Water Quality Classification Research Articles

Intelligent water quality prediction system with a hybrid CNN–LSTM model

ABSTRACT Water pollution remains a longstanding challenge globally, prompting substantial investment in water quality protection. The integration of advanced machine learning models offers promising avenues for accurate water quality prediction, enabling proactive measures to safeguard water sources. Presently, water quality assessment relies predominantly on physical and chemical metrics. This study developed MultiLayer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), long short-term memory (LSTM), and a hybrid CNN–LSTM model to forecast pH and dissolved oxygen (DO) levels. Results demonstrated the hybrid model's superior performance, with mean squared errors (MSEs) of 0.0015 and 0.0361 for pH and DO prediction, respectively. For Water Quality Classification (WQC), Random Forest (RF), k-Nearest Neighbors (kNNs), Support Vector Machine (SVM), and Light gradient Boosting Machine (Light GBM) were employed, with SVM achieving the highest accuracy at 88.75%. The research underscores the effectiveness of the CNN–LSTM model in predicting pH and DO levels. Leveraging these predictions as inputs to the SVM model offers valuable insights, particularly in regions where conventional monitoring methods face limitations. This streamlined approach, requiring only two parameters, signifies a significant advancement in accurate water quality prediction.

Delineation and Mapping of Groundwater Quality Assessment in Salem District, Tamil Nadu, India using GIS Techniques

Groundwater is a crucial natural resource with significant economic importance, supporting industrial activities, irrigation, and drinking water supplies. However, its extensive use for these purposes depletes water tables, which diminishes its future availability and leads to increased salinity, stream depletion, and land subsidence. A study was conducted to evaluate and map groundwater quality across different blocks in Salem district viz., Salem, Gangavalli, Thalaivasal, Attur, Pethanaickenpalayam, Valappady, Ayothiyapattinam, Yercaud, Panamarathupatty, Veerapandi, Edappadi, Sankari, Kadayampatti, Kolathur, Konganapuram, Magudanchavadi, Mecheri, Nangavalli, Omalur, and Tharamangalam. Sampling was conducted in February 2024, during which a total of 200 samples were collected and examined for pH, electrical conductivity, cations like Ca2+, Mg2+, Na+ and K+, anions like CO32-, HCO3-, SO42-, and Cl-. Based on the ionic concentration, the water quality parameters are derived such as Sodium Adsorption Ratio(SAR) and Residual Sodium Carbonate (RSC). The pH and EC values were ranged from 7.08 to 8.58 and 0.74 to 2.75 dS/m, respectively. The residual sodium carbonate (RSC) concentration ranged from -7.3 to 10.1 meq/L, while the sodium adsorption ratio (SAR) ranged from 0.7 to 9.7 meq/L. According to the CSSRI, Karnal Water Quality Classification, approximately 66.5 % of the samples fit into the good quality category, approximately 13% of the samples fit into the alkaline water category, and 20% of the samples fit into the saline water category in the Salem district. Using this classification, thematic maps depicting groundwater quality in the Salem district were generated with ArcGIS software. The study concludes that the majority of the samples are classified as good-quality water, while saline and alkali water emerge as the next major concern. Using this saline water for irrigation can change the soil's physical properties and lower agricultural productivity. Thus, it's crucial to apply soil amendments like gypsum and provide proper drainage to avoid long-term soil damage.

Evaluation of Groundwater Quality Through Identification of Potential Contaminant

Groundwater, is crucial for human consumption and industrial purposes, demands continuous monitoring to assess quality standards. This study conducts a comprehensive evaluation of groundwater quality to assess its overall condition and identify potential contaminants. The research predicts the presence and levels of contaminants such as heavy metals, organic pollutants, and microbial agents using hydrogeological studies, chemical analysis, and statistical modelling. A covariance analysis identified places with low water quality. Analysis shows most samples satisfy drinking water requirements. A consolidated map illustrates a significant expanse suitable for domestic and drinking purposes, particularly in terms of drinking water quality. However, water quality in 2467.09 sq. km is deemed unacceptable. Further analysis, including correlation, ANOVA, and t-tests such as One Sample Test, Bayesian Statistics, and Power Analysis, identifies 836.87 sq. km under the category of maximum permissible water quality and 9.19 sq. km as highly desirable for drinking and domestic use.

Remote Sensing Inversion of Water Quality Grades Using a Stacked Generalization Approach

Understanding water quality is crucial for environmental management and policy formulation. However, existing methods for assessing water quality are often unable to fully integrate with multi-source remote sensing data. This study introduces a method that employs a stacking algorithm within the Google Earth Engine (GEE) for classifying water quality grades in the Songhua River Basin (SHRB). By leveraging the strengths of multiple machine learning models, the Stacked Generalization (SG) model achieved an accuracy of 91.67%, significantly enhancing classification performance compared to traditional approaches. Additionally, the analysis revealed substantial correlations between the normalized difference vegetation index (NDVI) and precipitation with water quality grades. These findings underscore the efficacy of this method for effective water quality monitoring and its implications for understanding the influence of natural factors on water pollution.

Machine learning framework for predicting water quality classification

ABSTRACT Groundwater serves as the source for nearly half of the world's drinking water, yet understanding of global groundwater resources remains incomplete, and management of aquifers falls short, particularly concerning groundwater quality. This research offers insights into the groundwater quality in 242 stations of Maharashtra and Union Territory of Dadra and Nagar Haveli and nine parameters (pH, TDS, TH, Calcium (Ca2+), Magnesium (Mg2+), Chloride (Cl−), Sulphate (SO42−), Nitrate (NO3−), Fluoride (F−)) were considered for computing the Water Quality Index (WQI) and hence Water Quality Classification (WQC) based on Water Quality Index (WQI). This research introduces the utilisation of Machine Learning (ML) models, specifically, Random Forest, Adaptive Boosting (AdaBoost), Gradient Boosting, XGBoost, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) model for predicting WQC and models are tested. Grid search method as a hyperparameter tuning of parameters is utilized to achieve the best possible performance of ML models. The performance metrics that are used for evaluating and reporting the performance of classification models are Accuracy, Precision, Recall or Sensitivity, F1 Score. SVM achieved the highest performance in predicting WQC. With accurate predictions of WQC, these findings have the potential to enhance NEP concerning water resources by facilitating ongoing improvements in water quality.

Machine Learning-Based Water Quality Classification Assessment

Machine Learning-Based Water Quality Classification Assessment

Predicting and Evaluating Water Quality using Machine Learning in Maharashtra, India

Water quality is critical for public health and environmental sustainability, necessitating effective monitoring to prevent contamination. In this study, we focus on predicting and evaluating water quality in Maharashtra, India, using machine learning techniques. Groundwater contamination in Maharashtra is a significant issue due to poor waste management, yet research in this area is limited. Traditional water quality monitoring methods involve complex calculations based on fixed parameters, which can lead to errors. This study aims to streamline the monitoring process by identifying the most significant features, thereby saving time, money, and energy. We calculated the Water Quality Index (WQI) using the Weighted Arithmetic Mean method, analyzing data from 2012 to 2022 from the National Water Monitoring Program in India. The analysis identified three key parameters, BOD, pH, and Fecal Coliform, as most correlated with the WQI. Machine learning techniques, including regression and classification, were employed to predict WQI and Water Quality Classification (WQC). The results indicate that Polynomial Regression and Ridge Regression achieved high accuracy in predicting the WQI, while the Decision Tree classifier excelled in WQC classification. This research demonstrates the potential of machine learning to enhance water quality monitoring, offering a cost-effective solution for managing water resources in Maharashtra.

Long-term dynamics of the heterоtrophic bacterioplankton development in the mouth of the Usinsky bay of the Kuibyshev reservoir

Data of our long-term observations of the bacterioplankton development in the mouth section of the Usinsky bay (the Kuibyshev reservoir) during the summer–autumn periods are presented. The total abundance of heterotrophic bacterioplankton varied within (1.61–7.44)×106 cells/mL, the biomass was 39.01–249.53 µgC/L, which corresponds to III–V water quality classes. Between 2010 and 2017 the total abundance of heterotrophic bacterioplankton was nonmonotonically decreasing, and since 2021 its significant increase is recorded. Among heterotrophic bacteria, single freefloating cells predominated, mainly cocci and coccobacilli, and the proportion of rod-shaped cells increased during cyanobacterial bloom. Picocyanobacteria and picodetritus particles were almost always present in plankton, but their average contribution to the total organic carbon of picoseston was insignificant.

Chemical composition of sediment and macrozoobenthos of small urban lakes, the Republic of Karelia, Russia

Assessing the benthic communities in water bodies under increasing anthropogenic pressure seems to be an urgent task of scientific research aimed at short-term and long-term monitoring of water bodies. This study focuses on the chemical composition of modern sediment and the current state of macrozoobenthos of small lakes in the Republic of Karelia (Kitaiskoe and Plotichie) influenced by anthropogenic factors. It was discovered that the lakes of Medvezhyegorsk have a higher concentration of heavy metals (such as lead (Pb), cadmium (Cd), molybdenum (Mo), and antimony (Sb),) compared to the Earth’s crust and natural background levels. The current study established the significant impact of industry and transportation on the movement and build up of pollutants in these lakes. The qualitative and quantitative parameters analysed for the benthic communities in the littoral and profundal zones included the species diversity, the structure of dominant species, and their percentage in the samples. According to the level of macrozoobenthos development, both reservoirs (lakes) were classified as mesotrophic, and according to the values of the chironomid index “K” as moderately polluted. The Pantle–Buck method (saprobic index) showed that the lakes can be classified as polluted (water quality class 4). Macrozoobenthos groups most tolerant to environmental conditions, for example, Chironomidae larvae, prevailed in the studied urban lakes. The economic development of the lakes leads to ecosystem transformation and long-term eutrophication over time affecting the biotic indicators of surface water quality. The results obtained can serve as a basis for complex environmental monitoring of the urbanized territories in the taiga zone.

Revealing the distribution of synthetic musks in Chinese estuarine sediments driven by natural and anthropogenic factors

Synthetic musks (SMs) commonly used in personal care products can accumulate in the estuarine environment, but influencing factors on their distribution at large-scale region remain largely unexplored. Herein, surface sediment samples from 18 main estuaries of China and two river outlets in the Yangtze River Estuary were collected to discern the spatial and temporal variations of SMs. Moreover, fourteen influencing factors consisting of natural and anthropogenic parameters were scrutinized and their significance were analyzed by using Spearman’s rank correlation and Random Forest. The widespread distribution of SMs were observed in Chinese estuarine sediments with the levels ranging from < reporting limit to 28 ng g-1 on a basis of dry weight (mean: 3.5 ng g-1). Predominated polycyclic musks shared similar sources both spatially and temporally. Positive correlation was found between SMs and total organic carbon in sediments, whereas the SM distribution was strongly influenced by regional anthropogenic activities. Regional population density was the primary influencing factor, followed by gross domestic product per unit area and wet deposition of particulate matters. A good correlation between SMs and water quality category indicated SMs could serve as an indicator for water quality. To the best of our knowledge, this is the first study to identify the main influencing factors on SM distribution in estuarine sediments, aiming to better understand the distribution and fate of emerging organic chemicals in the estuarine environment.

Data-Driven Techniques and Data Analytics in Water Treatment Facilities: Innovative Safety Protocols and Optimization

Aim: To examine harnessing of data-driven techniques and data analytics in water treatment facilities considering innovative safety protocols and process optimization. Problem Statement: The most significant part of human existence and industrial operations has been linked to water which often becomes vulnerable to hazardous contaminants which are brought on through natural processes and human activity. Significance of Study: The use of water treatment facilities in order to make water a sustainable natural resource for the whole world is vital. To achieve this, it is imperative to monitor and classify water quality. Methodology: Recent literature materials in form of books, journals and relevant published articles in the area of data-driven techniques and data analytics in water treatment facilities were consulted. Discussion: This review article has critically examined harnessing of data-driven and data analytics in water treatment facilities with consideration also given to innovative safety protocols and process optimization. The basic fundamental principle of water treatment facilities were discussed alongside the application of data-driven techniques. Safety protocols in water treatment facilities were discussed. Data driven techniques in water treatment facilities and applications of machine learning and artificial intelligence techniques to water treatment were explained. It was noticed that AI-Driven solutions transforms real-time water quality analysis and offers a proactive approach to water treatment. The integration of machine learning and AI algorithms capabilities in water treatment facilities can now respond quickly to fluctuations and continuously monitor key parameters fluctuations in water quality. Consideration was given to artificial intelligence as data analytics optimization tool for water treatment facilities. Future prospects, limitations and challenges of the study were stated. Conclusion: AI algorithms and historical data can be harnessed into water treatment facilities in order to assess performance patterns, predict equipment malfunctions and proactively plan the maintenance activities.

Plankton and contour algal communities in the Ukrainian section of the Western Bug River and its tributaries

The paper deals with spatial dynamics of cell count, biomass, dominant species complexes, information diversity of planktonic and contour algal communities in the Western Bug River and its tributaries. The trophic state and water quality of the rivers under study have been assessed. The spatial heterogeneity of phytoplankton, microphytobenthos and phytoperiphyton brought about high cell count and biomass values during the low-water summer-autumn season. The cell count and biomass have been shown to increase from the upper reaches downstream, correlating with the river bed width. High quantitative diversity of algal communities was due to Bacillariophyta dominance. Cyanobacteria and Chlorophyta were recorded as subdominants. The trophic state of the aquatic ecosystems under study varied between oligotrophic and eutrophic. The Shannon’s index made up 1.58–4.62 bit/cell and 1.60–4.40 bit/mg. The trophic state and information diversity assessed according to contour algal communities were higher than according to phytoplankton. This is indicative of the clear water regime forming in the rivers under study during the low-water summer-autumn season. The obtained findings differ from the data, published earlier for the Kaniv Water Reservoir, where the primary role belonged to phytoplankton. The spatial heterogeneity of algal communities is related to the dominant complexes structure. As a rule, these are monodominant Bacillariophyta complexes or oligodominant Bacillariophyta – Cyanobacteria or Bacillariophyta – Chlorophyta complexes. The water quality assessment according to the abiotic variables and saprobiologic characteristics has shown that the modal classes of water quality are the 2nd–3rd classes (clean waters – satisfactory clean waters). Therefore, the water quality of the Ukrainian section of the Western Bug River and its tributaries does not pose any substantial hazard to the adjacent European countries.

Evaluation of contaminated groundwater for excessive heavy metal presence and its further assessment of the potential risk to public health.

Water plays a significant role in human life. However, the contamination of groundwater by heavy metals (HMs) has profound implications for public health. Industrialization, urbanization, and agricultural activities are turning out to be major causes for the increasing concentration of HMs in rapidly industrializing areas like Rohtak district, Haryana, India. The current study aimed at evaluating and predicting the health hazards associated with the radical rise of HMs in the groundwater of Rohtak district. For this purpose, 45 seasonal-based groundwater samples were collected from five blocks in Rohtak district, namely Kalanaur, Meham, Lakhan Majra, Rohtak City, and Sampla, both during pre- and post-monsoon seasons. Besides physicochemical analysis, these groundwater samples were analyzed for the contamination of HMs. The findings revealed that groundwater samples were relatively more contaminated during the post-monsoon period rather than pre-monsoon. The water quality index (WQI), devised to classify water quality into specific classes, depicted the Kalanaur region as "very poor." Another index named the HM pollution index (HPI) denoted the levels of HMs and categorized Kalanaur as most deteriorated, followed by Meham, Lakhan Majra, Sampla, and Rohtak City. Additionally, principal component analysis (PCA) was employed that showed a significant variation in the distribution pattern of HMs, with the major load being attributed to PC1 and PC2 for both seasons. Pearson's correlation analysis indicated a significant association of pH (R2 = 0.917) with HMs (specifically for Cd and Cr). In terms of health risk assessment, carcinogenic human health risk due to Pb and Cr was found to be higher in children than adults. Non-carcinogenic risk, indicative of harmful human health effects, apart from cancer, was calculated in terms of hazard quotient (HQ) and hazard index (HI). Results of the same, designated "children" as a vulnerable category compared with "adults," especially in the Kalanaur, Sampla, and Rohtak City blocks of the study area. The results thus reiterated that Kalanaur is the most contaminated block among the five blocks chosen and should be given urgent attention. The study holds importance as it provides a framework regarding the methodology that should be adapted for the evaluation, management, and protection of groundwater at a regional level, which could further be replicated by environmentalists and hydrogeologists across the world. PRACTITIONER POINTS: Water logging is one of the most common problems in Kalanaur block of Rohtak district, responsible for causing groundwater pollution. Cadmium and lead pollution was prevalent in Rohtak due to electroplating industries, paint industry, automobile sector, and industrial discharge. Bioremediation is one of the suitable techniques that can be used for the treatment of groundwater that involves the use of microorganisms. Efficient use of groundwater resources is necessary for sustainable development.

Double-transfer learning-based least squares wavelet support vector machine for water quality classification

In the context of intelligent wastewater interception systems, the enhancement of decision control capability heavily relies on precise water quality classification outcomes. Nonetheless, conventional classification techniques encounter challenges in attaining satisfactory accuracy because of the intricate interplay between feature parameters of water quality and the imbalanced distribution of samples across different classes. In this paper, a least squares wavelet support vector machine (LSWSVM) is proposed with a double-transfer learning (DTL) strategy and an enhanced adaptive differential evolution (EADE) algorithm, referred to as DTL-EADE-LSWSVM. Firstly, the radial basis function is replaced by a wavelet function with multiresolution analysis to enhance the generalization ability of the LSWSVM. Secondly, three adaptive adjustment strategies for mutation factor, crossover probability and population size are designed in the EADE algorithm. Then, the EADE algorithm is adopted to obtain the optimal penalty factor and the parameter of the wavelet kernel function of the LSWSVM. Thirdly, the DTL strategy is developed to transfer the classification labels and model knowledge of the LSWSVM as well as the optimal population and optimal parameters of the EADE in the source domain to the target domain to improve the optimization efficiency and classification performance of the model in the target domain. Finally, the classification accuracy of the class imbalance samples is improved by reshaping the objective function. The experimental results indicate that the accuracy of the proposed DTL-EADE-LSWSVM classification model on balanced and imbalanced datasets is 92.5 % and 92.4 %, respectively, which is better than that of neural networks, stochastic deep forests and classical SVMs. In addition, the proposed DTL strategy has a stronger knowledge transfer capability than the single transfer learning strategy. The proposed DTL-EADE-LSWSVM is fully capable of classifying water quality in wastewater intercepting systems.

Interpretable prediction, classification and regulation of water quality: A case study of Poyang Lake, China

Effective identification and regulation of water quality impact factors is essential for water resource management and environmental protection. However, the complex coupling of water quality systems poses a significant challenge to this task. This study proposes coherent model for water quality prediction, classification and regulation based on interpretable machine learning. The decomposition-reconstruction module is used to transform non-stationary water quality series into stationary series while effectively reducing the feature dimensions. Spatiotemporal multi-source data is introduced by using the Maximum Information Coefficient (MIC) for feature selection. The Temporal Convolutional Network (TCN) is used to extract the temporal features of different variables, followed by the introduction of External Attention mechanism (EA) to construct the relationship between these features. Finally, the target water quality sequence is simulated using Gated Recurrent Unit (GRU). The proposed model was applied to Poyang Lake in China to predict six water quality indicators: ammonia nitrogen (NH3-N), dissolved oxygen (DO), pH, total nitrogen (TN), total phosphorus (TP), water temperature (WT). The water quality was then classified based on the prediction results using the XGBoost algorithm. The findings indicate that the proposed model's Nash-Sutcliff Efficiency (NSE) value ranges from 0.88 to 0.99, surpassing that of the benchmark model, and demonstrates strong interval prediction performance. The results highlight the superior performance of the XGBoost algorithm (with an accuracy of 0.89) in addressing water quality classification issues, particularly in cases of category imbalance. Subsequently, interpretability analysis using the SHapley Additive exPlanation (SHAP) method revealed that the model is capable of learning relationships between different variables and there exists a possibility of learning the physical laws. Ultimately, this study proposes a water quality regulation mechanism that improves TN and DO levels by stepwise changing the magnitude of water temperature, which significantly improves in the case of data limitations. In conclusion, this study presents an overall framework for integrating water quality prediction, classification and improvement for the first time, forming a complete set of water quality early warning and improvement management strategies. This framework provides new ideas and ways for lake water quality management.

Spatiotemporal Dynamics of Plankton Communities in the Chongqing Section of the National Nature Reserve for Rare and Endemic Fishes in the Upper Yangtze River

In order to understand the community structure of plankton and environmental factors in the Chongqing section of the National Nature Reserve for Rare and Endemic Fishes (referred to as the “Reserve”) along the upper Yangtze River, this study investigated phytoplankton and zooplankton in the water body from 2021 to 2022. The results revealed a diverse phytoplankton community with 243 species from 105 genera and 8 phyla, dominated by Bacillariophyta and Chlorophyta. Phytoplankton showed average densities of 1.7 × 106 cells/L and biomass of 2.6221 mg/L, following a seasonal pattern of summer &gt; spring &gt; winter. Zooplankton analysis identified 141 species from 77 genera and 4 phyla, with rotifers most abundant, followed by protozoa. Zooplankton displayed average densities of 0.17 × 104 ind./L and biomass of 0.3226 mg/L, also following a seasonal pattern of summer &gt; spring &gt; winter. Total phosphorus (TP) emerged as the primary environmental factor influencing plankton community structure, positively correlating with phytoplankton density and zooplankton biomass. Plankton biodiversity indices classified water quality in the Chongqing section of the “Reserve” as oligo-/mesotrophic. Overall, plankton diversity in this section is notably rich, with similar species composition between mainstems and tributaries but seasonal variations in community structure. While mainstem water quality generally meets standards, some tributaries exhibit varying degrees of pollution, underscoring the need for improved ecological management and protection measures. This is crucial for maintaining the sustainability of the ecosystem.

Deciphering anthropogenic impact: A multifaceted statistical analysis of physico-chemical parameters in a catchment with limited water quality data

The purpose of the paper was to identify and evaluate the impact of anthropogenic factors on water quality in a catchment with limited water quality data. The Serafa stream flowing through the Lesser Poland region was selected for the study. Changes in the content of 21 selected physico-chemical indicators were evaluated at five monitoring sites of the Serafa over a 12-month period. Cluster analysis, Kruskal-Wallis test, factor analysis with varimax rotation method, and surface water quality classification were used to develop the results. It was found that of the 21 physico-chemical indicators tested, for seven of them (EC, TDS, Cl-, Mg2+, Na+, K+ and pH), there were statistically significant differences between the values at point 1 and the ones at the other points (2−5), at monitoring site 1, the values of these indicators were lower compared to the rest of the catchment. The study of physico-chemical indicators showed that the water qualified for below good status, due to exceeded values of EC, BOD5, TDS, Cl-, Ca2+, Mg2+, pH, P–PO43-, N–NO2-. The evaluation of anthropogenic factors affecting the water resources of the catchment showed that the quality of water in the Serafa catchment is mainly influenced by improper wastewater management.

Transfer Learning Artificial Neural Network-based Ensemble Voting of Water Quality Classification for Different Types of Farming

Transfer Learning Artificial Neural Network-based Ensemble Voting of Water Quality Classification for Different Types of Farming

Spatial Distribution of Water Quality Classes of Rawa Pening Lake

Abstract Rawa Pening Lake is a source of water for irrigation and clean water for the people around the lake. The quality of water is the primary concern for sustainable functioning. This study aims to examine the water quality status of the lake under government regulations. The variables are temperature, total dissolved solid (TDS), total suspended solid (TSS), Escherichia coli (E. coli), dissolved oxygen (DO), biological oxygen demand (BOD), chemical oxygen demand, phosphate, nitrate, and oil. The study was conducted during the rainy season, from September to November 2020. It’s because of the season that farmers and the community use more of the lake water. The method used is purposive sampling, where a total of 12 locations represent each village, inlet, and outlet. The data analysis used is Storet to determine the water quality class and Inverse Distance Weighted (IDW) for the spatial distribution of water quality classes. The results showed that the water quality class of the lake suffered mild pollution. TSS and DO were variables that influenced that condition. It can be concluded that the lake has sucked sedimentation as a result of the deposits of mud and sand, which can damage the ecosystem of the lake.

Study on environmental monitoring classification system based on improved bayesian algorithm

Abstract The commonly used methods for classifying water quality data are based on water quality parameters. The naive Bayesian classification method can be applied to substitute different evaluation criteria and selected water quality parameters for different water bodies. Compared to other water quality data classification methods, naive Bayesian classification methods have advantages such as simple calculation, high classification accuracy, and strong universality. However, this method overlooks the correlation between various water quality parameters and categories. To address the issues of poor universality, computational complexity, and low accuracy of traditional water quality data classification methods, a water quality data classification method based on weighted naive Bayes is proposed. This method comprehensively considers the impact of water quality attributes and their values on the classification results and replaces the original naive Bayes with weighted attribute conditional probabilities to make the classification results as close as possible to the actual category of the sample. The results indicate that this method exceeds 94% accuracy and can be directly utilized as a water quality classification module in water quality monitoring systems.