Tool For Water Quality Management Research Articles

Comparison of novel physics-guided machine learning models with empirical equations for predicting longitudinal dispersion coefficient in diverse natural river systems

Accurate calculation of the longitudinal dispersion coefficient (LDC) is crucial for assessing river fate and transport processes. Traditional methods, including experimental, analytical, and empirical equations, each have their challenges, such as complexity and susceptibility to errors. This study introduces and evaluates advanced physics-guided machine learning (ML) models, including hybrid hydrodynamic-particle simulation (HHPS), physics-enhanced ML (PEML), and physics-regularized regression trees (PRRT). Our dataset includes hydraulic and geometric parameters collected from 50 diverse rivers across the US and the UK, encompassing variables such as river width (W), flow depth (H), average flow velocity (U), flow shear velocity (U*), concentration of the solute (μgL) and LDC (ε). Input parameters were dimensioned using the UU∗ and WHratios, while the dimensionless LDC (εHU∗) served as the model output. By embedding core hydrodynamic principles such as continuity, mass and momentum conservation, and Navier-Stokes equations into the ML algorithms, these models achieved high predictive accuracy. Specifically, the HHPS model reached a coefficient of determination of 0.997, and both PEML and PRRT demonstrated Nash-Sutcliffe efficiencies exceeding 0.950, significantly outperforming traditional empirical equations. Additionally, SHapley Additive exPlanations (SHAP) sensitivity analysis revealed the substantial influence of channel width and flow conditions on LDC predictions. Our study highlights the superior performance of physics-guided ML models in providing accurate and reliable tools for river water quality management, demonstrating their substantial improvements over traditional methods and their potential broader applications in environmental studies.

Integrating community perceptions, scientific data and geospatial tools for sustainable water quality management

Globally, ecosystems and human health are at risk due to declining river water quality. The current study focuses on the River Asan, Uttarakhand, which faces significant water quality challenges due to various environmental, industrial, and domestic factors. This research presents an exhaustive study that intricately blends local community perceptions with scientific data, employing Geographic Information Systems to map water quality across seven critical locations along the river. Participatory Rural Appraisal (PRA) and systematic water quality test methods were applied to find the objective of this study. The research highlights the importance of considering social, cultural, and environmental factors in understanding water quality issues. The detailed, location-specific analysis, enriched by the vast array of community insights, offers a unique lens through which the environmental challenges at each site are examined. Significant findings represent that in Nayagaon, from 2019 to 2023, rising water temperature (1.6 °C increase) and decreasing pH (7.3–6.5) were observed. Reduced dissolved oxygen (9.7–6.1 mg/L) aligns with community concerns about water quality, highlighting the urgent need for interventions to protect the Asan River and its dependent communities. Integrating local perceptions with scientific data provides a nuanced understanding of water quality issues, emphasizing the urgent need for targeted interventions to safeguard the river ecosystem and the well-being of the communities dependent on it, thereby offering valuable insights for sustainable environmental management.

Prediction of Diffuse Attenuation Coefficient Based on Informer: A Case Study of Hangzhou Bay and Beibu Gulf

Marine water quality significantly impacts human livelihoods and production such as fisheries, aquaculture, and tourism. Satellite remote sensing facilitates the predictions of large-area marine water quality without the need for frequent field work and sampling. Prediction of diffuse attenuation coefficient (Kd), which describes the speed at which light decays as it travels through water, obtained from satellite-derived ocean color products can reflect the overall water quality trends. However, current models inadequately explore the complex nonlinear features of Kd, and there are difficulties in achieving accurate long-term predictions and optimal computational efficiency. This study innovatively proposes a model called Remote Sensing-Informer-based Kd Prediction (RSIKP). The proposed RSIKP is characterized by a distinctive Multi-head ProbSparse self-attention mechanism and generative decoding structure. It is designed to comprehensively and accurately capture the long-term variation characteristics of Kd in complex water environments while avoiding error accumulation, which has a significant advantage in multi-dataset experiments due to its high efficiency in long-term prediction. A multi-dataset experiment is conducted at different prediction steps, using 70 datasets corresponding to 70 study areas in Hangzhou Bay and Beibu Gulf. The results show that RSIKP outperforms the five prediction models based on Artificial Neural Networks (ANN, Convolutional Neural Networks (CNN), Gated Recurrent Unit (GRU), Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN), and Long Short-Term Memory Networks (LSTM)). RSIKP captures the complex influences on Kd more effectively to achieve higher prediction accuracy compared to other models. It shows a mean improvement of 20.6%, 31.1%, and 22.9% on Mean Absolute Error (MAE), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE). Particularly notable is its outstanding performance in the long time-series predictions of 60 days. This study develops a cost-effective and accurate method of marine water quality prediction, providing an effective prediction tool for marine water quality management.

A hybrid prediction model of dissolved oxygen concentration based on secondary decomposition and bidirectional gate recurrent unit.

Dissolved oxygen is one of the important comprehensive indicators of river water quality, which reflects the degree of pollution in the water body. Monitoring and predicting dissolved oxygen are an important tool for water quality management, which helps to effectively maintain water ecological balance and prevent environmental problems. A single model cannot describe the dynamic characteristics of dissolved oxygen sequence, which affects the prediction accuracy. In order to obtain more accurate dissolved oxygen prediction results, decomposition techniques are commonly used to extract the main fluctuations and trends of water quality sequences. However, the high-frequency modes obtained from decomposition are still unstable. To solve this problem, this paper proposed a hybrid prediction model of dissolved oxygen concentration based on secondary decomposition and bidirectional gate recurrent unit. Firstly, dissolved oxygen sequence is preliminarily decomposed by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and obtain several intrinsic mode functions (IMF). The fuzzy entropy (FE) is calculated to quantify the complexity of the IMF. Then, variational mode decomposition improved by northern goshawk optimization is used to decompose the IMF with higher entropy. The nonlinearity and instability of the sequence are further weakened. Finally, the bidirectional gate recurrent unit (BiGRU) neural network is used to predict each IMF component, and the final prediction result is obtained by reconstructing the prediction results of each component. In order to verify the effectiveness of the proposed model, this paper selects the dissolved oxygen data of Xin'anjiang Reservoir as the research object. The experimental results show that the RMSE, MAE, MAPE, and R2 of the proposed model are 0.1164, 0.0894, 1.0403%, and 0.9939, respectively, which is best among other comparative prediction models (BP, LSTM, GRU, BiGRU, EMD-BiGRU, CEEMDAN-BiGRU, VMD-BiGRU, and GNO-VMD-BiGRU). Therefore, this model effectively deals with high volatility and nonlinear dissolved oxygen data and provides reference for water environment management and ecological protection.

Selection of a diagnostic tool for microbial water quality monitoring and management of faecal contamination of water sources in rural communities

The aim of the current study was to evaluate, validate and select microbial water quality monitoring tools to establish their suitability and feasibility for use in rural communities. The monitoring of water quality was performed at three different levels: i) basic level focusing on sanitary inspection and hydrogen sulphide (H2S) test; ii) intermediate level via enumeration of faecal indicator bacteria (faecal coliforms, Escherichia coli, Enterococcus spp. and Clostridium perfringens); and iii) advanced level based on qPCR detecting host-associated genetic markers (BacHum, BacCow, Cytb, Pig-2-Bac, and BacCan) and pathogens (Vibrio cholerae, Escherichia coli O157:H7, and Shiga toxin-producing Escherichia coli). A positive correlation was recorded between sanitary risk and faecal coliforms (r = 0.613 and p < 0.002), E. coli (r = 0.589 and p < 0.003), and Enterococcus spp. (r = 0.625 and p < 0.003). The H2S test showed positive correlations with sanitary risk score (r = 0.623; p < 0.003), faecal coliforms (r = 0.809; p < 0.001), E. coli (r = 0.779; p < 0.001) and Enterococcus spp. (r = 0.799; p < 0.001). Similar correlation patterns were also found with advanced techniques used for detecting host-associated genetic markers, excepted between Clostridium perfringens, and Pig-2-Bac (pig), BacCan (dog), and V. cholerae. The H2S test and sanitary inspections are therefore suitable and cost-effective tools to capacitate rural areas at household level for the monitoring of faecal contamination and management of water sources.

Aquaculture 4.0: hybrid neural network multivariate water quality parameters forecasting model

This study examined the efficiency of hybrid deep neural network and multivariate water quality forecasting model in aquaculture ecosystem. Accurate forecasting of critical water quality parameters can allow for timely identification of possible problem areas and enable decision-makers to take pre-emptive remedial actions that can significantly improve water quality management in aquaculture industry. A novel hybrid deep learning neural network multivariate water quality parameters forecasting model is developed with the aid of ensemble empirical mode decomposition (EEMD) method, deep learning long-short term memory (LSTM) neural network (NN), and multivariate linear regression (MLR) method. The presented water quality forecasting model (shortened as EEMD–MLR–LSTM NN model) is developed using multivariate time-series water quality sensor data collected from Loch Duart company, a Salmon offshore aquaculture farm based around Scourie, northwest Scotland. The performance of the novel hybrid water quality forecasting model is validated by comparing the forecast result with measured water quality parameters data and the real Phytoplankton data count from the aquaculture farm. The forecast accuracy of the results suggests that the novel hybrid water quality forecasting model can be used as a valuable support tool for water quality management in aquaculture industries.

Deriving analytical expressions of the spatial information entropy index on riverine water quality dynamics

Information entropy theory has been largely applied in hydrology and water resource engineering. Recently, entropy theory has received significant attention for describing reactive solute mixing and transport processes in ground water and surface water and for its applications in water quality management. However, analytical expressions of the entropy index of riverine water quality dynamics are often not included in the literature. In this study, the analytical expressions of the spatial information entropy index (Gx) in the 1D steady-state transport process under full-extent observation and tracking observations are derived after the definition of the system boundary and probability space. The expressions of Gx were successfully validated by field data from two tracer experiments, and the different characteristics of Gx under different riverine hydraulic situations were uncovered. The formula of Gx shows a reasonable linkage with the Peclet number (Pe) in hydrodynamics. This indicates that Gx is a physical quantity describing or linking to the real world more than a statistical index, and in practice, similar decision or management measurements based on entropy theory can be made for rivers with similar Pe conditions. Hydrologists will benefit in many ways from analytical expressions, such as theoretical analysis, quick calculation of the entropy index, preliminary engineering design, etc. A clearly defined example of maximum entropy time (tGmax) and its application in water quality evaluation, monitoring optimization and pollution source identification are demonstrated. These new findings will provide a convenient tool for catchment water quality management.

Application of genetic programming in presenting novel equations for longitudinal dispersion coefficient in natural streams considering rivers geometry - Implementation in assimilation capacity simulation

Precise estimation of the longitudinal dispersion coefficient (LDC) is crucial for the accurate simulation of water quality management tools such as assimilation capacity. Previous research analyzed the LDC of natural streams in two general categories: ignoring or considering the river sinuosity (σ). Genetic programming (GP) is used in this study to investigate both mentioned categories by applying two experimental datasets from 56 to 24 different rivers worldwide. The first proposed LDC equation of this research (without σ) improves the amounts of statistical measures R2 (Determination Coefficient), OI (Overall Index), NSE (Nash-Sutcliffe Efficiency), WI (Willmott's Index of Agreement), RMSE (Root Mean Square Error), and MAE (Mean Absolute Error) by 3.75%, 4.71%, 7.81%, 0.85%, 13.72%, and 0.68%, respectively, compared to the best values of these indicators in the previous investigations. Regarding the second category, relative and absolute sensitivity analyses are conducted, which reveal that σ is the most influential parameter in the accurate prediction of the LDC among all hydraulics and geometric parameters of the river. This part of the investigation presents four unique LDC equations that closely match the experimental results. Significant improvement of the most accurate presented LDC for statistical indices R2, OI, NSE, WI, RMSE, MAE, and accuracy percentage are obtained equal to 3.27%, 2.41%, 3.16%, 0.81%, 35.1%, 24.47%, 3.8%, respectively, in comparison with the best previous relations. Also, a new indicator for measuring the efficiency of mathematical equations called Mean Normalized Statistical Index (MNSI) is introduced and applied in different parts of this research. Finally, the assimilation capacity of the Kashafrud River is determined based on the analytical method of pollution propagation for three types of water demands utilizing the accurately presented LDC in 1993–2020. The average amount of river assimilation capacity using accurate LDC is simulated at 91.93 tons/day, much lower than the currently reported pollution entrance, which equals 540 tons/day.

Assessment of the water sources for potential channels of faecal contamination within Vhembe District Municipality using sanitary inspections and hydrogen sulphide test

Numerous human activities and poor sanitation management cause public health concern, particularly in rural communities without reliable water supply systems and resources for the monitoring of the quality of their water sources. This study assessed the relationship between observed sanitary risks and hydrogen sulphide (H2S) strip test results in the identification of faecal contamination of various water sources used at household level in rural areas of the Vhembe District Municipality. The highest percentage sanitary risk scores ranging from 50 to 100% were recorded for both river and dam water commonly used by the households for multiple purposes, including drinking. All the surface water samples (100%) also tested positive for H2S production, which is linked to the contamination of water sources by bacteria of faecal origin. The overall results showed a significant and positive correlation (r = 0.623, p = 0.003 in the wet season and r = 0.504, p = 0.017 in the dry season) between sanitary risk scores and H2S strip test results. In low resource settings, the use of sanitary inspections combined with the inexpensive and easy-to-use H2S strip tests can be effective as drinking water quality management tools to raise an awareness among community members of the faecal contamination of their water sources.

An advanced remote sensing retrieval method for urban non-optically active water quality parameters: An example from Shanghai

The optical insensitivity of non-optically active water quality parameters (NAWQPs) presents a significant challenge for remote sensing-based quantitative monitoring, which is an important tool for water quality assessment and management. Based on the analysis of the samples from Shanghai, China, it was found that the spectral morphological characteristics of the water body were obviously different under the combined effect of multiple NAWQPs. In view of this, in this paper, a machine learning method was proposed for the retrieval of urban NAWQPs by using multi-spectral scale morphological combined feature (MSMCF). The proposed method integrates both local and global spectral morphological features, and employs a multi-scale approach to enhance its applicability and stability, providing a more accurate and robust solution. To explore the applicability of the MSMCF method in retrieving urban NAWQPs, different methods were tested in terms of the retrieval accuracy and stability on the measured data and three different hyperspectral data. As can be seen from the results, the proposed method has good retrieval performance, which can be applied to hyperspectral data with different spectral resolutions with certain ability to suppress noise. Further analysis indicates that the sensitivity of each NAWQP to spectral morphological features varies. The research methods and findings in this paper can promote the development of hyperspectral and remote sensing technology in the prevention and treatment of urban water quality deterioration, and provide reference for related research.

Decision Support Tools for Water Quality Management

The sustainability of inland water resources worldwide is becoming increasingly endangered as climate change contributes to the human-induced problems of water supply scarcity and maldistribution [...]

Long-Term Water Quality Prediction Using Integrated Water Quality Indices and Advanced Deep Learning Models: A Case Study of Chaohu Lake, China, 2019–2022

The rapid development of urban industrialization has had many negative effects on the quality of water sources around cities. Long-term prediction of water quality can be of great help to the conservation of water environment. This case tries to use several popular deep learning models, such as RNN, LSTM, MLP, and Transformer-based models to predict the long-term integrated water quality index in the Chaohu Lake area. The dataset is derived from daily monitoring data from four monitoring sites within Chaohu Lake from 2019 to 2022, and the long-term prediction performance of the model is evaluated using MAE and MSE as evaluation metrics. The experimental results showed that all models selected in this case achieved good results within the study area, but Informer performed more prominently (MSE = 0.2455, MAE = 0.2449) as the length of the prediction series increased. Our results demonstrate the effectiveness of popular deep learning models in the field of WQI prediction, especially the significant advantage of transformer-based models represented by Informer in long-term water quality prediction, which will further provide an effective modern tool for water quality monitoring and management.

Machine learning-based prediction of harmful algal blooms in water supply reservoirs

Abstract Harmful algal blooms (HABs) pose a potential risk to human and ecosystem health. HAB occurrences are influenced by numerous environmental factors; thus, accurate predictions of HABs and explanations about the predictions are required to implement preventive water quality management. In this study, machine learning (ML) algorithms, i.e., random forest (RF) and extreme gradient boosting (XGB), were employed to predict HABs in eight water supply reservoirs in South Korea. The use of synthetic minority oversampling technique for addressing imbalanced HAB occurrences improved classification performance of the ML algorithms. Although RF and XGB resulted in marginal performance differences, XGB exhibited more stable performance in the presence of data imbalance. Furthermore, a post hoc explanation technique, Shapley additive explanation was employed to estimate relative feature importance. Among the input features, water temperature and concentrations of total nitrogen and total phosphorus appeared important in predicting HAB occurrences. The results suggest that the use of ML algorithms along with explanation methods increase the usefulness of predictive models as a decision-making tool for water quality management.

Distribution of human fecal marker genes and their association with pathogenic viruses in untreated wastewater determined using quantitative PCR

Quantitative microbial risk assessment (QMRA) of human health risks using human fecal marker genes (HFMGs) is an useful water quality management tool. To inform accurate QMRA analysis, generation of probability distribution functions for HFMGs, and reference pathogenic viruses can be improved by input of correlation and ratios based upon measurement of HFMGs and gene copies (GC) of pathogenic viruses in untreated wastewater. The concentrations of four HFMGs (Bacteroides HF183, Lachnospiraceae Lachno3, CrAssphage and pepper mild mottle virus (PMMoV)), and GC of three reference pathogenic viruses human adenovirus 40/41 (HAdV 40/41), human norovirus GI + GII HNoV GI + GII and enterovirus (EV) were measured in untreated wastewater samples collected over a period of 12 months from two wastewater treatment plants in Sydney, Australia using quantitative polymerase chain reaction (qPCR) and reverse transcription qPCR (RT-qPCR). Over the course of the study, the GC of potential pathogenic viruses were 3–5 orders of magnitude lower than HFMGs in untreated wastewater. The GC of pathogenic viruses were highly variable over the course of the study, which contrasted with the concentrations of HFMGs that were quite stable with little variation observed within and between WWTPs. Among the HFMGs, HF183, CrAssphage and PMMoV correlated well with pathogenic virus GC, whereas weak or negative correlations were observed between Lachno3 and pathogenic virus GC. While the two assessed WWTPs had dissimilar population service sizes, the ratios between log10 transformed pathogenic virus GC and HFMGs demonstrated similar central tendency and variability for the same combinations between WWTP A and WWTP B with no difference between the WWTPs. This suggests the widespread presence of these HFMGs in both populations serviced by these two WWTPs. The observed correlation and ratios of HFMGs and GC of reference pathogenic viruses can contribute to improved QMRA of human health risks in environmental waters subject to fresh sewer overflows.

Culture and molecular methods as complementary tools for water quality management

Bacterial communities in a full-scale drinking water treatment plant (DWTP) were characterized using matrix-assisted laser desorption/ionization time of flight mass-spectrometry (MALDI-TOF MS) to identify HPC isolates and the obtained results were compared to 16S rRNA (V4) metabarcoding data acquired in a previous study. Sixty-three samples were collected at nine stages of the potabilization process: river water and groundwater intake, decantation, sand filtration, ozonization, carbon filtration, reverse osmosis, the mixing chamber and post-chlorination drinking water. In total, 1807 bacterial colonies were isolated, 32 % of which were successfully identified to at least the genus level by MALDI-TOF MS using our previously developed Drinking Water Library. Trends in diversity were similar by both approaches, but differences were observed in the detection of taxa, especially at lower hierarchy levels. High bacterial diversity was observed in river and groundwater, where Proteobacteria predominated. The diversity decreased significantly after the chlorination step, where Bacillus sp. (Firmicutes) and an unknown genus of Obscuribacteraceae (Cyanobacteria) were the most prevalent genera according to MALDI-TOF MS and metabarcoding, respectively. The two approaches gave similar results for the decantation, sand filtration and mixing chamber steps, where the most abundant taxon was Flavobacterium. The combined use of these culture-based and culture-independent methods to characterize microbial populations may help to better understand the role of bacteria in water treatment and quality, which will be of value for DWTP management.

What is the relationship between land use and surface water quality? A review and prospects from remote sensing perspective.

Good surface water quality is critical to human health and ecology. Land use determines the surface water heat and material balance, which cause climate change and affect water quality. There are many factors affecting water quality degradation, and the process of influence is complex. As rivers, lakes, and other water bodies are used as environmental receiving carriers, evaluating and quantifying how impacts occur between land use types and surface water quality is extremely important. Based on the summary of published studies, we can see that (1) land use for agricultural and construction has a negative impact on surface water quality, while woodland use has a certain degree of improvement on surface water quality; (2) statistical methods used in relevant research mainly include correlation analysis, regression analysis, redundancy analysis, etc. Different methods have their own advantages and limitations; (3) in recent years, remote sensing monitoring technology has developed rapidly, and has developed into an effective tool for comprehensive water quality assessment and management. However, the increase in spatial resolution of remote sensing data has been accompanied by a surge in data volume, which has caused difficulties in information interpretation and other aspects.

A simple water clarity-turbidity index for the Great Lakes

There are a multitude of satellite-derived water clarity and turbidity indicators to support the decision making of environmental managers and policy makers. However, water quality dynamic ranges addressed by these indicators can differ significantly, subjecting non-expert users to potential pitfalls. Here we propose a satellite water clarity-turbidity index (CTI) as a simplified way to capture major changes in water clarity/turbidity across all water types in the Great Lakes. The CTI is defined to merge key information from three prerequisite variables derived from Visible Infrared Imaging Radiometer Suite (VIIRS) measurements, namely, the Secchi disk depth, the particulate backscattering coefficient, and the nephelometric turbidity, which are suitable for clear, intermediate, and turbid waters, respectively. Application to the Great Lakes shows that with one parameter, the CTI can illustrate major spatial and temporal patterns that are not entirely visible with each of the three original indicators alone. Using the CTI, we identified significant decrease in water turbidity in Lakes Michigan and Huron from 2000 to 2005, during which daily variability of CTI in August initially spiked and then gradually decreased most likely owing to diminishing whiting events. The CTI is a convenient and holistic assessment tool for water quality management.

Culture and Molecular Methods as Complementary Tools for Water Quality Management

Culture and Molecular Methods as Complementary Tools for Water Quality Management

Seasonal dynamics of chromophoric dissolved organic matter in Poyang Lake, the largest freshwater lake in China

Chromophoric dissolved organic matter (CDOM) plays a vital role in the biogeochemical cycles of elements in aquatic ecosystems. Seasonal dynamics of CDOM of the lake are sensitive indicators of the biogeochemical processes and water quality, which are critical to the water security of the lake. Thus, a field investigation of the CDOM and dissolved organic carbon (DOC) properties was conducted during four hydrological seasons in 2016 to track the temporal variability of CDOM and DOC properties and to explore the influence of rivers and wetlands on the quantity and quality of CDOM in Poyang Lake. The results showed that the alternations of flood and dry periods have a different influence on the quantity and quality of CDOM and DOC in the main lake and the river mouths districts. DOC and aromaticity in the main lake district were more influenced by seasonal variations, while CDOM concentrations and molecular weight in the river mouths were more affected. CDOM fluorescent components in both these districts varied obviously across the hydrological seasons. More terrestrial humic-like substances with higher aromaticity and lower DOC in the rising and flood season than in the dry and retreating season. The contributing rate of CDOM and its terrestrial humic-like substances from input rivers to the lake in the rising season can account for more than 50%, which was more than that in the flood season. Flooding causes wetlands to contribute a higher abundance of CDOM and DOC with lower aromaticity to the lake, contrary to the CDOM features in the flood season, highlighting the important role of wetlands in the organic carbon pool. The DOC can be modeled using CDOM fluorescent and optical parameters by the Support Vector Regression (SVR) method, which provides a tool for DOC dynamic monitoring and water quality management.

Research on Water Quality Simulation and Water Environmental Capacity in Lushui River Based on WASP Model

In recent years, the severe deterioration of water quality and eutrophication in the Yangtze River has brought much trouble to people’s lives. Because of this, numerous management departments have paid more and more attention to the treatment of the water environment. In order to respond to water environmental protection policy and provide management departments with a basis for refining water quality, this paper takes the Zhuzhou section of Yangtze River-Lushui watershed as its research object. First, we used the Water Quality Analysis Simulation Program (WASP) model as a tool, and obtained the pollution load using the FLUX method formula. During the calibration process, the sensitivity analysis method, the orthogonal design method, and the trial and error method were used. Then, we verified the results by using water quality monitoring data published by Zhuzhou Ecological Environment Bureau. Following that, the water environmental capacity of the Lushui River in normal, wet and dry periods was calculated using the WASP model: the chemical oxygen demand (COD) was 14,072.94 tons/yr, 17,147.7 tons/yr and 10,998.18 tons/yr, respectively; ammonia nitrogen (AN) was 469.098 tons/yr, 571.59 tons/yr and 366.606 tons/yr, respectively; and total phosphorus (TP) was 93.8196 tons/yr, 114.318 tons/yr and 73.3212 tons/yr, respectively. The results show that the WASP model is applicable and reliable and can be used as an effective tool for water quality prediction and management in this area.