Water Quality Classification Research Articles

Water Quality Prediction and Classification based on Linear Discriminant Analysis and Light Gradient Boosting Machine Classifier Approach

Estimating water quality has existed as one of the vital factors embarked on the planet in the present eons. This paper illustrates a water quality estimate based on the Linear Discriminant Analysis (LDA) technique. Weighted arithmetic index technique is used in the computation of the Water Quality Index (WQI). At that moment, the LDA is linked to the dataset, and the ultimate principal WQI dynamics have been determined. Subsequently after predicting the WQI, Light Gradient Boosted Machine (LGBM) classification is performed in the LDA. Lastly, the LGBM classifier is activated to label the water quality. This proposed LGBM with LDA technique is demonstrated and evaluated on a Gulshan Lake-related dataset. The results show 96% forecast accuracy for the LDA and 100% categorization accuracy for the Light Gradient Boosted Machine classifier system that indicate consistent interpretation linked over the futuristic prototypes. This innovative model LDA-LGBM is aimed at enhancing the prediction of water quality and its classification through AI - ML approach.

A global review of beaver dam impacts: Stream conservation implications across biomes.

Beaver are recolonizing previously occupied regions, expanding into new territories, and increasingly being introduced and protected for stream conservation and restoration across numerous biomes. However, beaver dam effects on the physical, chemical, and biological characteristics of streams may vary within and among biomes. A comprehensive review of these impacts is lacking. The goals of this review were to: 1) summarize the distribution of studies by biome on beaver dam effects related to channel morphology, hydrology, water quality, and aquatic biota, as well as on beaver habitat selection, 2) summarize the extent to which beaver dam impacts have been consistent within and among biomes, and 3) share testable hypotheses regarding beaver impacts within understudied biomes. We quantify the directionality of beaver dam impacts from 267 peer-reviewed studies. Results show that the majority of studies have been completed within temperate forest environments and that many biomes are understudied. Across biomes, beaver preferred sites for dam development characterized by relatively low gradients and unconfined reaches with small drainage areas. Overall, parameters related to stream morphology and hydrology showed relatively consistent responses to beaver dams within and among biomes, yet water quality and biotic responses were variable among biomes. Responses also varied by parameter within water quality and biotic impact categories. The findings of this study can be useful for stream conservation and restoration efforts that introduce or protect beaver. Additional studies are needed within arid and cold biomes historically occupied by beaver and in novel biomes where beaver populations are currently expanding.

Predicting Irrigation Water Quality Indices Based on Data-Driven Algorithms: Case Study in Semiarid Environment

Ascertaining water quality for irrigational use by employing conventional methods is often time taking and expensive due to the determination of multiple parameters needed, especially in developing countries. Therefore, constructing precise and adequate models may be beneficial in resolving this problem in agricultural water management to determine the suitable water quality classes for optimal crop yield production. To achieve this objective, five machine learning (ML) models, namely linear regression (LR), random subspace (RSS), additive regression (AR), reduced error pruning tree (REPTree), and support vector machine (SVM), have been developed and tested for predicting of six irrigation water quality (IWQ) indices such as sodium adsorption ratio (SAR), percent sodium (%Na), permeability index (PI), Kelly ratio (KR), soluble sodium percentage (SSP), and magnesium hazards (MH) in groundwater of the Nand Samand catchment of Rajasthan. The accuracy of these models was determined serially using the mean squared error (MSE), correlation coefficients (r), mean absolute error (MAE), and root mean square error (RMSE). The SVM model showed the best-fit model for all irrigation indices during testing, that is, RMSE: 0.0662, 4.0568, 3.0168, 0.1113, 3.7046, and 5.1066; r: 0.9364, 0.9618, 0.9588, 0.9819, 0.9547, and 0.8903; MSE: 0.004381, 16.45781, 9.101218, 0.012383, 13.72447, and 26.078; MAE: 0.042, 3.1999, 2.3584, 0.0726, 2.9603, and 4.0582 for KR, MH, SSP, SAR, %Na, and PI, respectively. The KR and SAR values were predicted accurately by the SVM model in comparison to the observed values. As a result, machine learning algorithms can improve irrigation water quality characteristics, which is critical for farmers and crop management in various irrigation procedures. Additionally, the findings of this research suggest that ML models are effective tools for reliably predicting groundwater quality using general water quality parameters that may be acquired directly on periodical basis. Assessment of water quality indices may also help in deriving optimal strategies to utilise inferior quality water conjunctively with fresh water resources in the water-limited areas.

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 anddecision-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.

Water quality assessment based on Nemerow pollution index method: A case study of Heilongtan reservoir in central Sichuan province, China.

In this paper, three monitoring sections were set up in Heilongtan Reservoir, and water samples were collected in 2019, 2020, and 2021 for the determination of physical and chemical properties such as permanganate index, chemical oxygen demand, and biochemical oxygen demand (BOD5). The water quality was evaluated by the single factor pollution index method and the Nemerow pollution index method, and the temporal and spatial changes of water quality were analyzed.The single factor pollution index method determines the water quality category by identifying the single worst indicator of water quality, based on the classified water quality category. The Nemerow pollution index method emphasizes the most polluting factor while also taking into account the contribution of other factors in the assessment system, and determines the water quality category through the comprehensive pollution index. The results of the study indicate that the monitoring indicators of the monitoring sections have reached the Category III water quality standard and above in the "Surface Water Environmental Quality Standard" during the three years 2019 to 2021. The Heilongtan Reservoir's water quality in 2019, 2020, and 2021 is of Category I standard, according to the results of the evaluation of water quality using the single factor pollution index technique. According to the Nemerow pollution index method's results for evaluating water quality, the water quality pollution index for the three monitoring sections as a whole ranges from 0.36 to 0.51 in three years. The three monitoring sections' water quality-Dongfeng Canal, Longmiao, and Sixin Village-has not changed significantly during that time, remaining clean. In terms of temporal and spatial rates of change, the temporal rate of change (T) and spatial rate of change (S) over the three years were less than 20%, and the changes in water quality at each monitoring site were not significant.

Selection of suitable aggregation function for estimation of water quality index for the Orontes River

This study aims to select the most appropriate aggregation function to determine a preliminary classification of water quality according to special criteria for required use. The Orontes River was taken as a study case as an important water resource, to assess the suitability of its water for various uses by using water quality index. Four main steps were applied to build a water quality index; the first step is selecting parameters using the Delphi technique based on experts' opinion, where 5 parameters of the most important water pollutants were selected, the relative weight of each parameter was determined based on its significance to the final index using the weight criteria method. To standardize the range of pollution indicators, the quality rating curves for each parameter were drawn using regression analysis and extracting equations for the quality rating qi. The final step is aggregation Sub-indicators, about 20 aggregation functions were applied to select the most appropriate aggregation function for assessing the water quality of the Orontes River (ORSI) based on special criteria (Ambiguity, Eclipsing, Constant functional behavior, weight, sensitivity). After comparing the values of the indicators based on the criteria, the results showed that the weighted arithmetic mean (ORSIwa) is the best linear function for assessing the Orontes River water quality by the classifications of the main categories according to the required use.

River Water Quality Prediction and index classification using Machine Learning

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

Perspectives for review of the classification of water quality of the Benevente river basin from the use of frequency curves and water quality modeling

RESUMO Este trabalho discute a aplicação das curvas de permanência de qualidade como ferramenta para subsidiar decisões sobre o enquadramento de cursos d'água superficiais. A bacia hidrográfica do Rio Benevente (Espírito Santo, Brasil) constituiu a área de estudo. As cargas totais de DBO5,20 foram estimadas para diferentes seções de controle, considerando-se o esgotamento sanitário como a única fonte poluidora. Com o auxílio do modelo QUAL-UFMG, foram avaliadas as perspectivas de enquadramento associadas a diferentes cenários de simulação da autodepuração. As curvas de permanência de qualidade para o parâmetro DBO5,20 foram construídas para rios de água doce classes 1, 2 e 3. A capacidade de autodepuração do Rio Benevente permitiu a redução de 17% da carga total de DBO5,20 aportada. Independentemente do cenário de simulação avaliado, o Rio Benevente apresentou condições de qualidade usualmente mais próximas dos padrões estabelecidos para a classe 1 de enquadramento. Nesse sentido, ainda que não ocorra ampliação da cobertura do serviço de tratamento de esgotos, as curvas de permanência de qualidade para o parâmetro DBO5,20 apontaram condições para enquadramento mais restritivo dos cursos d'água da bacia hidrográfica do Rio Benevente do que aquele acordado no enquadramento legal.

Performa Metode Klasifikasi Tunggal dan Ensemble Model dalam Identifikasi Baku Mutu Air

Water quality classification for the needs of recreational facilities, livestock, fisheries, and plantations is needed to determine utilization based on water quality according to national water quality standards. The methods used in this research are K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), and Ensemble Model. The parameters measured consisted of temperature, TDS, TSS, pH, COD, BOD, DO, and rainfall. The main objective of this research is to discover the performance of a single classification method and ensemble model on data types with unbalanced class distributions. Classification objects are divided into two classes. First, is the class for the designation of recreational facilities, fisheries, and livestock. Second, the class for the allotment of crop cultivation. The test results of the application of the KNN obtained 86%, SVM obtained 87%, and NB obtained 90.57%. Meanwhile, through the ensemble model, the results obtained are 94.43% Bagging Classifier, 94.96% Gradient Boosting Classifier, and 95.94% Adaboost Classifier

Research on the Application of Multimodal-Based Machine Learning Algorithms to Water Quality Classification

With the development of society and the accelerated industrialization, the problem of water pollution has become increasingly prominent. In order to stop the gathering and diffusion of harmful substances in water bodies, leading to further deterioration of water quality and more serious environmental problems, environmental management departments have developed a series of pollutant discharge standards to prevent water pollution in real time. Common testing methods are the colorimetric method and TDS (total dissolved solids) value testing method, which are mostly through water bodies that contain acid, alkali, salt, and other indicators of the concentration test, to produce an assessment of water quality. However, the traditional methods of water quality testing, whether in the measurement time or in the accuracy of the test, are certain defects. In order to be able to quickly detect the concentration of water quality indicators in water bodies, timely response and treatment of highly polluted water bodies are urgently needed. In this paper, we propose a water quality detection classification model based on multimodal machine learning algorithm. Firstly, we preprocessed and analyzed the collected water quality dataset and determined the reasonable and perfect water quality classification influencing factors. Then, we successively built 15 kinds of classification models based on machine learning algorithms for water quality detection. At the same time, we evaluated the performance of each model. From the four evaluation indexes of precision, recall rate, F1 value, and accuracy, respectively, the real value is compared with the predicted value of each model. The experimental results show that sulfate, pH, solids, and hardness are the important influencing factors to perform water quality testing. And the three models XGBoost (Extreme Gradient Boosting), CatBoost (Categorical Boosting), and LGBM (Light Gradient Boosting Machine) have better performances in conducting water quality testing. Finally, we further optimized the classification models based on XGBoost, CatBoost, and LGBM by using two major tools: cross-validation and hyperparameter tuning.

Peta Distribusi Sebaran Kualitas Fisik Air di Danau Sipin Kota Jambi dan Rekomendasi Pemanfaatannya

This study aims to determine the water quality in Lake Sipin based on the physical quality of the water, to provide information on the distribution map of the distribution of water quality based on the physical quality of the water and to examine the allotment for the management of Lake Sipin. Lake Sipin water is one of the water sources used by the community for daily life. The quality of water in aquaculture activities is influenced by the life of the surrounding environment. Water quality has different quality standards for each designation, so it is important to monitor and evaluate water quality. The data collection technique was carried out by purposive sampling using the Storet method and the Stepwise test was carried out. The parameters observed in this study were temperature, TDS, TSS, turbidity and pH. Based on the results of the study, it was found that the quality standards for each parameter were included in the second class water quality standard. Calculation using the Storet method, water quality gets a value of -4, meaning that the water quality of Lake Sipin is in a lightly polluted status. The relationship between parameters that have a relationship from the results of the stepwise test. TSS and TDS have a relationship with the value of R = 0.661 with the assumption that the higher the TSS value, the lower the TDS value. Turbidity and TSS have a relationship with the value of R = 0.731 with the assumption that the greater the value of Turbidity, the greater the TSS value. pH and TDS have a relationship with the value of R = 0.518 with the assumption that the smaller the pH value, the greater the TDS value. The status of the water quality in Lake Sipin meets the water quality standards, meaning that the water quality in Lake Sipin is still good. The water quality distribution map has various distributions and the water in Sipin Lake can still be used according to the second class water classification based on observations of water physics parameters.

Micro- and macrofauna of benthic invertebrates of the estuary section of the Mokra Moskovka, a small river in the City of Zaporizhzhia

Nowadays, in the period of scientific and technological progress, the anthropogenic impact on the environment keeps increasing. At the same time, its forms and its degree are very diverse. The study of aquatic ecosystems, including ecosystems of small rivers, is one of the applied environmental researches. Small rivers form water resources, hydrochemical composition and water quality of medium and large rivers. They form natural landscapes and contribute to human economic activities.
 Most of the indicators classify the current environmental state of small and medium rivers of Zaporizhzhia Region as unsatisfactory. The main reason for this situation is an excessive anthropogenic load on environmental systems of small rivers that have a noticeable reaction to any interference. One of the consequences of this process includes siltation of small rivers. A small river Mokra Moskovka is not an exception to the above-described characteristics of aquatic ecosystems. The river flows through the territory of Zaporizhzhia Region and its lower part of about 11 km long flows in the densely built-up part of the City of Zaporizhzhya. The mouth section of the Mokra Moskovka River is 2.6 km long and runs through the territory of Aleksandrovsky and Kommunarsky districts of Zaporizhzhia from the river's mouth to the Zaporizhzhia-1-Zaporizhzhia-2 railway bridge. Over the years of its existence, the mouth section of the small river's bed silted up considerably and has an unsatisfactory condition. This is due to the rising of the Kakhovka Reservoir water level and daily fluctuations of the Dnipro's water level that together lead to the reverse movement of water masses and emergence of stagnant phenomena within the studied portion of the river's bed. In addition, the outlets of the municipal rainwater drainage system present a significant source of the sediment, debris and pollutants entering the river.
 In order to improve the environmental condition of the Mokra Moskovka and remove its silt sediments within the bounds of the city, the riverbed was being cleared during 2004-2013. Our data indicate that the thickness of the river's silt sediments reaches 1.0-1.5 m in some places. To restore and maintain favorable hydrological regime and sanitary condition of the mouth section of the Mokra Moskovka it is planned to clean the mouth section of the river channel from silt sediments using hydromechanization technologies and dredging mechanisms in 2022-2023 (scheduled activities).
 The research is aimed at studying the structural organization of the bottom fauna of the estuary section of a small river Mokra Moskovka within the urban ecosystem. The work is based on the results of our own hydrobiological research. During the observation that took place in 2021 53 species of benthic invertebrates were recorded at the mouth of the watercourse. It was found that, out of the total number, 21 species belonged to the macrozoobenthos and 32 – to the benthic microfauna groupings. The conducted saprobiological assessment of the studied river sections for the indicated organisms of micro- and macrozoobenthos revealed that the surveyed part of the watercourse belongs to the α-mesosaprobic zone and is classified as "polluted waters" according to the surface water quality classification. In order to improve the environmental condition of the mouth section of the Mokra Moskovka River it is necessary to implement certain measures of biological water treatment using modern biotechnological solutions developed in Ukraine.

Hybridization of long short-term memory with Sparrow Search Optimization model for water quality index prediction

Water quality (WQ) analysis is a critical stage in water resource management and should be handled immediately in order to control pollutants that could have a negative influence on the ecosystem. The dramatic increase in population, the use of fertilizers and pesticides, and the industrial revolution have resulted in severe effects on the WQ environment. As a result, the prediction of WQ greatly helped to monitor water pollution. Accurate prediction of WQ is the foundation of managing water environments and is of high importance for protecting water environment. WQ data presents in the form of multi-variate time-sequence dataset. It is clear that the accuracy of predicting WQ will be enhanced when the multi-variate relation and time sequence dataset of WQ are fully utilized. This article presents the Water Quality Prediction utilising Sparrow Search Optimization with Hybrid Long Short-Term Memory (WQP-SSHLSTM) model. The presented WQP-SSHLSTM model intends to examine the data and classify WQ into distinct classes. To achieve this, the presented WQP-SSHLSTM model undergoes data scaling process to scale the input data into uniform format. Followed by, a hybrid long short-term memory-deep belief network (LSTM-DBN) technique is employed for the recognition and classification of WQ. Moreover, Sparrow search optimization algorithm (SSOA) is utilized as a hyperparameter optimizer of the proposed DBN-LSTM model. For demonstrating the enhanced outcomes of the presented WQP-SSHLSTM model, a sequence of experiments has been performed and the outcomes are reviewed under distinct prospects. The WQP-SSHLSTM model has achieved 99.84 percent accuracy, which is the maximum attainable. The simulation outcomes ensured the enhanced outcomes of the WQP-SSHLSTM model on recent methods.

Seasonal analysis of groundwater samples to identify water quality index and comparative statistical analysis of Hunsur Taluk, Mysuru, Karnataka, India

Groundwater quality assessment is critical for maintaining freshwater sources in semi-arid and dry environments, which is critical for long-term development. Water quality control authorities can regulate the use of water for agriculture or drinking implementations based on groundwater quality in various areas, as nearly 85% of India's population is reliant on groundwater for domestic and irrigation needs, particularly as a source of drinking in rural areas. From Hunsur taluk, Mysore district, Karnataka, India, this study explores and identifies potential places for pumping groundwater for drinking and irrigation. An analysis of groundwater quality was conducted by analyzing the Water Quality Index (WQI) determined from 30 wells during two seasons of the year 2019, namely Pre-Monsoon and Post-Monsoon. The identification of the quality of water resources for irrigation and drinking purposes can be determined with the help of the WQI. It’s extremely useful for classifying water quality considering the standard-based classification of water as excellent, good, poor, very poor, or unsuitable for drinking. By using the Weighted Arithmetic Index method calculated using the groundwater samples collected data for the study, reported ‘excellent water’ ranges between 80 and 83.33 and ‘good water’ between 20 and 16.67, and never found ‘poor water.’ The IWQ index for the study area has been reported to be in the average range of 17.35–65.64. This paper highlights the physico-chemical parameters assess water quality in comparison with climatology.

Non-ionized ammonia content according to ammonium values in surface water quality classes

The study shows that the NH3 content in surface waters at pH 6.5–7.0 does not exceed the mandatory value for salmon and cyprinid waters of <= 0.025 mg/dm3. At pH 7,5 (15-200C, class IV) to pH 9,0 (5-200C, class I-IV) the value is exceeded 1.1-44.5 times. In the Protocol on Water and Health in the Republic of Moldova for the years 2016-2025, point 123, it is mentioned that there is a lack of monitoring on the quality of water for fish farming in artificial ponds. Thus, it is proposed to include NH3 in the surface water quality monitoring program, in particular to reduce the risk of toxicity to aquatic biota, protect or improve the maintenance of fish life.

A preliminary evaluation of microbial water quality in the irrigation pond.

This study aimed to determine the microbial water quality of Imrahor Pond by enumerating the coliform bacteria levels in the area. Water samples were collected biweekly from the surface and bottom waters at seven points in the pond. Samples were analyzed for total coliforms, Escherichia coli, physicochemical parameters (water temperature, conductivity, pH, turbidity, dissolved oxygen, nitrate) and 1-day rainfall. The average values of TC and E.coli were 1487.4 and 36.3 MPN/100 ml, respectively. TC concentrations/physicochemical parameters were met at least 2nd class water quality class and E.coli results were met "guideline value" (E.coli < 250 MPN/100ml) of national regulation. Overall, among measured physicochemical parameters, rainfall had the strongest positive correlation (r = 0.377 for total coliforms and r = 0.466 for E.coli, p< 0.05) with both indicators, indicted that surface runoff due to rainfall is the main factor which effects microbial water quality in the study area. This study demonstrated the preliminary microbial water quality results (TC and E.coli) in the Imrahor Pond and can serve as a basis for developing more precise water quality monitoring and management studies in the future. PRACTITIONER POINTS: Prevalence of TC and E.coli in the surface and bottom waters of Imrahor Pond were investigated for the first time. Imrahor Pond was met guideline value of national regulations based on E.coli concentrations, in the study period. Surface runoff after rainfall was the main environmental factor which influenced the microbial water quality of the pond.

Water quality assessment using optimized CWQII in Taihu Lake

To improve the rationality of weight allocation and weight proportion of different periods in the process of water quality assessment, the comprehensive water quality identification index (CWQII) model was optimized in this study. A new improved comprehensive water quality identification index (ICWQIIG) model based on game theory was established to combine subjective weight and objective weight. Based on ICWQIIG, an improved comprehensive water quality identification index (ICWQIIP) model with phased period combination weights was established to determine determined the weight proportion of phased periods was established. In this study, CWQII, ICWQIIG, and ICWQIIP were used to evaluate the water quality of seventeen sites in Taihu Lake in 2020. The models selected nine water quality parameters and six water quality indicators. The assessment results of water quality classification were between “slightly polluted” and “moderately polluted”. The pollution level on the east bank was lower than that on the west bank and north bank. Furthermore, it was also affected by seasonal change, water quality was worse in January and February but better in October and November. The mean value of Iwq calculated by CWQII, ICWQIIG, and ICWQIIP were 2.405, 2.833, and 3.000, respectively. The compared results showed that the ICWQIIG method can more representative identify the location of polluted water than CWQII. Moreover, the ICWQIIP method calculation results not only retained the representative polluted water samples in the ICWQIIG method but can also identify more pollution sites and worse polluted water bodies. Both ICWQIIG and ICWQIIP had high reliability and accuracy in assessment results, and ICWQIIP was more accurate under sufficient data conditions. This study can offer a scientific basis for local water resource management in Taihu Lake, while simultaneously proposing a science-based and valid methodology for the assessment of other similar water bodies.

Water quality classification using machine learning algorithms

Monitoring water quality is essential for protecting human health and the environment and controlling water quality. Artificial Intelligence (AI) offers significant opportunities to help improve the classification and prediction of water quality (WQ). In this study, various AI algorithms are assessed to handle WQ data collected over an extended period and develop a dependable approach for forecasting water quality as accurately as possible. Specifically, various machine learning classifiers and their stacking ensemble models were used to classify the WQ data via the Water Quality Index (WQI). The studied classifiers included Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), CATBoost, XGBoost, and Multilayer Perceptron (MLP). The dataset used in the study included 1679 samples and their meta-data collected over nine years. In addition, precision-recall curves and Receiver Operating Characteristic curves (ROC) were used to assess the performance of the various classifiers. The findings revealed that the CATBoost model offered the most accurate classifier with a percentage of 94.51. Moreover, after applying stacking ensemble models with all classifiers, accuracy reached 100% in various Meta-classifiers. Furthermore, the CATBoost achieved the highest accuracy as a primary gradient boosting algorithm and a meta classifier. Therefore, the boosting algorithm is proposed as a reliable approach for the WQ classification. The analysis presented in this article presents a framework that can support the efforts of researchers working toward water quality improvement using artificial intelligence.

Water Quality Classification for Inland Lakes and Ponds with Few Color Image Samples Based on Triple-GAN and CSNN

Water color is an important representation reflecting the characteristics of its quality in inland lakes or ponds; however, sufficient water color image samples are often difficult to obtain due to the limitation of fishery production. For few color image samples, the existing data enhancement methods based on the depth generation model have the problems of low quality of generated data, difficulty of network training, and so on; moreover, for image classification, traditional methods based on convolutional neural network (CNN) cannot effectively extract the potential manifold structure features in the image and the full connection layer in CNN cannot simulate biological neurons well, resulting in high time cost and low efficiency. In this paper, a water quality classification method has been proposed to solve the above problems, the improved semisupervised triple-generation adversarial network (triple-GAN) algorithm is used to enhance the few water color image samples, and the feature data can then be extracted from enhanced data by manifold learning method t-distributed stochastic neighborhood embedding (t-SNE). Moreover, convolutional spiking neural network (CSNN), in which spiking neural network (SNN) has replaced the original full connection layer of CNN, is used for final water quality classification. The main contribution of this paper is to build a new algorithm framework, introduce triple-GAN and CSNN into the field of classification of few water color image samples for the first time, and make an exploration of integrating artificial intelligence (AI) and water quality analysis problems. By comparing with traditional methods, the proposed method is proved to have the advantages of less time-consuming, low operation cost, and high classification accuracy.

Microcontroller-Based Water Quality Monitoring System Implementation

So far, Regional Drinking Water Companies (PDAMs) have used conventional methods by taking water samples, measuring all water quality parameters, and analyzing them one by one. In addition, the process of making conclusions on water quality has not been integrated so that it can cause misclassification of water quality and prolong the work. In this study, an expert system was designed to monitor water quality that works in real time so that it can be accessed anytime and anywhere. The water quality analysis process is carried out with a fuzzy classifier realized using Arduino Mega 2560. The fuzzy input variables include the pH value, total dissolved solids (TDS), and turbidity or turbidity. A fuzzy inference system is used to classify water quality into three classes, namely good (meets quality standards), ordinary, and bad (polluted). The expert system of success provides inference results with a 100% success percentage. The results of monitoring and water quality classification can be accessed online using the Internet of Things (IoT) ThingSpeak platform