.

Hydrogeochemical assessment and health-related risks due to toxic element ingestion and dermal contact within the Nnewi-Awka urban areas, Nigeria.

Awka and Nnewi metropolises are known for intensive socioeconomic activities that could predispose the available groundwater to pollution. In this paper, an integrated investigation of the drinking water quality and associated human health risks of contaminated groundwater was carried out using geochemical models, numerical water quality models, and the HHRISK code. Physicochemical analysis revealed that the groundwater pH is acidic. Predicted results from PHREEQC model showed that most of the major chemical and trace elements occurred as free mobile ions while a few were bounded to their various hydrated, oxides and carbonate phases. This may have limited their concentration in the groundwater; implying that apart from anthropogenic influx, the metals and their species also occur in the groundwater as a result of geogenic processes. The PHREEQC-based insights were also supported by joint multivariate statistical analyses. Groundwater quality index, pollution index of groundwater, heavy metal toxicity load, and heavy metal evaluation index revealed that 60-70% of the groundwater samples within the two metropolises are unsuitable for drinking as a result of anthropogenic influx, with Pb and Cd identified as the priority elements influencing the water quality. The HHRISK code evaluated the ingestion and dermal exposure pathway of the consumption of contaminated water for children and adult. Results revealed that groundwater from both areas poses a very high chronic and carcinogenic risk from ingestion than dermal contact with the children population showing greater vulnerability. Aggregated and cumulative HHRISK coefficients identified Cd, Pb, and Cu, to have the highest health impact on the groundwater quality of both areas; with residents around Awka appearing to be at greater risks. There is, therefore, an urgent need for the adoption of a state-of-the-art waste management and water treatment strategies to ensure safe drinking water for the public.

Incorporation of information entropy theory, artificial neural network, and soft computing models in the development of integrated industrial water quality index.

Keeping purpose and targeted end-users in perspective, several water quality indices have been developed over the past decades to summarily convey water quality information to decision-makers and the general public. Industrial water quality is often analyzed based on the corrosion and scaling potentials (CSPs) of water. The commonly used CSP index parameters are chloride-sulfate mass ratio, Langelier index, Larson-Skold index, aggressive index, Ryznar stability index, and Puckorius scaling index. Simultaneous application of these index parameters often classifies a sample into multiple water quality categories, thereby introducing bias in assessment and decision-making. No previous numerical model integrated the CSP indices to provide a single, composite index value for a more unbiased interpretation of industrial water quality. Therefore, this paper proposes an integrated industrial water quality index (IIWQI) that integrates the six CSP index parameters for direct and concise assessment of industrial water resources. To achieve its aim, this research incorporated information entropy theory and soft computing techniques. The developed IIWQI was applied to water samples from southeastern Nigeria. Different classification groups were observed based on the six CSP indices. However, the IIWQI summarized the classifications of the water samples into three categories: Class 1 (28.57%, slight-medium corrosivity, significant scaling potential); Class 2 (46.43%, medium-high corrosivity, no scaling); and Class 3 (25.00%, high-very high corrosion, no scaling). Correlation analysis revealed the relationships between the physicochemical variables, CSP index parameters, IIWQI, and the entropy-based variability of the IIWQI. The spatiotemporal water quality groups were revealed by Q-mode hierarchical dendrograms. Multiple linear regression and two multilayer perceptron neural networks accurately predicted the IIWQI. The findings of this paper could help in better evaluation, interpretation, and management of industrial water quality.

Combining data-intelligent algorithms for the assessment and predictive modeling of groundwater resources quality in parts of southeastern Nigeria.

Machine learning algorithms have proven useful in the estimation, classification, and prediction of water quality parameters. Similarly, indexical modeling has enhanced the evaluation and summarization of water quality. In Nigeria, works that have incorporated machine learning modeling in water quality analysis are scarce. Although studies across the globe have utilized overall index of pollution (OIP) and water quality index (WQI), works that have simulated and predicted them using machine learning algorithms seem to be scarce. Studies have not simulated nor predicted OIP. In this paper, several physicochemical parameters were analyzed and used for groundwater quality modeling in southeastern Nigeria based on integrated data-intelligent algorithms. Standard methods were followed in all the analysis and modeling performed in this work. OIP and WQI were computed, and their results revealed that 80% of the groundwater resources are suitable for drinking whereas 20% are highly polluted and unsuitable. Pearson's correlation analysis and R-mode hierarchical clustering revealed the possible sources of contamination. Meanwhile, agglomerative Q-mode hierarchical clustering and K-means (partitional) clustering were used to show the spatial demarcations of water quality in the area. Both clustering algorithms identified two main water quality classes-the suitable and unsuitable classes. Furthermore, multiple linear regression (MLR) model and multilayer perceptron neural networks (MLP-NN) were used for the estimation and prediction of the water quality indices. With low modeling errors, both MLR and MLP-NN showed very strong predictions, as their determination coefficient ranged between 0.999 and 1.000. However, MLR slightly outperformed the MLP-NN in the prediction of OIP. The findings of this paper would enhance sustainable water management in the study region and also contribute great insights to the national and global water quality prediction literatures.

Modeling the impact of potentially harmful elements on the groundwater quality of a mining area (Nigeria) by integrating NSFWQI, HERisk code, and HCs.

With excess potentially harmful elements (PHEs), drinking water is marked unsuitable and could pose some health risks when ingested or absorbed by humans. Different age groups are exposed to varied risk levels of PHEs. Analyzing the health risks of PHEs for several age groups could provide detailed insights for effective water resources management. No known study in Ameka Pb-Zn mine province (Nigeria) investigated the health risks of PHEs in water resources for several age groups. Therefore, in this paper, the carcinogenic and non-carcinogenic health risks (due to ingestion and dermal contact) of PHEs in groundwater resources of this area were investigated for nine age groups. To achieve its aim, this study integrated novel HERisk code, NSFWQI (national sanitation foundation water quality index), and hierarchical clusters (HCs) in modeling the groundwater quality. Standard elemental composition analysis revealed that the groundwater is polluted with PHEs. The NSFWQI indicated that 15% of the analyzed water samples have moderate water quality whereas 85% are unsuitable for drinking. The HERisk code, which considered nine age groups (1 to < 2 years, 2 to < 3 years, 3 to < 6 years, 6 to < 11 years, 11 to < 16 years, 16 to < 18 years, 18 to < 21 years, 21 to < 65 years, and > 65 years), revealed that all the samples pose high chronic and cancer risks to all the age groups due to oral ingestion. However, it was realized that age groups 1 to < 16 and > 65 are posed with higher risks than age groups 18 to < 65. Overall, it was realized that all the age groups are far more exposed to ingest or absorb Se, Co, Cd, Se, As, Ni, and Pb than Cu, Fe, and Zn. Nevertheless, the health risks due to dermal absorption are far lower than the risks due to oral ingestion. Conclusively, children and aging people are more predisposed to the health threats than middle-aged populations. HCs and geospatial maps aided the spatiotemporal analysis of the groundwater quality.

Data-driven soft computing modeling of groundwater quality parameters in southeast Nigeria: comparing the performances of different algorithms.

In recent decades, the simulation and modeling of water quality parameters have been useful for monitoring and assessment of the quality of water resources. Moreover, the use of multiple modeling techniques, rather than a standalone model, tends to provide more robust and reliable insights. In this present paper, several soft computing techniques were integrated and compared for the modeling of groundwater quality parameters (pH, electrical conductivity (EC), total dissolved solids (TDS), total hardness (TH), modified heavy metal index (MHMI), pollution load index (PLI), and synthetic pollution index (SPI)) in Ojoto area, SE Nigeria. Standard methods were employed in the physicochemical analysis of the groundwater resources. It was found that anthropogenic and non-anthropogenic activities influenced the concentrations of the water quality parameters. The PLI, MHMI, and SPI revealed that about 20-25% of the groundwater samples are unsuitable for drinking. Simple linear regression indicated that strong agreements exist between the results of the water quality indices. Principal component and Varimax-rotated factor analyses showed that Pb, Ni, and Zn influenced the judgment of the water quality indices most. Q-mode hierarchical and K-means clustering  algorithms grouped the water samples based on their pH, EC, TDS, TH, MHMI, PLI, and SPI values. Multiple linear regression (MLR) and artificial neural network (ANN) algorithms were used for the simulation and prediction of  the pH, EC, TDS, TH, PLI, MHMI, and SPI. The MLR performed better than the ANN model in predicting EC, TH, and TDS. Nevertheless, the ANN model predicted the pH better than the MLR model. Meanwhile, both MLR and ANN performed equally in the prediction of PLI, MHMI, and SPI.

Prediction modeling of potentially toxic elements' hydrogeopollution using an integrated Q-mode HCs and ANNs machine learning approach in SE Nigeria.

Machine learning techniques have proven to be very useful in environmental and engineering assessments, including water quality studies. This is because they have flexible linear and nonlinear forecasting functions that can efficiently and reliably estimate measurable and continuous variables. The aim of this paper was to classify the water quality and also predict potentially toxic anions (PTAs; e.g., Cl, SO4, HCO3, and NO3) and potentially toxic heavy metals (PTHMs; e.g., Fe, Zn, Ni, Cr, and Pb) in water resources in Ojoto and its surroundings, Nigeria. Q-mode hierarchical clusters (HCs) and artificial neural networks (ANNs) were integrated to achieve the research objectives. Prior to the HCs and ANNs modeling, correlation-, unrotated principal component-, and varimax-rotated factor analyses were performed to flag the level of associations between the input water quality variables. With respect to pH, two water quality cluster groups were identified. However, three and four cluster groups were identified based on the PTAs and PTHMs concentrations, respectively. Four ANN models (two for each group) were used for predicting the PTAs and PTHMs in the waters resources. Using coefficient of determination (R2) and AUC (area under curve) values and direct comparison of parity plots, the performance and accuracy of the ANN models were substantiated. Overall, the results obtained reveal that the proposed ANN models suitably predicted the concentrations of the PTAs and PTHMs. Thus, this paper provides useful information for better monitoring, management, and protection of the water resources. However, more modeling studies are encouraged to validate and/or improve the findings of the current work.

Appraising drinking water quality in Ikem rural area (Nigeria) based on chemometrics and multiple indexical methods.

The continuous deterioration of drinking water quality supplies by several anthropogenic activities is a serious global challenge in recent times. In this current study, the drinking water quality of Ikem rural agricultural area (southeastern Nigeria) was assessed using chemometrics and multiple indexical methods. Twenty-five groundwater samples were collected from hand-dug wells and analyzed for physicochemical parameters such as pH, major ions, and heavy metals. The pH of the samples (which ranged between 5.2 and 6.7) indicated that waters were slightly acidic. Cations and anions (except for phosphate) were within their respective standard limits. Except for Mn, heavy metals were also found to be below their maximum allowable limits. Factor analysis identified both geogenic processes and anthropogenic inputs as possible origins of the analyzed physicochemical parameters. Modified heavy metal index, geoaccumulation index, and overall index of pollution revealed that all the hand-dug wells were in excellent condition, and hence safe for drinking purposes. However, pollution load index, water quality index (WQI), and entropy-weighted water quality index (EWQI) revealed that some wells (about 8-12%) were slightly contaminated, and hence are placed in good water category. A hierarchical cluster analysis (HCA) was performed based on the integration of the WQI and EWQI results. The HCA revealed two major quality categories of the samples. While the first cluster comprises of samples classified as excellent drinking water by both WQI and EWQI models, the second cluster comprises of about 12% samples which were identified as good water by either the WQI or EWQI.