Groundwater Quality Classification Research Articles

Classification of Groundwater Quality for Irrigation Purposes in Wetland Region by Irrigation Water Quality Index

Classification of Groundwater Quality for Irrigation Purposes in Wetland Region by Irrigation Water Quality Index

Improving the efficiency of water use in agriculture by modelling the classification of groundwater quality

This study investigates the potential of machine learning for classifying groundwater quality in Telangana, India, to optimize water resource utilization in agriculture. The study aims to develop and evaluate a decision tree model capable of accurately predicting groundwater quality based on chemical composition data. The objective is to identify key factors influencing water quality and provide insights for improving water management practices and enhancing agricultural productivity. The study utilizes a dataset of groundwater quality parameters collected over three years (2018-2020) and employs a decision tree algorithm for model development. The results demonstrate the effectiveness of the model, achieving an accuracy of 95.7%. The analysis highlights the significance of sodium content, dissolved salts ratio, total dissolved solids, and total water hardness as key factors influencing groundwater quality. This research underscores the potential of machine learning for enhancing water resource management in agriculture and suggests further exploration of temporal dynamics, predictive modeling, and broader geographic application to further refine and extend the model’s impact.

Machine Learning For Groundwater Quality Classification: A Step Towards Economic and Sustainable Groundwater Quality Assessment Process

Machine Learning For Groundwater Quality Classification: A Step Towards Economic and Sustainable Groundwater Quality Assessment Process

The Application of Modified K-Nearest Neighbor Algorithm for Classification of Groundwater Quality Based on Image Processing and pH, TDS, and Temperature Sensors

The limited availability of water in remote areas makes rural communities pay less attention to the water quality they use. Water quality analysis is needed to determine the level of groundwater quality used using the Modified K-Nearest Neighbor Algorithm to minimize exposure to a disease. The data used in this study was images combined with sensor data obtained from pH (Potential of Hydrogen), TDS (Total Dissolved Solids) sensors and Temperature Sensors. The test used the Weight voting value as the highest class majority determination and was evaluated using the K-Fold Cross Validation and Multi Class Confusion Matrix algorithms, obtaining the highest accuracy value of 78% at K-Fold = 2, K-Fold = 9, and K- Fold = 10. Meanwhile, the results of testing the effect of the K value obtained the highest accuracy value at K = 5 of 67.90% with a precision value of 0.32, 0.37 recall, and 0.33 F1-Score. From the results of the tests carried out, it can be concluded that most of the water conditions are suitable for use.

Effective Groundwater Quality Classification Using Enhanced Whale Optimization Algorithm with Ensemble Classifier

Effective Groundwater Quality Classification Using Enhanced Whale Optimization Algorithm with Ensemble Classifier

Geospatial mapping and suitability classification of groundwater quality for agriculture and domestic uses in a Precambrian basement complex

Application of groundwater for domestic and agricultural uses has increased in sub-Sahara Africa. However, geology and anthropogenic activities can impact groundwater quality. But information on quality evaluation and suitability classification of groundwater based on water quality index (WQI) is limited. Thus, this study evaluated the spatial variability of groundwater quality and its suitability for potable and irrigation purposes in a Precambrian complex of southwest Nigeria. Water samples were collected from 40 wells across the study area and analyzed for physicochemical properties. Suitability for domestic and irrigation uses were determined. Maps showing spatial variations of pH, electrical conductivity (EC), total dissolved solid (TDS), total hardness (TH), cations (Ca2+, Mg2+, Na+, and K+), anions (SO42−, Cl−, NO3−-N, PO3−-P, B−, F−, and HCO3−) and irrigation water quality index (IWQI) and drinking water quality index (DWQI)) were produced using ArcGIS. The average values of pH, EC, TDS and TH were 6.6, 0.3 dS m−1, 152.4 mg L−1, and 208.7 mg L−1, respectively. The concentrations of Ca2+, Mg2+, K+ and Na+ were 28.7, 32.8, 2.49, and 7.13 mg L−1, respectively, whereas SO42−, Cl−, NO3−-N, PO3−-P, B−, F−, and HCO3− concentrations were 20.4, 0.32, 0.46, 0.04, 0.39, 0.42, and 230.7 mg L−1, respectively. The quality indices for irrigation (IWQI) and drinking (DWQI) were 0.22 and 0.75, respectively. The IWQI significantly correlated with Mg2+, TH, SO42−, pH and TDS (P ≤ 0.05, r = 0.34–0.66), whilst DWQI significantly correlated with TDS, SO42−, Cl−, NO3−-N, PO3−-P, Ca2+, Mg2+, pH, TH, and F− (P ≤ 0.05, r = 0.38–0.93). The suitability classification of the groundwater quality in the area shows that 100% and 78% of the water are safe for irrigation and domestic purposes, respectively. However, regular quality monitoring of the groundwater is recommended in order to avert likely deterioration indicated by some quality parameters.

Appraisal of water quality and hydro-geochemistry of groundwater quality classification for drinking and irrigation in and around of Nagalapura Taluk, Bellary District Karnataka, India

Appraisal of water quality and hydro-geochemistry of groundwater quality classification for drinking and irrigation in and around of Nagalapura Taluk, Bellary District Karnataka, India

A Novel Approach for Indexing Heavy Metals Pollution to Assess Groundwater Quality for Drinking Purposes

The present study proposes a new approach for indexing heavy metals ions to examine groundwater quality in North Kurdufan Province, Sudan. The new approach is developed based on the most frequently used methods for indexing heavy metals pollution in water. It is created in order to avoid the weaknesses of the current indexing systems. As per the new indexing approach, heavy metal contamination in water samples is evaluated by two types of indices: the negative evaluation index (NEI) and positive evaluation index (PEI). The water worthiness is assessed based on a pair of indices, NEI and PEI. Water quality increases with the decrease of PEI and NEI values. NEI indicates the contribution of heavy metals with a concentration not exceeding the highest desirable limit () in the water sample, while vice versa regarding the PEI. If all heavy metals concentrations in the water sample do not exceed , the sum of NEI should be less than zero, but not less than −100, implying that the sum of PEI will be zero. When all heavy metals concentration exceeds , the sum of NEI should be equal to zero, and PEI will be greater than zero. The results of the newly proposed approach have been discussed and compared with the existing indexing methods as regards to the best and worst samples. The spatial distribution of NEI and PEI are in complete agreement with the metals spatial distribution. The comparison result showed that the new index is robust, with fair calculations, and gives the best classification of groundwater quality.

A Simple Approach of Groundwater Quality Analysis, Classification, and Mapping in Peshawar, Pakistan

Groundwater is an important source of water for drinking, agriculture, and other household purposes, but high population growth, industrialization, and lack of oversight on environmental policies and implementation have not only degraded the quality but also stressed the quantity of this precious source of water. Many options existed, but this study evaluated, classified, and mapped the quality of groundwater used for potable consumption with a simple approach in an urban area (Peshawar valley) of Pakistan. More than 100 groundwater samples were collected and analyzed for physio-chemical parameters in a laboratory. Hierarchal clustering analysis (HCA) and classification and regression tree (CART) analysis were sequentially applied to produce potential clusters/groups (groundwater quality classes), extract the threshold values of the clusters, classify and map the groundwater quality data into meaningful classes, and identify the most critical parameters in the classification. The HCA produced six distinct potential clusters. We found a high correlation of electrical conductivity with t o t a l h a r d n e s s ( R 2 = 0.72 ), a l k a l i n i t y ( R 2 = 0.59 ) and c h l o r i d e ( R 2 = 0.64 ) , and, t o t a l h a r d n e s s with c h l o r i d e ( R 2 = 0.62), and a l k a l i n i t y ( R 2 = 0.51). The CART analysis conclusively identified the threshold values of the six classes and showed that t o t a l h a r d n e s s was the most critical parameter in the classification. The majority of the groundwater was either with worse quality or good quality, and only a few areas had the worst groundwater quality. This study presents a simple tool for the classification of groundwater quality based on several aesthetic constituents and can assist decision makers develop and support policies and/or regulations to manage groundwater resources.

Health-Risk Assessment of Arsenic and Groundwater Quality Classification Using Random Forest in the Yanchi Region of Northwest China

High-arsenic (As) groundwater was first discovered in the Yanchi region, Northwest China, which is an arid or semiarid area, and the groundwater quality seriously affects the health of local residents. A comprehensive understanding of the spatiotemporal distribution characteristics, water quality, and health risk of high-As groundwater is indispensable for the sustainable utilization of groundwater sources and resident health. Seventy-nine groundwater samples were collected from different aquifers and seasons. The hazard quotient (HQ) and carcinogenic risk (CR) of As for adults and children were assessed. Moreover, the effects of groundwater sampling site and seasonal change on As concentration were investigated. Then, the random forest method was used to evaluate the importance of the indicators and the influence of these important indicators on groundwater classification. Thirty-three percent of the groundwater samples had HQ values > 1, and the CR values of all groundwater > 1.00 × 10−6 for children, representing a serious health risk. Twenty-one percent of the groundwater samples had health risk for adult. High-As groundwater is present at depths less than 60 m, and groundwater As concentrations are slightly affected by seasonal changes. The random forest shows that the most important indicators that affect groundwater quality are Na, TDS, TH, and F, and the least important is As. Furthermore, the optimal set of indicators contained all four of the most important indicators obtained by the random forest model, which achieved a classification accuracy of 88.21% for groundwater quality.

Hydrochemical, bacteriological assessment, and classification of groundwater quality in Thulamela Municipality, South Africa: potential health risk

Potential effects of anthropogenic activities on different boreholes around Thulamela Municipality, South Africa, were evaluated by quantifying the bacteria indicators and physicochemical parameters during summer, autumn, and winter. The purpose was to determine whether the borehole water in this region is safe for domestic use across the seasons. The concentrations of physicochemical (Temperature, pH, electrical conductivity (EC), turbidity, and nitrate) and bacteriological (both Escherichia coli and Enterococcus faecalis) contaminants in the borehole water samples were determined using standard microbiology methods. The mean concentration of NO3 for most of the boreholes failed to comply with the recommended guidelines throughout the season. High microbial load of E. coli (2.0 × 101 – 4.6 × 103 CFU/100 ml) and E. faecalis (2.0 × 10° – 6.0 × 102 CFU/100 ml) was recorded in the wet season than in the dry season (0.0 – 7.0 × 102 and 0.0 – 1.0 × 101 CFU/100 ml, respectively). Sanitary inspection and water source classification showed that most boreholes are prone to chemical contaminants during summer and autumn due to rainfall and this correlates with the measured microbial contamination. The result is significantly important because water from these boreholes is used for domestic purposes without treatment and could pose major public health risks to the consumers.

Characterization of a regional coastal zone aquifer using an interdisciplinary approach – an example from Weser-Elbe region, Lower Saxony, Germany

In this study, interdisciplinary approaches are considered to characterize the coastal zone aquifer of the Elbe-Weser region in the North of Lower Saxony, Germany. Geological, hydrogeological, geochemical and geophysical information have been considered to analyze the current status of the aquifers. All the information collectively states that the salinity distribution in the subsurface is heterogeneous both horizontally and vertically. Early age flooding also contributed to this heterogeneity. No general classification of groundwater quality (according to some piper diagrams) could be identified. Helicopter-borne electro-magnetic data clearly show the presence of freshwater reserves below the sea near the west coast. Groundwater recharge largely happens in the moraine ridges (west side of the area) where both the surface elevation and the groundwater level are high. Consequently, submarine groundwater discharge occurs from the same place. All these information will facilitate to develop the planned density driven groundwater flow and transport model for the study area.

Self Organizing Map of Artificial Neural Network for Groundwater Quality Classification in the F'kirina Plain : Oum El Bouaghi Province-NE of Algeria

Self Organizing Map of Artificial Neural Network for Groundwater Quality Classification in the F'kirina Plain : Oum El Bouaghi Province-NE of Algeria

Shallow groundwater quality assessment: use of the improved Nemerow pollution index, wavelet transform and neural networks

Shallow groundwater is generally of great interest to the community due to its easy availability. However, it is very sensitive to external stimulus. In this paper, shallow groundwater quality is assessed and classified with improved Nemerow pollution index, multi-layer perceptron artificial neural network (MLP-ANN) optimized with a back-propagation algorithm and wavelet neural network (WNN) methods in a coastal aquifer, Fujian Province, South China. The data used in three models were collected during the pre-monsoon over the period 2004–2011. The eight parameters, total dissolved solids, total hardness, chemical oxygen demand, chloride, sulphate, nitrate, nitrite and fluorides, were selected to characterize groundwater quality classification based on the National Quality Standard for Groundwater (GB/T 14848-93). The results of MLP-ANN and WNN are interpreted by mean absolute error, root mean square error and R2 (determination coefficient) criteria. The results obtained from three methods demonstrate that WNN has a higher accuracy compared with the other two methods. The study reveals that these methods are efficient tools for assessing groundwater quality.

Groundwater quality classification derivation using Multi-Criteria-Decision-Making techniques

The paper introduces a novel framework of evaluating and validating the groundwater quality index (GWQI) by employing two Multi-Criteria-Decision-Making models (MCDMs) such as Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and Compromise Programming (CP). GWQIs are plagued by discrete values which are attributed to excellent, good, poor, very poor, and unsuitable for drinking purpose classes. Furthermore, the existence of chemical parameters with low weights but high concentration values (or vice versa) reduces equilibrium of evaluations. Based on the literature review, MCDMs have not been applied so far to validate groundwater quality indexes. This simple yet practical structure assists the analysts to investigate robustness of a water quality index. In order to validate the classes, the intervals of classic GWQI were modified to figure out what changes were made to the classes of samples in the ranking table considering quality of 92 wells in the Varamin plain, Iran. After employment of the MCDMs, the results revealed that WQI could rarely evaluate water quality classes accurately. Several wells which were classified as “excellent quality” were belonged to the lower quality class. It also came true for other classes. The results demonstrated that TOPSIS could present a more precise analysis for the classes with a low number of wells. Moreover, increases in value of the sensitivity parameter of CP technique reduced the accuracy of results. Owing to proper application of MCDMs, one can suggest the use and development of MCDM-based water quality assessment models for future researches.

Groundwater utilization and management: policy guidelines for the South West Saurashtra region

The South West part of Saurashtra is connected to Arabian Sea which in the Southern side of Junagadh city (Gujarat, India). The study area covers 14 Taluka blocks and which mostly depends on groundwater for irrigation. An attempt has been made to assess the groundwater resources and groundwater quality in the region for its prospect and sustainable development. Groundwater potential was estimated by Thiessen Polygon network, aquifer properties, and ground water-level fluctuations. Contour maps of pre- and post-monsoon absolute head, water table and change in water table were prepared using their 3 year (2009 and 2011) average values. The contour maps were prepared using tools like, Bhuvan, Google earth and AutoCAD software. Absolute water head was determined subtracting water table from the reduce level. The reduced level at ground surface beside observation well was recorded using global positioning system and Google earth. The storage coefficient and transmissibility were determined by pumping well test using Papadopoulos and Jacob methods. Variations in the region in storage coefficient and transmissibility are presented by contour maps. Estimated groundwater potential was verified basis on (1) water balance sheet, (2) estimated groundwater draft, and (3) MODFLOW solution. The water balance sheet was prepared by comparing total water potential and total water consumption in the region; groundwater draft was estimated by pumping structures working in the region. The groundwater potential of South West Saurashtra region was estimated 4060.67 million cubic meter (MCM), 1747.21 MCM direct rainfall recharge was estimated, and 2313.45 MCM recharge from water harvesting structures was estimated. Change in water table has negative values and shows that groundwater level in the region is in increasing in trend. Groundwater quality classification maps were prepared based on three parameters electrical conductivity (EC), sodium adsorption ratio (SAR), and residual sodium carbonate (RSC); Sharma and Minhas (Management options and policy guidelines for use of poor quality groundwater in agriculture, Central Soil Salinity Research Institute, Karnal, 2003). Result shows that the region may be divided into three groundwater quality classes for irrigation under post-monsoon observation: 7598.09, 1564.05, and 139.95 km2 areas were found as Good, Marginal saline, and Saline classes, respectively. While in pre-monsoon observation, 7168.48, 1628.38, and 505.23 km2 areas were under Good, Marginal saline, and saline classes, respectively. During post- and pre-monsoon groundwater, samples were collected from each observation well. Chemical parameters, such as EC, pH, Na, Ca, Mg, Ca + Mg, CO3, HCO3, Cl, Mg/Ca, SAR, RSC, SSP (soluble sodium percentage), and total soluble salts, were determined by standard methods. MODFLOW mass balance shows that water resource in the region for 930 days was found positive (IN–OUT) 20,480.00 m3; positive value indicates gain in water resources in the region, but gain was negligible.

New Diagram Useful for Classification of Groundwater Quality

Due to human and human activities the groundwater is polluted. This is the serious problem now a century. Thus the analysis of the water quality is very important to preserve and prefect the natural ecosystem.The primary objective of this paper is to study the groundwater quality parameters. The mechanism of chemical reactions leading to the change in the composition of groundwater and source of the dissolved ions in the groundwater can be understood by Banaga's diagram. The Banaga method is not only shows graphically the nature of a given water sample and dictates the relationship to other samples but there are a number of different methods and schemes used to classify natural water quality, source, origin and determine their suitability for different purposes depending on the concentrations of the basic components. The new diagram is useful for better understanding the evolution of hydrochemical parameters of groundwater that can be by plotting the concentration of major cations and anions in percentage of meq/l, and it is divides the water quality into five types. The results of this analysis were compared with the water quality standards of Piper diagram.

Ground water quality classification by decision tree method in Ardebil region, Iran

A decision tree-based approach is proposed to predict ground water quality based on the United States Salinity Laboratory (USSL) diagram using the data from aquifers in agricultural lands of Ardebil province, northwest of Iran. Several combinations of hydro chemical parameters of groundwater and monthly precipitation with different lag time were considered to find an accurate and economical alternative for groundwater quality classification. The performance evaluation was based on the number of correctly classified instances (CCI) and kappa statistics. The results suggested the suitability of decision tree-based classification approach for the used data sets. The overall average of CCI and kappa statistic for the prediction of groundwater quality classes based on the USSL diagram was 0.88 and 0.83 %, respectively. Principal component analysis (PCA) was also used to determine the important parameters for groundwater quality classification. The results showed that groundwater quality classification by decision tree is more precise and efficient in comparison with PCA. The best alternative could evaluate groundwater quality class with only two parameters: electrical conductivity and cumulative precipitation of 11 months earlier. The developed model is able to predict water quality class by only two variables and this lead to a reduction in the number of variables analyzed on a routine basis, resulting in a significant reduction in laboratory costs and latency times between the sampling moment and the outcome of the laboratory analyses.

Monitoring and methods to analyse the groundwater quality degradation risk in coastal karstic aquifers (Apulia, Southern Italy)

A multi-methodological approach based on monitoring and spatio-temporal analysis of groundwater quality changes is proposed. The presented tools are simple, quick and cost-effective to give service to all sorts of users. The chief purpose of the monitoring network is the detection of the piezometric or potenziometric level in the aquifer. The spatial and multi-temporal analysis of usual chemical and physical data provides both an assessment of the spatial vulnerability of the aquifer to seawater intrusion, defining a salinity threshold between fresh groundwater and brackish groundwater and of the water quality trend in terms of salinity. The evaluation of the salinity trend or of salinity-correlated parameters highlights the effects of groundwater mismanagement. The multiparameter logging provides a rapid groundwater quality classification for each well. The whole approach allows evaluating the effects of current management criteria and designing more appropriate management targets. The Apulian karstic coastal aquifers have been selected as a case study (Southern Italy). Three types of aquifer zones can be distinguished: (1) areas with low vulnerability to seawater intrusion, (2) areas with high vulnerability and (3) areas with variable vulnerability in which the salt degradation largely depends on the ability to manage the well discharge. The water quality degradation caused by seawater intrusion appears to be a combined effect of an anomalous succession of drought periods observed from about 1980 onwards and increased groundwater pumping, particularly during drought periods. A management criterion based on aquifer zones is proposed.

A Methodology for Space-Time Classification of Groundwater Quality

Safeguarding groundwater from civil, agricultural and industrial contamination is matter of great interest in water resource management. During recent years, much legislation has been produced stating the importance of groundwater as a source for drinking water supplies, underlining its vulnerability and defining the required quality standards. Thus, schematic tools, able to characterise the quality and quantity of groundwater systems, are of very great interest in any territorial planning and/or water resource management activity. This paper proposes a groundwater quality classification method which has been applied to a real aquifer, starting from several studies published by the Italian National Hydrogeologic Catastrophe Defence Group (GNDCI). The methodology is based on the concentration values of several parameters used as indexes of the natural hydro-chemical water condition and of potential man-induced modifications of groundwater quality. The resulting maps, although representative of the quality, do not include any information on its evolution in time. In this paper, this "stationary" classification method has been improved by crossing the quality classes with three indexes of temporal behaviour during recent years. It was then applied to data from monitoring campaigns, performed in spring and autumn, from 1990 to 1996, in the plain of Modena aquifer (central Italy). The results are reported in the form of space-time classification table and maps.