Water Quality Index Research Articles

Water quality assessment using A Novel Iraqi water quality index for Euphrates River between Karbala and Babylon provinces as a case study

تواجه أجزاء كثيرة من العالم مشاكل ندرة المياه بسبب محدودية الموارد المائية تزامنا مع تزايد عدد السكان. الأنهار هي أنظمة حيوية للمياه العذبة والتي تعتبر بالغة الأهمية لاستمرار الحياة. يتناول هذا العمل مراقبة وتقييم نوعية مياه نهر الفرات بين محافظتي كربلاء وبابل لعشرة مواقع بالقرب من تصريف المنشآت الصناعية وتصريف الأراضي الزراعية ومياه الصرف الصحي ومرافق اخرى ، وتم أخذ العينات شهرياً ومن ثم تحويل النتائج إلى موسمين (جاف – رطب). تم إجراء العديد من التحاليل الفيزيائية والكيميائية والميكروبية بناءً على الطرق القياسية. تم قياس المعلمات التالية (الدالة الحامضية, المتطلب البايلوجي للاوكسجين, الأوكسجين المذاب, درجة حرارة الماء,القولونيات الكلية, العسرة الكلية, الكبريتات, النترات, الكلورايد, الصوديوم, الفوسفات, كاربونات الصوديوم المتبقية, نسبة امتزاز الصوديوم, نسبة الصوديوم المذابة, خطورة المغنيسيوم, البورون, النتريت والمغنيسيوم). وباستخدام مؤشر جودة المياه العراقي الجديد الذي يتناسب مع النظم المائية العراقية ويعكس الواقع البيئي للمياه العراقية، يتضمن مؤشر IWQI الجديد المكونات المذكورة أعلاه، وأظهرت النتائج أن نوعية مياه نهر الفرات في المواقع المدروسة تراوحت بين (رديئة - سيئة للغاية) بالنسبة للمياه العذبة أما بالنسبة لملائمة المياه للزراعة والحياة المائية والشرب فقد تراوحت بين (جيد – غير صالح) خلال المواسم الرطبة والجافة. وبناء على هذه النتائج نستنتج أن المنشآت الصناعية ومياه الصرف الصحي في المدن والمجتمعات الكثيفة التي تعيش على طول ضفة النهر تؤثر سلبا على نوعية مياه النهر.

Alcohol ink-modified microfluidic paper-based analytical devices for enhanced white detection in simultaneous determination of multiple water quality indicators.

White detection remains a critical limitation in using colorimetry to determinesubstances with microfluidic paper-based analytical devices (µPADs). Here, we introduced a simple, safe alcohol ink-modified µPAD for the straightforward and facile detection of white color in precipitation reactions. Although absolute alcohol ink was found to cause device leakage, dilution of the ink with water was the key to successfully precoat wax-created µPADs. Device utility was demonstrated through simultaneous detection of sulfate, phosphate, and waterhardness via precipitation reactions. While phosphate interfered with sulfate detection by Ba2+, in situ distance-based quantification of phosphate was implemented. Aside from anions, the modified µPADs could be extended to detect cationic analytes such as total hardness. The limits of detection (LODs) for sulfate, phosphate, and hardness were 0.005mmol L-1, 0.005mmol L-1, and 0.5mmol L-1, respectively, with the linear ranges of 0.01-10.0mmol L-1, 0.005-1.0mmol L-1, and 0.001-0.5mol L-1. The µPADs were applied to real water samples, demonstrating results that were consistent with standard methods at a 95% confidence level. By incorporating white detection, these alcohol ink-modified µPADs offer enhanced versatility for addressing a broader array of analytical challenges in real-world settings.

Surface water quality assessment and probable health threats of metal exposure in the Tano South Municipality, Ahafo, Ghana

The prime goal of this study was to assess the surface water quality and the associated health risks for residents in the Tano South Municipality, Ghana. The WHO drinking water criteria were compared with the findings of an analysis of eight surface waters for parameters such as physiochemical parameters, nutrient levels, and concentrations of selected metals. An evaluation was performed regarding the potential non-carcinogenic and carcinogenic risks associated with metal exposure by oral and dermal absorption. The estimated water quality index indicated that seven water samples were deemed unsuitable for human consumption, while one sample indicated very low water quality. The fluoride levels in all water samples were below the limit of detection, although it guards against dental caries. All of the water samples had mean concentrations of Cd and Fe above WHO guideline values, while one water sample had a Pb concentration that was higher than recommended. Principal component analysis showed that aside from the natural source, human-induced sources such as runoff of excess chemicals and soil erosion from adjacent farm soils were responsible for the substantial levels of contaminants in surface water samples. There was a possibility of non-carcinogenic consequences for children in seven out of eight water samples. However, cancer risk for Cd and Pb was not likely for adults and children in the study area. Findings serve as a representative case study for other districts and call on water managers to treat surface waters to guard against harmful health consequences and safeguard the designated buffer zones.

Performance of Machine Learning, Artificial Neural Network (ANN), and stacked ensemble models in predicting Water Quality Index (WQI) from surface water quality parameters, climatic and land use data

Assessing water quality is essential for managing freshwater resources, safeguarding ecosystems, and guaranteeing public health. Traditional water quality assessment methods suffer from seasonal sampling, multi-parameter requirements, and labor-intensive sampling processes, which are major constraints for the frequent monitoring of vast river basins. To overcome this issue, the study modeled the remote sensing-based climatic and land use parameters with Principal Component Analysis (PCA) to leverage Artificial Neural Networks (ANN) and machine learning (ML) algorithms to predict the Water Quality Index (WQI). The Weighted Arithmetic Water Quality Index (WAWQI) method was used to calculate the WQI of the Godavari River Basin for the available 19 stream water quality parameters (SWQPs). Further, PCA was applied to reduce the dimensionality of the parameters from 19 to 6. These results led to the development of two modeling methods to predict the WQI. In the first method, the correlation-based model was developed to predict WQI by evaluating six SWQPs. The second method, the causal-effect model, uses land use and meteorological factors to determine WQI using causality. Using advanced AutoML techniques, the initial pool of 40 ML models was meticulously evaluated and refined, culminating in the selection of the top three exemplary models such as Extreme Gradient Boosting (XGB), Extra Trees (ET), and Random Forest (RF). In both methods, XGB models show better prediction, with the coefficient of determination (R2) value of 0.95 during training and 0.83 during testing in method one. Whereas in the second method, R2 of 0.93 in training and 0.80 in testing are obtained. Further, XGB, ET, and ANN outputs were stacked with each model to enhance these results in both methods. Among these three stacked models, the stacked ANN_ML model performed better compared to stacked XGB_ML and stacked ET_ML. In the first method, the stacked ANN_ML model predicts R2 values of 0.95 and 0.91 for training and testing. In the second method, 0.95 and 0.90 for training and testing are obtained using stacked ANN_ML model. These findings emphasize the stacked model prediction ability to capture nonlinear relationships in the parameters and the novel approach of land use and climate parameters based WQI prediction, which replace the laborious, time-consuming SWQP measurements.

The evolution of the Canadian (CCME) Water Quality Index

The evolution of the Canadian (CCME) Water Quality Index

A Hybrid Model Combined Deep Neural Network and Beluga Whale Optimizer for China Urban Dissolved Oxygen Concentration Forecasting

The dissolved oxygen concentration (DOC) is an important indicator of water quality. Accurate DOC predictions can provide a scientific basis for water environment management and pollution prevention. This study proposes a hybrid DOC forecasting framework combined with Variational Mode Decomposition (VMD), a convolutional neural network (CNN), a Gated Recurrent Unit (GRU), and the Beluga Whale Optimization (BWO) algorithm. Specifically, the original DOC sequences were decomposed using VMD. Then, CNN-GRU combined with an attention mechanism was utilized to extract the key features and local dependency of the decomposed sequences. Introducing the BWO algorithm solved the correction coefficients of the proposed system, with the aim of improving prediction accuracy. This study used 4-h monitoring China urban water quality data from November 2020 to November 2023. Taking Lianyungang as an example, the empirical findings exhibited noteworthy enhancements in performance metrics such as MSE, RMSE, MAE, and MAPE within the VMD-BWO-CNN-GRU-AM, with reductions of 0.2859, 0.3301, 0.2539, and 0.0406 compared to a GRU. These results affirmed the superior precision and diminished prediction errors of the proposed hybrid model, facilitating more precise DOC predictions. This proposed DOC forecasting system is pivotal for sustainably monitoring and regulating water quality, particularly in terms of addressing pollution concerns.

Experimental Evaluation of Blockage Resistance and Position Caused by Microparticle Migration in Water Injection Wells

Offshore oil field loose sandstone reservoirs have high permeability. However, during the water injection process, water injection blockage occurs, causing an increase in injection pressure, making it impossible to continue injecting water on site. Current research mainly focuses on the factors causing water injection blockage, with less attention given to the blockage locations and the pressure increase caused by water injection. There is a lack of research on the change in the law of injection capacity. This paper establishes a simulation experiment for water injection blockage that can accommodate both homogeneous and heterogeneous cores. The experimental core is 1 m long and capable of simulating the blockage conditions in the near-well zone during water injection, thereby analyzing the core blockage position and blockage pressure. The study clarifies the influence of water quality indicators, heterogeneity, and core length on the blockage patterns in reservoirs during water injection. The research findings are as follows: I. The reservoir blockage samples were characterized using scanning electron microscopy (SEM), casting thin sections, and X-ray diffraction (XRD) analysis. The results indicate that the main factors causing blockage are clay, silt, and fine particulate suspensions, with the fine particles mainly consisting of hydrated silicates and alkali metal oxides. The primary cause of blockage in loose sandstone is identified as the mechanism of migration and accumulation of clay, fine rock particles, and suspended matter in the injected water. II. By monitoring pressure and permeability changes in the core flooding experiments, the impact of reservoir heterogeneity on water injection capacity was evaluated. The evaluation results show that the blockage locations and lengths in heterogeneous cores are twice those in homogeneous cores. III. For heterogeneous reservoirs, if the initial permeability at the inlet is lower than in other segments of the core, significant blockage resistance occurs, with the final resistance being 1.27 times that of homogeneous cores. If the initial permeability at the inlet is higher than in other parts, the final blockage resistance is close to that of homogeneous cores. This study provides theoretical support for the analysis of blockage locations and pressures in loose sandstone water injection and offers technical support for the design of unplugging ranges and pressures after blockage in heterogeneous formations. At the same time, it provides a theoretical basis for selecting the direction of acidizing after blockage occurs in loose sandstone.

Decision Support Framework for Water Quality Management in Reservoirs Integrating Artificial Intelligence and Statistical Approaches

Planning, managing and optimising surface water quality is a complex and multifaceted process, influenced by the effects of both climate uncertainties and anthropogenic activities. Developing an innovative and robust decision support framework (DSF) is essential for effective and efficient water quality management, so it can provide essential information on water quality and assist policy makers and water resource managers to identify potential causes of water quality deterioration. This framework is crucial for implementing actions such as infrastructure development, legislative compliance and environmental initiatives. Recent advancements in computational domains have created opportunities for employing artificial intelligence (AI), advanced statistics and mathematical methods for use in improved water quality management. This study proposed a comprehensive conceptual DSF to minimise the adverse effects of extreme weather events and climate change on water quality. The framework utilises machine learning (ML), deep learning (DL), geographical information system (GIS) and advanced statistical and mathematical techniques for water quality management. The foundation of this framework is the outcomes from our three studies, where we examined the application of ML and DL models for predicting water quality index (WQI) in reservoirs, utilising statistical and mathematical methods to find the seasonal trend of rainfall and water quality, exploring the potential connection between streamflow, rainfall and water quality, and employing GIS to show the spatial and temporal variability of hydrological parameters and WQI. Three potable water supply reservoirs in the Toowoomba region of Australia were taken as the study area for practical implementation of the proposed DSF. This framework can serve as a comprehensive mechanism to identify distinct seasonal characteristics and understand correlations between rainfall, streamflow and water quality. This will enable policy makers and water resource managers to enhance their decision making processes by selecting the management priorities to safeguard water quality in the face of future climate variability, including prolonged droughts and flooding.

Impact of COVID-19 lockdown on water quality of major rivers in Sri Lanka

ABSTRACT The COVID-19 lockdown resulted in a reduction in human activities, lowering pollution levels in these rivers. Nevertheless, limited research can be found on the impact of COVID-19 on river water quality in Sri Lankan rivers. Therefore, this research was carried out to investigate the water quality index (WQI) of four major rivers (Mahaweli, Nilwala, Kelani, and Kalu) in Sri Lanka in three consecutive time slots spanning from 2019 to 2022 (before, during, and after the lockdown). In-depth WQI analysis has unveiled nuanced dynamics in river health. While the lockdown period contributed to positive alterations in key parameters, subsequent periods demonstrated declining water quality post-lockdown. This decline underscores the direct correlation between human activity and river water quality deterioration. Several parameters showed positive changes during the lockdown, indicating an improvement in river water quality. When comparing the periods before, during, and after the lockdown, pH, colour, turbidity, total iron, sulphate, chloride, total coliform, and E. coli all showed a significant positive impact. However, some parameters, such as fluoride and electrical conductivity (EC), had a neutral effect. This study sheds light on the positive effects of the COVID-19 lockdown on reducing river pollution in Sri Lanka.

Enhancing local-scale groundwater quality predictions using advanced machine learning approaches

Assessing groundwater quality typically involves labor-intensive, time-consuming, and costly laboratory tests, making real-time monitoring impractical, especially at the local level. Groundwater quality projections at the local scale using broad spatial datasets have been inaccurate due to variations in hydrogeology, human activities, industrial operations, groundwater extraction, and waste disposal. This study aims to identify the most dependable and resilient machine learning algorithms for forecasting groundwater quality at nearby monitoring locations by utilizing simple water quality metrics that can be quickly assessed without extensive sampling and laboratory testing. The Entropy-weighted Water Quality Index (EWQI) was calculated using a large spatial and temporal dataset (2014–2021) of 977 wells with parameters including pH, total hardness (TH), calcium (Ca2⁺), magnesium (Mg2⁺), sodium (Na⁺), potassium (K⁺), sulfate (SO₄2⁻), chloride (Cl⁻), nitrate (NO₃⁻), total dissolved solids (TDS), and fluoride (F⁻). Further, similar parameters were also observed in 33 open wells at the three local monitoring sites from December 2022 to March 2023. The EWQI was predicted using a Random Forest (RF), eXtreme Gradient Boosting (XGB), and Deep Neural Network (DNN). The pH, TH, and TDS were used as input variables for EWQI predictions, as they can be easily measured using handheld probes or multi-parameters. The model performance was evaluated using R2, MAE, and RMSE. During the training stage, all three models predicted the EWQI with an R2 greater than 90%, with minimal errors when pH, TH, and TDS were input variables. To validate the models at a local scale, the EWQI was predicted at the village level (e.g., Antoli, Balapura, and Lapodiaya) using pH, TH, and TDS as input variables. The machine learning models were able to predict the EWQI very closely to the actual EWQI, with an R2 greater than 90%. It is also evident that the models could predict the EWQI using basic parameters that are easily measured, providing an overall idea of the water quality for a small area. Hence, these machine learning models could be useful for accurately representing groundwater quality, thereby avoiding the use of time-consuming and costly laboratory techniques.

Evaluation and pollution analysis of water environment of state-controlled river in Zaozhuang City from 2016 to 2022

The quality of water environment is closely linked to the survival and development of human beings. Thanks to the Water Pollution Prevention and Control Action Plan, the quality of the water environment has improved significantly. However, challenges remain in the surface water environment due to human activities in the basin. We analyze the surface water quality of the six state-controlled rivers in Zaozhuang City, which are key tributaries to the Nansi Lake and the water storage and distribution area of the South-to-North Water Diversion East Project. Physical-chemical parameters and metal pollutants were detected from 2016 to 2022. The Various indices were used for evaluating the surface water environmental quality and pollution issue. Although there were significant inter-year differences in each river, the results of Water quality index and Nemerow composite index analysis indicated that the water quality of the six rivers has continuously improved over the years. Nevertheless, as this research reports, such as considerable annual fluctuations in pollution factors, obvious pollution characteristics in river basins, and difficulty in controlling non-point source pollution, which still restrict the further improvement of the water environment. Each river presents various water environment problems due to differences in industrial structures within its basin. Through the analysis of production and lifestyle in each basin, the main pollution sources of each river were evaluated and determined. Based on the type and characteristics of pollution sources, control measures and optimization strategies are proposed for the improvement of the water environment.

Domestic and irrigation water quality on the southern slopes of Mount Kilimanjaro

This study assessed the water quality for drinking and irrigation purposes on the southern slopes of Mt. Kilimanjaro during the dry season under low flow conditions. Fifty-one samples covering eight different water sources (i.e., stream water from natural and anthropogenic impacted streams, domestic water, spring water, rainfall, groundwater, lake water and water from irrigation canals) were collected in a snapshot sampling campaign over 10 days in February 2023. First, physical, chemical and biological parameters were analysed and compared with Tanzanian and international drinking and irrigation water quality requirements. The samples were then ranked according to their suitability for drinking and/or irrigation using water quality indices (WQI). All drinking water quality parameters except for E. coli and turbidity were within the permissible limits. A generalised problem of faecal contamination was found in the study area, including in domestic water, highlighting the need to identify sources of contamination and remediate them before distribution. The drinking water quality index (DWQI) classified 89% of the samples as unsuitable and 11% as excellent for drinking. Irrigation water quality parameters were within the guidelines of restriction of use except for pH in 5 samples. In contrast to the DWQI, the vast majority of the water samples (88%) can be used for irrigation without restrictions according to the irrigation water quality index (IWQI). The suitability of water for irrigation was also assessed using three indices, i.e., Kelley’s Index, Soluble Sodium Percentage and Magnesium Ratio, which indicated potential problems with excess of sodium (about 30% of the samples) and magnesium (about 20%). Further studies combining suitability indices, soil characteristics and crop types are recommended to assess water quality for irrigation use.

Real-time water quality monitoring along the lower stretch of River Ganges and its connected drains using sensors and Water Quality Index

ABSTRACT In this study, water quality is measured using a Real-Time Water Quality Monitoring System for a total of 84 times at 14 locations, in which four drains discharged sewage directly to river Ganges at Bihar, five locations on river Ganges at West Bengal, two tributaries of river Ganges at West Bengal and three drains discharged wastewater directly to river Ganges at West Bengal. In Bihar, four major drains discharged 377.98 MLD wastewater into the river Ganges which in turn released 8985.17 kg of BOD per day. In West Bengal, three major drains had a total flow of 1630.88 MLD that discharged 11563.77 kg of BOD per day to the River Ganges. The average Water Quality Index of the river Ganges was observed as 64.55 and that of drains of West Bengal and Bihar were recorded as 309.78 and 775.56, respectively. The average BOD to COD ratio of less than 0.6 indicated wastewater from drains of Bihar and West Bengal was nonbiodegradable. DO and pH values were recorded compliant with the bathing water quality standard at all river locations, however, the average BOD value at five monitoring points of the river Ganges and its tributaries was slightly above the bathing water quality standard.

Assessment of Groundwater Quality Using Water Quality Indices in Illegal Mining Communities: A Case Study of the Atwima-kwanwoma District and Obuasi East Metropolis, Ghana

This study investigated groundwater quality in illegal mining zones within the Atwima-Kwanwoma District and Obuasi East Metropolis of the Ashanti Region, Ghana, employing both the Canadian Council of Ministers of the Environment Water Quality Index (CCME-WQI) and Nemerow's Pollution Index (NPI). The analysis revealed severe contamination across multiple parameters, including heavy metals, microbial indicators, and physicochemical parameters. The CCME-WQI values for the five towns consistently indicated "Poor" water quality, ranging from 26.8 to 31.1, reflecting significant deviations from acceptable water quality standards. Notably, Town A exhibited a cyanide concentration of 11.25 mg/L, while Town B recorded lead levels at 118.73 μg/L, both far exceeding permissible limits set by health authorities. The presence of Escherichia coli further exacerbates health risks, underscoring the urgent need for improved water treatment and management practices. This study demonstrates that the integrated use of NPI and CCME-WQI provides a comprehensive assessment of groundwater quality, revealing significant environmental and public health challenges. Immediate intervention, including regulatory enforcement, sustainable mining practices, and remediation strategies, is crucial to safeguard groundwater resources. The findings contribute uniquely to the understanding of water quality dynamics in mining-affected regions and advocate for a coordinated approach to mitigate environmental degradation.

Chironomid Pupal Exuviae Technique in Ecological Research of Man-Made Water Bodies

Reservoirs serve functional purposes such as irrigation and power generation. However, concerns are raised due to the alterations of the connected riverine ecosystems. Chironomidae (Diptera), a diverse aquatic macroinvertebrate group, are vital to the functioning of ecosystems and serve as water quality indicators. Their holometabolous development includes the pupal stage after four larval stages. The chironomid pupal skin (exuvia) is used in environmental assessments, where the Chironomid Pupal Exuvial Technique (CPET) is a recognized standard. The CPET method is adaptable to different freshwater environments and here was applied in the study of 28 man-made lakes in the Pannonian Lowlands and Dinaric Western Balkan Ecoregion in Croatia to obtain information on chironomid diversity and analyze the potential influence of environmental factors on the chironomid community. The lake surface was skimmed with an exuvial hand net (mesh size of 300 µm) along the lake edge with a transect length of 10 m in the area of accumulated debris of organic and inorganic matter. Individual exuviae were mounted in a Berlese mounting medium and identified by morphological characteristics to the lowest taxonomic level. During the study, 5698 chironomid pupal skins were collected, and 141 taxa (including 97 species) belonging to five subfamilies were identified. The tribe Tanytarsini comprised 40% of the identified taxa, with Paratanytarsus spp. being the most abundant. In the Dinaric ecoregion, Paratanytarsus bituberculatus dominated, while Microchironomus tener and the genus Cricotopus were the dominant taxa in the Pannonian ecoregion. Community structure in the Pannonian ecoregion was influenced by total organic carbon (TOC) and orthophosphates (PO43−), indicating higher anthropogenic pressure compared to the Dinaric ecoregion, where water conductivity influenced Chironomidae assemblages. The research has provided valuable and useful information on the chironomid diversity in man-made and highly altered water bodies, as some of the most vulnerable aquatic habitats to anthropogenic influence. The CPET method could be a useful tool for the ecological studies and bioassessment of water quality in Croatia.

Long-time prediction of multi-indicator water quality based on the improved WaveNet under time series decomposition and phase space reconstruction

Abstract Long–time prediction of water quality indicator such as chlorophyll–a (Chl–a) is crucial for water process engineering and environmental management. In order to capture the characteristics of long–time series and reduce the limitations of traditional long–time prediction strategies, this paper proposes a novel hybrid model by combining data decomposition, phase space reconstruction, feature fusion and improved WaveNet. Firstly, the original data is decomposed into several subsequences through time series decomposition. Then, the subsequences with chaotic characteristics are integrated with multiple features for phase space reconstruction. Next, the decomposed and reconstructed subsequences are fed back into the improved WaveNet model separately. Finally, the prediction results are obtained by summing the predicted values of the subsequences. In this paper, the reliability of the method is assessed using the dissolved oxygen, water temperature, pH and Chl–a data of a monitoring station in the Beihai coastal sea area, ablation experiments are conducted to demonstrate the effectiveness of each module in the proposed model, and comparisons with multiple benchmark and hybrid models show that the proposed model exhibits better performance in long–time prediction of coastal water quality in the next fourteen days.

Prediction of urban surface water quality scenarios using hybrid stacking ensembles machine learning model in Howrah Municipal Corporation, West Bengal

In the pursuit of understanding surface water quality for sustainable urban management, we created a machine learning modeling framework that utilized Random Forest (RF), Cubist, Extreme Gradient Boosting (XGB), Multivariate Adaptive Regression Splines (MARS), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), and their hybrid stacking ensemble RF (SE-RF), as well as stacking Cubist (SE-Cubist), to predict the distribution of water quality in the Howrah Municipal Corporation (HMC) area in West Bengal, India. Additionally, we employed the ReliefF and Shapley Additive exPlanations (SHAP) methods to elucidate the underlying factors driving water quality. We first estimated the water quality index (WQI) to model seven water quality parameters: total hardness (TH), pH, total dissolved solids (TDS), dissolved oxygen (DO), biochemical oxygen demand (BOD), calcium (Ca), magnesium (Mg). Then six independent factors were utilized (i.e. Precipitation (Pr), Maximum Temperature (Tmax), Minimum Temperature (Tmin), Normalized Difference Turbidity Index (NDTI), Normalized Difference Chlorophyll Index (NDCI), and Total Dissolved Solids (TDS)) for predicting the WQI mapping through the different ML models. This study demonstrated that the SE-Cubist model outperforms other ML models. During the testing phase, it achieved the best modeling results with an R2 = 0.975, RMSE = 0.351, and MAE = 0.197. The ReliefF and SHAP analyses identified Pr and Tmax as the most significant factors influencing WQI within the study area.

Performance of artificial intelligence model (LSTM model) for estimating and predicting water quality index for irrigation purposes in order to improve agricultural production.

The primary goal of this study is to predict the current and future water quality index for irrigation (WQII) of the western Mitidja alluvial aquifer in northern Algeria. The modified WQII was used to evaluate groundwater suitability for irrigation through geographic information system (GIS) techniques. Additionally, a long short-term memory (LSTM) model was employed to calculate the WQII and map future groundwater quality, considering factors like overexploitation, anthropogenic pollution, and climate change. Two scenarios were analyzed for the year 2030. Results from applying the modified WQII model to 2020 data showed that about 83% of the study area has medium to high groundwater suitability for irrigation. The LSTM model exhibited strong predictive accuracy with determination coefficients (R2) of 0.992 and 0.987, and root mean square error (RMSE) values of 0.061 and 0.084 for the training and testing phases, respectively. For the first 2030 scenario, the area with low and medium groundwater suitability is expected to increase by 4% and 7% compared to the 2020 map. Conversely, under the second scenario, groundwater quality is predicted to improve, with a decrease of 14% and 11% in the low and medium suitability areas. The combination of the modified WQII and LSTM model proves to be an effective tool for estimating and predicting water quality indices in similar regions globally, offering valuable insights for water resource management and decision-making processes.

Modelling water quality parameters using model tree, random forest, and non-linear regression for Mula-Mutha River, Pune, India.

Evaluation of vital water-quality indicators, especially biological and chemical demand of oxygen (BOD and COD), is important for environmental factors, human health, and agricultural output. In the recent past, data-driven techniques (DDT) offer the ability to automate water quality assessment with more reliable and rapid evaluation. The present study thus aims to utilize various DDTs: random forest (RF), model tree (MT), and non-linear-regression (NLR) to predict vital water quality indicators such as BOD and COD for the three stretches of Mula-Mutha River, Pune, India. Since the river has three stretches: Mutha, Mula, and Mula-Mutha respectively, BOD-COD models have been developed separately for each using MT, RF, and NLR. Data analysis using a violin diagram is done to understand the data characteristics. Further, the models developed were developed using the appropriate input parameters for predicting BOD and COD. Error measures including coefficient of correlation (R), mean absolute error (MAE), and root mean square error (RMSE) were used to evaluate the constructed models. The Taylor diagram, scatter plot, and hydrograph were also used for visual performance analysis. The findings suggest that the MT and RF techniques exhibit a stronger connection between the actual and anticipated levels of BOD and COD, with NLR following closely behind. Practical acceptance of these approaches is increased by RF in the form of trees, MT with an output in the form of a sequence of equations, and NLR with a single equation. These findings help us gain insight into DDT's water quality assessment model, which will also help future researchers and water quality professionals make decisions.

Identifying groundwater characteristics and controlling factors in Jiaozhou Bay’s northern coastal region, China: a combined approach of multivariate statistics, isotope analysis, and field empirical investigations

Explicit identification of hydrochemical processes and their controlling factors within groundwater systems is critical for the sustainable utilization of water resources in coastal urban areas. This study was undertaken in the North Coastal Region of Jiaozhou Bay (NCRJB), located in the eastern part of Shandong Province, China, an area grappling with significant issues of groundwater quality degradation and water scarcity. A total of 105 groundwater samples and 34 surface water samples, collected from 2020 to 2024, were analyzed and studied using various hydrogeological tools, multivariate statistical analyses, and water quality assessment methods. These include the Piper diagram, hydrochemical facies evolution diagram (HFE-D), Principal Components Analysis (PCA), correlation analysis, stable isotope analysis, Water Quality Index (WQI), and USSL diagrams. The results indicated that all surface water and pore groundwater samples were categorized as Na-Cl type, exhibiting high Total Dissolved Solids (TDS) and Electrical Conductivity (EC) values, characteristics that render them poor to unsuitable for drinking and irrigation purposes. The fracture groundwater is predominantly of the Ca-Na-Cl mixed type, with average suitability for irrigation and a limited proportion (22.5%) deemed suitable for drinking. Seawater intrusion, primarily through the surface water system, and the impact of human activities were identified as the predominant controlling factors con-tributing to the degradation of the local groundwater environment. Field empirical investigations further validated the results derived from hydrogeological assessments, multivariate statistical analyses, and isotopic approaches. The long-term shifts in hydrochemical properties, along with the latent threat of seawater intrusion, exhibit an upward trend during the dry season and show a certain degree of mitigation during the wet season. This study highlights that field investigations, in conjunction with hydrochemical tools, multivariate statistical analyses, and stable isotope analysis, can successfully furnish reliable insights into the predominant mechanisms governing regional groundwater evolution within the context of long-term and intricate envi-ronmental settings.