Water Quality Forecasting Research Articles

Development of Predictive Models for "Very Poor" Beach Water Quality Gradings Using Class-Imbalance Learning.

Statistical water quality forecast models are useful tools to assist with beach management. In particular, multiple linear regression (MLR) models have been successfully developed for prediction of fecal indicator bacteria concentrations for beaches in river, lake, and marine environments. Nevertheless, an unresolved challenging issue is the reliable prediction of infrequent events of high bacterial concentrations to inform beach closure decisions to protect public health. The number of field data available for the infrequent events is typically an order of magnitude less than that for days when the water quality criterion is met-MLR models often perform poorly in predicting bacterial concentrations on days when the beaches should be closed. For beach management in Hong Kong, MLR models have been developed to predict beach water quality indices in terms of four gradings (BWQI-1 to 4) based on Escherichia coli (E. coli) concentrations. In this study, we propose an artificial intelligence (AI)-based binary classification (EasyEnsemble) model using class-imbalance learning to predict "very poor" occasions (BWQI-4)-when E. coli concentration exceeds 610 counts/100 mL. Models are developed for three marine beaches with different hydrographic and pollution characteristics using a 30 year data set spanning three periods with different water quality status. The model-data comparison over a wide range of conditions shows that the proposed method results in a significant improvement in the prediction of "very poor" water quality. The proposed class-imbalance method for predicting rare events has an F-score of 0.84, and it significantly outperforms MLR and classification tree (CT) models with corresponding F-scores of 0.39 and 0.69. A robust beach water quality forecast system can hence be developed using hybrid MLR-binary classification modeling.

Assessing the Performance of Deep Learning Algorithms for Short-Term Surface Water Quality Prediction

This study aimed to investigate the applicability of deep learning algorithms to (monthly) surface water quality forecasting. A comparison was made between the performance of an autoregressive integrated moving average (ARIMA) model and four deep learning models. All prediction algorithms, except for the ARIMA model working on a single variable, were tested with univariate inputs consisting of one of two dependent variables as well as multivariate inputs containing both dependent and independent variables. We found that deep learning models (6.31–18.78%, in terms of the mean absolute percentage error) showed better performance than the ARIMA model (27.32–404.54%) in univariate data sets, regardless of dependent variables. However, the accuracy of prediction was not improved for all dependent variables in the presence of other associated water quality variables. In addition, changes in the number of input variables, sliding window size (i.e., input and output time steps), and relevant variables (e.g., meteorological and discharge parameters) resulted in wide variation of the predictive accuracy of deep learning models, reaching as high as 377.97%. Therefore, a refined search identifying the optimal values on such influencing factors is recommended to achieve the best performance of any deep learning model in given multivariate data sets.

Forecasting Water Quality Index in Groundwater Using Artificial Neural Network

Groundwater quality monitoring in the vicinity of drilling sites is crucial for the protection of water resources. Selected physicochemical parameters of waters were marked in the study. The water was collected from 19 wells located close to a shale gas extraction site. The water quality index was determined from the obtained parameters. A secondary objective of the study was to test the capacity of the artificial neural network (ANN) methods to model the water quality index in groundwater. The number of ANN input parameters was optimized and limited to seven, which was derived using a multiple regression model. Subsequently, using the stepwise regression method, models with ever fewer variables were tested. The best parameters were obtained for a network with five input neurons (electrical conductivity, pH as well as calcium, magnesium and sodium ions), in addition to five neurons in the hidden layer. The results showed that the use of the parameters is a convenient approach to modeling water quality index with satisfactory and appropriate accuracy. Artificial neural network methods exhibited the capacity to predict water quality index at the desirable level of accuracy (RMSE = 0.651258, R = 0.9992 and R2 = 0.9984). Neural network models can thus be used to directly predict the quality of groundwater, particularly in industrial areas. This proposed method, using advanced artificial intelligence, can aid in water treatment and management. The novelty of these studies is the use of the ANN network to forecast WQI groundwater in an area in eastern Poland that was not previously studied—in Lublin.

Geochemical, geostatistical and time series analysis techniques as a tool to achieve the Water Framework Directive goals: An example from Piedmont region (NW Italy)

In this study, geochemical data processing and statistical/geostatistical techniques were coupled to achieve Water Framework Directive goals, collecting useful information from a complex database. Considering the Greater Turin metropolitan area, located in North-Western Italy, chemical data of 135 wells sampled and collected from 2000 to 2018 by the Environmental Protection Agency of Piedmont were analyzed. Both the processes that determine the groundwater chemical composition and the origin and evolution of groundwater were decoded and understood. The presence of two different components in the foothill aquifer system investigated was found. A bicarbonate alkaline earthy type component, linked with different degrees to phenomena of water-rock interaction, and a chlorinated type component related to nitrates, whose effects related to human activities can be recognized. This last component was mapped by using geostatistical techniques to define the most critical zones of the study area. Time series analysis on chlorides and nitrates displayed the presence of statistically significant increasing trends in some areas of the Turin plain. This study shows that the combining of geochemical approach, geostatistical techniques, and time series analysis can be used as reliable tools to understand geochemical processes acting on the system, to identify temporal and spatial hydrochemical variability, as well as to forecast water quality evolution. In this perspective, the multi-disciplinary approach developed in this study represents a reliable methodology for extracting useful information from a complex database and achieving the Water Framework Directive goals.

A hybrid wavelet-Lyapunov exponent model for river water quality forecast

Abstract The use of spectral theory and chaos theory on river water quality modeling is reported in a very limited way. This study proposes a wavelet-maximum Lyapunov exponent (WMLE) hybrid model for river water quality dynamics, combining spectral theory and chaos theory. The methodology involves the following major steps: (1) use of wavelet transformation to filter the noisy signal in the water quality time series; (2) reconstruction of phase space to embed the water quality time series and determine the trajectory of the underlying dynamics; and (3) identification of the presence/absence of chaos and prediction using the largest Lyapunov exponent value. Case studies on the Huaihe River in China and the Potomac River in the United States, as representatives of low-frequency and high-frequency forecast, show average relative errors on weekly dissolved oxygen (DO), chemical oxygen demand (COD), and ammonia nitrogen (NH3-N) data are 2.35%, 4.53%, and 18.85%, and on 15-minute based DO data are 1.185%. It also indicates that the hybrid model performs better to some extent when compared to the purely Lyapunov exponent model, ARMA model, and ANN model. This study is a proof that the combination of spectral theory and chaos theory is promising to describe and predict fluctuation of particular water quality indicators in rivers.

A water quality prediction model based on variational mode decomposition and the least squares support vector machine optimized by the sparrow search algorithm (VMD-SSA-LSSVM) of the Yangtze River, China.

Accurate and reliable water quality forecasting is of great significance for water resource optimization and management. This study focuses on the prediction of water quality parameters such as the dissolved oxygen (DO) in a river system. The accuracy of traditional water quality prediction methods is generally low, and the prediction results have serious autocorrelation. To overcome nonstationarity, randomness, and nonlinearity of the water quality parameter data, an improved least squares support vector machine (LSSVM) model was proposed to improve the model's performance at two gaging stations, namely Panzhihua and Jiujiang, in the Yangtze River, China. In addition, a hybrid model that recruits variational mode decomposition (VMD) to denoise the input data was adopted. A novel metaheuristic optimization algorithm, the sparrow search algorithm (SSA) was also implemented to compute the optimal parameter values for the LSSVM model. To validate the proposed hybrid model, standalone LSSVM, SSA-LSSVM, VMD-LSSVM, support vector regression (SVR), as well as back propagation neural network (BPNN) were considered as the benchmark models. The results indicated that the VMD-SSA-LSSVM model exhibited the best forecasting performance among all the peer models at Panzhihua station. Furthermore, the model forecasting results applied at Jiujiang were consistent with those at Panzhihua station. This result further verified the accuracy and stability of the VMD-SSA-LSSVM model. Thus, the proposed hybrid model was effective method for forecasting nonstationary and nonlinear water quality parameter series and can be recommended as a promising model for water quality parameter forecasting.

The architecture and application of an automatic operational model system for basin scale water environment management and design making supporting

An advanced framework for automatic water quality forecasting and water quality management design supporting was put forward. The system is designed as a flexible and extensible service-oriented architecture with data center, system control center, model center and client center. Two operational running modes, one for water environment automatic assessment and forecast and the other for situational analysis, were set to satisfy water quality management requirements. With loosely-coupled air-land-water numerical models, the weather, pollutants sources, hydrodynamic and water quality are automatically forecasted. According to philosophy of the framework, a one-stop platform with four different subsystems for the Three Gorges Reservoir Basin (TGRB) was developed and has been in operational running for more than two years. The system can accurately assessed, forecasted and perfectly displayed the current status and future character of TGRB in air, land and water environment.

WITHDRAWN: Prediction of water quality in municipal distribution system

In this study Feed Forward Back propagation (FFBP) and Cascade Feed Forward Back propagation (CFBP) algorithms have been compared for prediction of water quality in the distribution systems, so as make it tomeet the standards of sustainability. These algorithms have been used for forecasting Water Quality Index (WQI) in various zones of municipal distribution system by using pH, alkalinity, hardness, dissolved oxygen (DO), total solids (TS) and MPN as the input variables. Different ANN models were developed using training data set and tested in order to determine optimum number of neurons in the hidden layer, best fitting transfer function, optimum length of training dataset and best suited ANN algorithm. Further the developed ANN models were compared with multiple linear regression (MLR) technique, which is a commonly used statistical technique for modelling water quality variables. The study revealed that ANN model outperforms multiple regression technique for prediction of water quality in the distribution system and it is a robust tool for understanding the poorly defined relations between water quality variables and WQI in municipal distribution system.

Eddy correlation measurements of benthic oxygen fluxes in a stratified and operated reservoir

Benthic oxygen fluxes at the sediment-water interface (SWI) regulate the process and even direction of biochemical interfacial reactions; thus, they are crucial to the water quality. However, many medium- and large-sized reservoirs suffer from thermal stratification and human operations, lead to a significant impact on SWI oxygen exchanges. A 3-month-long noninvasive measurement of SWI oxygen fluxes was conducted in the Daheiting Reservoir using the eddy correlation method. Its result shows that reservoir stratification markedly affects the benthic boundary layer environment factors such as temperature, dissolved oxygen (DO) concentration, and hydrodynamics. In contrast, reservoir operations determine the benthic flow directions and its correlation to velocities in the mixed stage. A further discussion suggests that benthic temperatures mainly participate in the thermal structure rather than directly affecting the benthic fluxes. Conversely, it is DO concentrations coupled with hydrodynamics that control SWI oxygen fluxes. The flux is inhibited by DO shortage in anoxic conditions, but it is mainly controlled by hydrodynamics with redundant DO. Likewise, the hydrodynamics affects the fluxes by changing the diffusive boundary layer thickness, but this effect is also restrained by the DO field. These results indicate that a long-term and in-situ measurement of SWI oxygen fluxes in drinking reservoirs is of considerable significance to forecast water quality disasters, optimize operation plans, and ensure water security.

Machine learning based marine water quality prediction for coastal hydro-environment management

During the past three decades, harmful algal blooms (HAB) events have been frequently observed in marine waters around many coastal cities in the world including Hong Kong. The increasing occurrence of HAB has caused acute influences and damages on water environment and marine aquaculture with millions of monetary losses. For example, the Tolo Harbour is one of the most affected areas in Hong Kong, where more than 30% HAB occurred. In order to forewarn the potential HAB incidents, the machine learning (ML) methods have been increasingly resorted in modelling and forecasting water quality issues. In this study, two different ML methods – artificial neural networks (ANN) and support vector machine (SVM) – are implemented and improved by introducing different hybrid learning algorithms for the simulations and comparative analysis of more than 30-year measured data, so as to accurately forecast algal growth and eutrophication in Tolo Harbour in Hong Kong. The application results show the good applicability and accuracy of these two ML methods for the predictions of both trend and magnitude of the algal growth. Specifically, the results reveal that ANN is preferable to achieve satisfactory results with quick response, while the SVM is suitable to accurately identify the optimal model but taking longer training time. Moreover, it is demonstrated that the used ML methods could ensure robustness to learn complicated relationship between algal dynamics and different coastal environmental variables and thereby to identify significant variables accurately. The results analysis and discussion of this study also indicate the potentials and advantages of the applied ML models to provide useful information and implications for understanding the mechanism and process of HAB outbreak and evolution that is helpful to improving the water quality prediction for coastal hydro-environment management.

The Effects of Climate Change on the Reuse of Agricultural Drainage Water in Irrigation

Climate change is projected to have a major impact on agricultural water resources availability. Comprehending the effects of climate change on water supplies for agriculture is an essential aid for the effective management of available water resources. A forecasting model, a surface water quality model coupled with an optimization algorithm have been used in forecasting agricultural water quality and to maximize the reuse of wastewater in the Osan watershed, South Korea. In forecasting water quality and streamflow parameters for a 30 year period, AutoRegressive Integrated Moving Average (ARIMA) was used. Both ARIMA model fit and model performance were within accepted levels. Water quality and quantity were simulated using the QUAL2Kw model. Jaya algorithm was executed to optimize the process for determining optimal quantities for agricultural drainage water (ADW) reused at withdrawal points. Simulations of water quality show that organic matter levels are key attributes in the management of the Osan drain. QUAL2Kw model calibration and validation show that the model can be applicable with values of Nash—Sutcliffe model efficiency (NSE) > 0.5 respectively. Water quality results show that Biochemical Oxygen Demand (BOD), Dissolved Oxygen (DO), Total Nitrogen (TN) and Total Suspended Solids (TSS) were within acceptable ranges. ADW is suitable for indirect irrigation in the Osan watershed as water quality standards meets Korea’s standards and Food and Agricultural Organization (FAO) Guidelines. Irrigation water demand will increase by 47.1 % for summer and by 16.5% for winter by 2050 due to an increase in temperature. The total agricultural ADW reuse amounts will increase by 47.4% for summer and 17.5% for winter by 2050 due to the creation of farmlands, as there will be an increase in food demand. Optimization results show that drainage water availability will increase by 31.6% and 21.3% respectively for summer and winter by 2050 due to climate change effects. Overall, the results show that the reuse of ADW demand and the available amounts is most likely affected by climate change.

Efficient Water Quality Prediction for Indian Rivers Using Machine Learning

Water is perhaps the most fundamental component for the presence of life. The wellbeing and openness of drinking-water are significant worries all around the globe. Well-being dangers may emerge from the utilization of water sullied with irresistible specialists, poisonous synthetics, and so forth In this paper, a framework is proposed to check the water quality and caution the client before the water gets tainted. There are various boundaries that can debase the water. These boundaries are considered and utilized for foreseeing when to clean the water. The framework utilizes innovations, for example, AI, Web advancement. Here we planned to utilize the accompanying boundaries, for example, pH, turbidity, DO, conductivity, and so forth The information got from the Kaggle store for investigation. The AI calculation is utilized for anticipating the outcome. Results can be seen with the assistance of the site. This encourages the client to think previously about the defilement of water in their private tanks from streams. This procedure can in addition to the fact that limited be up to private tanks can be utilized in water treatment plants and ventures. The examination plans to give the best model forecast of water quality in river water utilizing various boundaries and water quality index. A notable AI calculation, for example, Gradient Boost, Naive Bayes, Random Forest, Decision Tree, and Deep learning algorithms were used for data interpretation and analysis. The outcome showed that the water quality record was generally in a reasonable and minor position that demonstrates of water quality was being compromised by various water poisons. A few investigations were directed to decide the ecological states of the lake, rivers that zeroed in on its actual qualities. To lessen the impact of tainted water, it is fundamental to evaluate various parts of water quality. The principal objective of this investigation is to give genuinely exact expectations to variable information. The proposed strategy accomplishes sensible precision utilizing an insignificant number of boundaries to approve the chance of its utilization of continuously water quality discovery frameworks.

Investigation of water quality in wet and dry seasons under climate change

Providing fresh water suitable for drinking and farming and living organisms in the ecosystem is essential. To evaluate water quality, qualitative indicators are often employed for managing water resources and water quality protection and pollution abatement. This study evaluated the quality of Borkhar basin water resources using three different water quality indices, including National Institutes of Health Water Quality Index (NIHWQI) having nine parameters, the Oregon Water Quality Index (OWQI) having eight parameters, and the Canadian Water Quality Indices (CWQI) with 22 main parameters. Using data for a period of 30 years, NIHWQI, OWQI and CWQI were used. To analyze water quality of the entire basin for current and future time. Results showed that water quality of the basin was in a very moderate range according to NSFWQI, and was in a very bad range accordingly to OWQI. Water quality forecasts showed that future water quality would be bad, based on OWQI and moderate based on NSFWQI, whereas based on CWQI, it will be good for drinking, and bad for aquatic animals, recreation, irrigation, and livestock use.

Occurrence of Harmful Blue-green Algae at Algae Alert System and Water Quality Forecast System Sites in Daegu and Gyeongsangbuk-do between 2012 and 2019

Objectives:We analyzed the occurrence of blue-green algae at Algae Alert System and Water Quality Forecast System sites in Daegu and Gyeonsangbuk-do between 2012 and 2019.Methods:Data from 17 sites in Daegu and Gyeonsangbuk-do were collected and reclassified to 8 Nakdong river (ND) sites and 9 water source (WS) sites. Influencing factors on the occurrence of blue-green algae were investigated.Results and Discussion:At the ND sites, blue-green algae were observed in the range of 0-495,360 cells/mL. Between 2012 and 2019, the average number of blue-green algae increased as the sites go downstream from ND-1 (Sangju weir) to ND-8 (Dalseong weir), while the number of blue-green algae was lower at the site in-between weirs than the site adjacent to weir. At the WS sites, blue-green algae were observed in the range of 0-112,000 cells/mL. The average numbers of blue-green algae in 2014, 2015 and 2017 were higher than those of other years. The dominant species of blue-green algae was Microcystis at all the sites during the summer when the water temperature was high; when the water temperature was low Aphanizomenon had higher rates of dominance. Water temperature was positively correlated with the number of blue-green algae grown, while the dissolved oxygen concentration was found to have a negative correlation with it. pH and chlorophyll-a were less correlated.Conclusions:In Daegu and Gyeongsangbuk-do, the main stream of the Nakdong river showed higher blue-green algae occurrence than the water source sites. In most cases, Microcystis was dominant species. In the main stream of Nakdong river, blue-green algae tended to occur more downstream, and the number of blue-green algae was higher at sites close to weir than sites in-between weirs. The occurrence of blue-green algae was highly related to water temperature.

Investigation of water quality in wet and dry seasons under climate change

Background: Providing fresh water suitable for drinking and farming and living organisms in the ecosystem is essential. To evaluate water quality, qualitative indicators are often employed for managing water resources and water quality protection and pollution abatement. Aim: This study evaluated the quality of Borkhar basin water resources using three different water quality indices, including National Institutes of Health Water Quality Index (NIHWQI) having nine parameters, the Oregon Water Quality Index (OWQI) having eight parameters, and the Canadian Water Quality Indices (CWQI) with 22 main parameters. Material and methods: Using data for a period of 30 years, NIHWQI, OWQI and CWQI were used. To analyze water quality of the entire basin for current and future time. New findings: Results showed that water quality of the basin was in a very moderate range according to NSFWQI, and was in a very bad range accordingly to OWQI. Water quality forecasts showed that future water quality would be bad, based on OWQI and moderate based on NSFWQI, whereas based on CWQI, it will be good for drinking, and bad for aquatic animals, recreation, irrigation, and livestock use.

Effect of iron and phosphorus on the microalgae growth in co-culture.

Iron and phosphorus (P) are the important micro- and macro-nutrient for microalgae growth, respectively. However, the effect of iron and P on microalgae growth in co-culture associating with the formation of dominate algae has not been investigated before. In the current study, Anabaene flos-aquae, Chlorella vulgaris and Melosira sp. were co-cultivated under the addition of different initial iron and P to reveal the effect of iron and phosphorus on the growth of microalgae. The results showed that the mean growth rate of A. flos-aquae, C. vulgaris and Melosira was 0.270, 0.261 and 0.062, respectively, indicating that the A. flos-aquae and C. vulgaris algae are liable to be the dominant algae while the growth of Melosira was restrained when co-cultured. The ratio of Fe to P has a significant impact on the growth of microalgae and could be regarded as an indicator of algae growth. Microalgae showed a much more obvious uptake of iron compared to that of P. The information obtained in the current study was useful for the forecast of water quality and the control of microalgae bloom.

ASSESSMENT AND FORECASTING OF ARTESIAN WATER QUALITY USING MODERN METHODS OF STATISTICAL DATA PROCESSING

The purpose of this study is to assessment and forecasting of artesian water quality, depending on well depth. This was done by discretization water supply sources by depth, followed by statistical analysis. Samples of groundwater were selected by the project Ukrainian Water Society «WaterNet» «Map of water quality» in the Kiev region for the years 2010-2020.For analysis of the groundwater pollution level were selected following water quality as a total hardness, the salt content, chromaticity, iron, manganese and nitrates. Pollutants such as iron and manganese have been found to occur at virtually any depth in concentrations that exceed the standards for drinking water. However, such quality indicators as nitrates, hardness, color and salt content exceed the norms only in certain ranges of depths. It has also been determined that the concentrations of these pollutants decrease with increasing well depth.So, the most probable contamination of groundwater with exceeding the standards of drinking water nitrates at a depth of 27.5 m and hardness salts at a depth of 45.5 m. Exceeding the standard of water chromaticity is presumably at a depth of 12.5 m. The probability of excessive salinity of groundwater is only at a depth of 27.5 meters.

Long-term trends in water quality and influence of water recharge and climate on the water quality of brackish-water lakes: A case study of Shahu Lake

This study aimed to assess the long-term fluctuations in water quality and the influence of Yellow River water recharge and climatic condition on the water environmental index of a typical brackish-water lake. This study investigated several surface water quality parameters and their relationships with the water quality index (WQI) and trophic status index (TSI) of Shahu Lake from 2011 to 2018. A health risk assessment was conducted, and the correlations among water recharge, climatic conditions, and the aforementioned elements were determined. Results show that the water quality in this lake went from good to moderate and back to good as reflected in the changes in its WQI values from 2011 to 2018. The relative water quality inferiority of this lake in 2015 and 2016 was attributed to the significant increase in its CODMn, TP, TN, NH3–N, and fluoride (F−) concentrations during these years. A combination of these parameters could rapidly predict water quality through a stepwise multiple linear regression. During the study period (except in the frozen season), Shahu Lake maintained a eutrophic status every month (especially in July) irrespective of the spatial changes resulting from low secchi depth and high TP. The limiting nutrient of Shahu Lake changed from phosphorus to both nitrogen and phosphorus, especially during summer, due to seasonal variations and exogenous inputs. The lake had an acceptable health risk level, and water recharge both had positive and negative effects on this lake as reflected in the significant decrease or increase in the concentrations of its principal parameters. This condition was also attributed to temperature and precipitation, which resulted in significant TSI variations. The findings of this study provide ways of estimating and forecasting water quality and trophic status and a basis for managing and improving similar brackish-water lakes.

Predicting water quality during urbanization based on a causality-based input variable selection method modified back-propagation neural network.

Rapid urbanization has been recognized as the primary cause of deteriorating water quality. Thus, it is crucial to take into account urbanization in water quality forecasting. The present study aims at finding the causal relationship between urbanization and water quality, and then predicting water quality based on this causality. For this purpose, nine urbanization indicators and 12 water quality parameters from 2006 to 2018 in Nanjing were collected as urbanization and water quality indices. Correlation and path analyses were firstly used to identify causal relationships between urbanization and water quality indices. Based on these causal relationships, comprehensive water quality indicators and their correlated urbanization parameters were input into a back-propagation neural network (BPNN) to predict water quality. In the improved BPNN, the R2 of the training sets were all greater than 0.99, and those of the test sets were all greater than 0.76, demonstrating that the optimized model is able to predict the water quality with reasonable accuracy. It also showed that the overall water quality in Nanjing will remain good from 2019 to 2028, which means that, when undergoing future urbanization process, water quality is not necessarily negatively affected. The transfer of industrial structure can have a positive influence on water quality. After 2028, the biological water environment index remained in a good state but the volatile phenol index continued to increase, making it a potential threat to future water quality. Industrial wastewater and fertilizer usage, as the primary sources of volatile phenols, should be prioritized for continued governmental control and monitoring into the future. This study provides new insight into the relationship between urbanization and water quality, and the presented models can assist in future-proofing water management strategies.

Calibration and quantifying uncertainty of daily water quality forecasts for large lakes with a Bayesian joint probability modelling approach

Correcting the systematic bias and quantifying uncertainty associated with the operational water quality forecasts are imperative works for risk-based environmental decision making. This work proposes a post-processing method for addressing both bias correction and total uncertainty quantification for daily forecasts of water quality parameters derived from dynamical lake models. The post-processing is implemented based on a Bayesian Joint Probability (BJP) modeling approach. The BJP model uses a log-sinh transformation to normalize the raw forecasts and corresponding observations, and uses a bivariate Gaussian distribution to characterize the dependence relationship. The posterior distribution of the transformation parameters is inferenced through Metropolis Monte Carlo Markov chain sampling; it generates unbiased probabilistic forecasts that account for uncertainties from all sources. The BJP is used to post-processing raw daily forecasts of dissolved oxygen (DO), ammonium nitrogen (NH), total phosphorus (TP) and total nitrogen (TN) concentrations of Lake Chaohu, the fifth largest lake in China with lead times from 0 to 5 days. Results suggest that an average 93.1% forecast bias has been removed by BJP. The root mean square error in probability skill scores range from 5.8% for NH to 68.2% for TP, and the non-parametric bootstrapping test suggests that 67.7% forecasts are significantly improved averaged across all sampling sites, water quality parameters and lead times. The probabilities of the calibrated forecasts are reasonably consistent with the observed relative frequencies, and have appropriate spread and thus correctly quantify forecast uncertainty. The BJP post-processing method used in this study can be a useful operational tool that help to better realize the potential of water quality forecasts derived from dynamical models.