A Machine Learning Approach towards Automatic Water Quality Monitoring

According to the World Health Organization (WHO), approximately 2 billion people worldwide use drinking water sources that are contaminated with faeces. This is a serious issue since contaminated water may lead to certain waterborne diseases such as cholera, hepatitis A, dysentery, jaundice, and typhoid fever. Therefore, many researchers around the world are interested in studying the water quality. One of the most commonly used approaches is by using machine learning. Machine learning approach has grabbed the interest of many researchers since the last several years due to its power to compute complicated mathematical computations on big data analysis. Therefore, this study explored the correlation between different water quality parameters and Water Quality Index (WQI) in water quality studies that used machine learning by using a meta-analysis approach. This study used estimated variance, heterogeneity index, Chi-squared heterogeneity test and the random effects model. Based on the selected articles, pH, dissolved oxygen (DO) and biochemical oxygen demand (BOD) are the parameters commonly used in water quality studies which use a machine learning approach. This study found that pH is the best chemical factor which greatly affects the Water Quality Index since it has the highest mean correlation and lowest estimated variance due to sampling error. The result showed that the correlation between pH and WQI are heterogeneous across studies based on the Chi-squared of heterogeneity, Q and heterogeneity index, I2 value. The 95% confidence interval of effect summary supports the findings that the correlation of pH is different among the studies. This study also found that there is no evidence of publication bias using Egger and Begg’s test. Therefore, in order to ensure good water quality supply, the local authorities and government agencies should give more attention to this parameter since pH of water plays an important role in determining the water quality status.

Water Quality Evolution Mechanism (WQEM) modeling and Water quality estimation are important technical means for water pollution prevention and control of lakes and reservoirs. However, existing classical WQEM models usually contain unknown parameters with empirical values range, which brings difficulty of estimation water quality changes of specific lakes and reservoirs to meet the accuracy requirements. Furthermore, water quality indicator is susceptible to natural factors and human factors, which makes the water system complex and nonliner, and enhances the difficulty of water quality estimation. Therefore, combining water quality mechanism, this paper proposes a Fruit Fly Optimization Algorithm (FFOA) based WQEM modeling method and studies a method of water quality estimation based on Particle Filter (PF) algorithm. First, a more comprehensive WQEM model is established to characterize the water quality mechanism of lakes and reservoirs. Then, combining observed data of water quality indicator and WQEM, the unknown parameters of a WQEM model are estimated by using FFOA. Finally, PF algorithm is used to estimate the water quality status. Simulation results show that the method can effectively estimate the unknown parameters of the WQEM model and estimate the water quality status.

In this work, a hydrodynamic and water quality model was developed for Lake Nubia based on a two-dimensional, laterally averaged and finite difference hydrodynamic and water quality code, CE-QUAL-W2. The model was calibrated and verified using data which were measured in the years of 2006 and 2007 during low flood periods, respectively. Measurements during the flood season are not available. The results of the presented model show a good agreement with the observed hydrodynamic and water quality records.
\nTwo water quality indices (WQIs), NSF WQI and CCME WQI, have been developed to assess the state of water quality in the investigated case study, Lake Nubia, during the first low flood period of January 2006. The CCME WQI has been modified to use the Egyptian standards (objectives) of raw water. Moreover, another two trophic status indices, Carlson TSI and LAWA TI, have been developed to evaluate the trophic status of Lake Nubia during the same period of January 2006. Results of the previously developed hydrodynamic and water quality model for Lake Nubia were used to validate the model. According to the developed water quality indices results, Lake Nubia has a good water quality state during the low flood period. The modified CCME WQI (based on measured data) indicates that the Lake Nubia water quality state is excellent according to the Egyptian standards of water quality for surface waterways. Results of the applied trophic status indices show that the Lake Nubia trophic status is eutrophic during the studied period. 
\nThe effect of the global climate change on the hydrodynamic and water quality characteristics of Lake Nubia was conducted for the 21st century. To do that, the outputs of eleven global climate models for two global emissions scenarios combined with hydrological modeling were used. A theoretical process algorithm has been simplified, further developed and calibrated to modify the initial conditions of dissolved oxygen due to the global climate change effects. A sensitivity analysis has been conducted by using each of the predicted air temperature and inflow data separately in the model in order to investigate its effect on the characteristics of the hydrodynamic and water quality. Three hydrodynamic characteristics of the reservoir were investigated with respect to the climate change: water surface levels, evaporation water losses and thermal structure. In addition, eight water quality characteristics of the reservoir were investigated with respect to the climate change: dissolved oxygen, chlorophyll-a, ortho-phosphate, nitrate-nitrite, ammonium, total dissolved solids, total suspended solids and potential of hydrogen (pH). Moreover, the climate change effects on the water quality and trophic status indices have been studied. The results of the climate change study show partially significant impacts on the examined hydrodynamic and water quality characteristics, while the water quality and trophic status indices are slightly affected by the climate change scenarios.

The water quality index (WQI) is a globally accepted guideline to indicate the water quality standard of any groundwater resource. Water levels in existing groundwater sources are declining in several coastal zones. Therefore, for monitoring water quality and improving water management, the prediction and identification of groundwater status by an effective technique with higher accuracy is urgently needed. Therefore, this research aims to find an effective model for WQI prediction by comparing entropy and critic weight-based WQI (ENW-WQI and CRITIC-WQI) with multi-layer perceptron artificial neural network (MLP-ANN) technique and also to identify contaminated zones using GIS. Initially, 1000 water sampling datasets with concentrations of several water quality parameters of different coastal blocks of eastern India during 2018 to 2022 are considered for the estimation of ENW-WQI and CRITIC-WQI. It shows 65% and 67% of the samples are excellent to good for drinking. ENW-WQI and CRITIC-WQI-based MLP-ANN models have been established considering different data portioning and hidden neuron numbers. Input variables and appropriate dataset partitioning with hidden neurons for models obtained from correlation and trial-error analysis. Spatial distribution maps are also produced for calculated WQIs using inverse distance weighted interpolation approaches. Three fitting models are obtained: ENW-WQI-MLP-ANN, CRITIC-WQI-MLP-ANN-I and CRITIC-WQI-MLP-ANN-II. CRITIC-WQI-MLP-ANN-II model (data ratio 85:15, network structure 6-12-1, R2 = 0.986, NSE = 0.98, and error rate 0.49%) provides the best accuracy in WQI prediction. The GIS-based WQI maps record several areas related to drinking water quality. The results of this research can help in planning the provision of safe drinking water in the future.

Since coastal waters are one of the most vulnerable marine systems to environmental pollution, it is very important to operationally monitor coastal water quality. This study attempts to estimate two major water quality indicators, chlorophyll-a (chl-a) and suspended particulate matter (SPM) concentrations, in coastal environments on the west coast of South Korea using Geostationary Ocean Color Imager (GOCI) satellite data. Three machine learning approaches including random forest, Cubist, and support vector regression (SVR) were evaluated for coastal water quality estimation. In situ measurements (63 samples) collected during four days in 2011 and 2012 were used as reference data. Due to the limited number of samples, leave-one-out cross validation (CV) was used to assess the performance of the water quality estimation models. Results show that SVR outperformed the other two machine learning approaches, yielding calibration R2 of 0.91 and CV root-mean-squared-error (RMSE) of 1.74 mg/m3 (40.7%) for chl-a, and calibration R2 of 0.98 and CV RMSE of 11.42 g/m3 (63.1%) for SPM when using GOCI-derived radiance data. Relative importance of the predictor variables was examined. When GOCI-derived radiance data were used, the ratio of band 2 to band 4 and bands 6 and 5 were the most influential input variables in predicting chl-a and SPM concentrations, respectively. Hourly available GOCI images were useful to discuss spatiotemporal distributions of the water quality parameters with tidal phases in the west coast of Korea.

Urban rivers play important roles in providing water resources for human, and ecosystem survival. Urban river water quality is therefore an important parameter that must be monitored. The lack of appropriate basic urban infrastructures, coupled to the rapidly increasing human populations in tropical cities, has led to an advanced state of pollution of these cities. The aim of this study was to assess the water quality of an urban river water body of the metropolitan city of Douala. We collected water samples both upstream, and downstream of a major saop manufacturing industry. We determined the water quality index (WQI), and tested for an association of this water pollutants with waterborne diseases in the area. The river was highly polluted, and the concentrations of pollutants (WQI usptream = 16.2; downstream =11.9) were very much higher than the standards recommended by the World Health Organization (WQI = 99.2). There was a very significant association between the polluted water, and waterborne diseases. We advocate taugher pollution control measures to stop the deterioration as cumulitive effects of environmental degredation are extremely difficult to reverse.

Water quality assessment, especially in relation to prevalent waterborne diseases is necessary to ensure that clean and safe drinking water is delivered and sustained to reduce water-borne disease and other public health issues that are associated with the use of unsafe water. Little has been documented about the relationship between water quality and prevalence of waterborne diseases in Omu-Aran, Nigeria. In this wise, eighteen (18) water samples were collected from the available drinking water sources in the three densely populated communities in the study area, Ifaja, Ihaiye and Aran. The microbiological analysis of the water samples was performed by the determination of total coliform, according to the modified methods while the physicochemical parameters were determined by Standard Methods (APHA, 2005). Questionnaires were administered to 100 respondents in the selected communities to elicit information on water sourcing, collection, storage, treatment and prevalence of waterborne diseases treatment. Eighteen (18) water quality parameters cutting across physico-chemical and biological traits were investigated. All parameters were found to be within the WHO limit except microbial parameter (coliform count). The contamination risk from the household activity assessment were found to be severe for water source and water storage while it is moderate for water collection and water treatment and hygiene practices. The prevalence of common waterborne diseases are 9%, 35% and 56% for cholera, typhoid and Diarrhea respectively. The correlation coefficient between microbial parameter and prevalence waterborne diseases are 0.02, -0.5 and 0.86 for cholera, typhoid and cholera respectively. This is indicative of the water quality potential to be inherently laddened with waterborne diseases.

The usefulness of water quality indices, as the indicators of water pollution, for assessment of spatial-temporal changes and classification of river water qualities was verified. Four water quality indices were investigated: WQI (considering 18 water quality parameters), WQI(min) and WQI(m) (considering five water quality parameters: temperature, pH, DO, EC and TSS) and WQI(DO) (considering a single parameter, DO). The water quality indices WQI(min), WQI(m) and WQI(DO) could be of particular interest for the developing countries because of the minimum analytical cost involved. As a case study, water quality indices were used to evaluate spatial and temporal changes of the water quality in the Bagmati river basin (Nepal) for the study period 1999-2003. The results allowed us to determine the serious negative effects of the city urban activity on the river water quality. In the studied section of the river, the water quality index (WQI) was 71 units (classified as good) at the entry station and 47.6 units (classified as bad) at the outlet station. For the studied period, a significant decrease in water quality (mean WQI decrease = 11.6%, p = 0.042) was observed in the rural areas. A comparative analysis revealed that the urban water quality was significantly bad as compared with rural. The analysis enabled to classify the water quality stations into three groups: good water quality, medium water quality and bad water quality. WQI(min) resulted in overestimation of the water quality but with similar trend as with WQI and is useful for the periodic routine monitoring program. The correlation of WQI with WQI(min) and DO resulted two new indices WQI(m) and WQI(DO), respectively. The classification of waters based on WQI(m) and WQI(DO) coincided in 90 and 93% of the samples, respectively.

Water on the earth is in abundance but its distribution is very much uneven on the land surface. Only 2% of the total water is available for use. Due to its distribution and quality, scarcity of portable water will be the major challenge at global level as most of the water available in surface reservoirs and groundwater are affected by various kind of contaminations of various sources. The situation is more aggravated in arid and semi-arid areas. Rajasthan state of India is located in arid & semi-climatic region with poor water quality. Same is the situation in the Bhilwara district located in the central part of the Rajasthan state where availability of water resource is very poor because of quality, quantity, and distribution issues. At the same time demand for potable water is increasing day by day for irrigation, industrial & domestic purposes. The present study is focused on spatial variability of groundwater quality for the Bhilwara district of Rajasthan, India using geospatial techniques. Four important water quality parameters that is Total dissolved solids, Chloride, Nitrate, and Fluoride (TDS, Cl, NO3, and F) has been taken into consideration for assessment of water quality. Data on these parameters have been collected and classified with the standard parameter values as suggested by the BIS standards (ISI 10,500:2012). After data normalization appropriate weights have been given according to the contribution of individual parameter in water quality and a ground Water Quality Index (WQI) is generated. The scale of WQI is categorized into (1) Very Good, (2) Good, (3) Average, and (4) Poor. The analysis indicates that good water quality is associated with high water level, more thickness of alluvium, deep bedrock, more water-saturated strata, good groundwater recharge areas, nearness from the river, etc. The results are verified in the field at appropriate locations supported by interviews of local farmers. Status of water quality shows that the 24.65 and 20.18% area of district cover by the “Very Good” and “Good” quality of water and 33.72% area show the “Average” quality of water while the 21.45% of area is covered by the “Poor” quality of water.KeywordsGroundwater qualityGISISI standardsOrdinary krigingWater Quality Index (WQI)

The ground water is contaminated, its quality cannot be restored by stopping the pollutants from the source. The common pollutants of groundwater are discharge of agricultural, domestic, and industrial waste, pesticides etc., which leads to water- borne diseases. Water-borne diseases may be of microbial origin such as diarrhea, dysentery, cholera, typhoid and chemical origin such as flurosis and methemoglobinemia. Water Quality Index (WQI) provides a single number that expresses overall quality at certain location and time based on several water quality parameters. The objective of an index is to turn complex quality data in to information that is understandable and useable by the public. The present study was undertaken to assess the suitability of 8 drinking water sources of Doiwala block of Dehradun for drinking purpose during pre- and post-monsoon seasons of the year 2021. The obtained water quality data of drinking water sources was further applied for the calculation of weighted arithmetic Water Quality Index (WQI). Most of the water sources during pre-monsoon season were graded as ‘A’ with good quality due to having low WQI values. However, Two sites were found with ‘B’ class, another two were classified as ‘C’ grade owing to higher WQI values and thus, categorized as having poor water quality. Two sampling sites were recorded with highest WQI value (59.29) and (68.24) its water quality was found poor for drinking purpose. During post-monsoon season, all analyzed water sources showed low WQI values, which indicates ‘A’ class i.e. excellent water quality. The higher WQI values during pre-monsoon season have been inferred owing to relatively higher calcium, magnesium and iron concentrations assessed during the period of study.

The aim of this work is to intelligently detect alarming events in the water quality using machine learning techniques at the edge device, which is adaptive to localities, applications and also time. There are four objectives of this work; (1) To develop an edge device for sensing the water quality parameters (2) to detect changes in the water quality with respect to base line parameter using a machine learning approach at the edge device itself (3) to generate the alarm signals when water quality parameters go beyond its threshold value and (3) to classify different types of contamination and analyze them for identifying possible contamination types. For the experimentation, three water quality indicative methods are used to calculate the water quality, namely (a) Weighted Arithmetic Index, (b) NSF Water Quality Index and (c) User feedback of the water quality. Water quality is determined using water quality indexes (WQI) on the basis of six physico-chemical sensor parameters like biological oxygen demand, dissolved oxygen, pH, total hardness, total dissolved solids and turbidity. With the help of WQI of these methods, a light weight machine learning model which is suitable for the edge device, has been developed using the Support Vector Machine (SVM) algorithm. We also clustered the alarming events to find out different types of alarming events.

The varieties of water-borne disease are caused by pathogens transmitted and spread by different routes. The spread of such infection increases while the water quality affected by external sources. Changes in the quality of water can influence the dynamics of microbial pathogens which can also influence the prevalence and transmission dynamics of water-borne diseases. The present study highlighted on selected chemical parameters of ground water to signify the water quality index and mapping of water-borne diseases susceptibility areas in Kolkata Municipal Corporation, India. The main objective of present study was to demonstrate the significance of geographical information system based Geostatistical technique for identifying water-borne diseases susceptibility by taking different ground water parameters, water quality index and reported water-borne diseases into consideration. Using Kriging interpolation, the spatial map of water parameters, water quality index and reported disease cases were prepared and reclassified by putting risk rank to generate susceptibility map of water-borne diseases. The accuracy of the result was assessed through error estimation and spatial autocorrelation. The result from error estimation, it was found that the root mean square error between diseases susceptibility and selected chemical parameters, water quality index and reported water-borne diseases are 0.0847, 0.1182 and 0.0640 respectively which is always < 1. The correlation of diseases susceptibility with chemical parameters has resulted highly positive (r2 = 0.97) and with water quality index has also resulted positive (r2 = 0.82). The study result also suggests the applicability of geographical information system in other types of diseases susceptibility analysis by setting proper objectives and selecting suitable study criteria with spatial justification.

Application of Water Quality Index (WQI) to assess the water quality for drinking water suitability and intensity of contamination is in practice worldwide. Many WQI methods have been in use since their conceptualization, and some are country-specific or use-specific. A generalized and widely acceptable method that can project ground truths in non-dimensional numerical form to evaluate the water quality, especially for drinking uses, is lacking. Complexity and disagreement among different methods are adding to incongruence among the scientists. The concept and a simple calculation method of WQI are deliberated. Five different WQI methods using water chemistry results of Vizianagarm District are discussed. The WQI output obtained from these methods displays discrepancies in the proper projection of water quality. Some samples show similarities in WQI values obtained from two to four methods. However, the suitability status of water for drinking purposes could not be precisely ascertained from these indices. Since the water chemistry results and WQI values are incompatible, the output from these methods could be red herring. Few issues are identified among the studied methods which need improvisation. The use of ideal value in the weighted arithmetic index method and arbitration in assigning Weight for each parameter gives scope for speculation. Non-uniformity in the categorization of water and the suitability statuses of drinking water are discouraging factors. The WQI is an effective tool in screening the vast database for identifying and addressing the issues in water quality. Since drinking water standards and water supply are government-sponsored, an institutional intervention is required to standardize the WQI computation procedure. Such an initiative is necessary for the practical application of water quality data to contain water-borne diseases.

Impact of land uses, drought, flood, wildfire, and cascading events on water quality and microbial communities: A review and analysis

Evaluation of water quality and potential scaling of corrosion in the water supply using water quality and stability indices: A case study of Juja water distribution network, Kenya