A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter- and extrapolation performance with inputs' significance analysis

Deep optimization of water quality index and positive matrix factorization models for water quality evaluation and pollution source apportionment using a random forest model

Effective evaluation of water quality and accurate quantification of pollution sources are essential for the sustainable use of water resources. Although water quality index (WQI) and positive matrix factorization (PMF) models have been proven to be applicable for surface water quality assessments and pollution source apportionments, these models still have potential for further development in today's data-driven, rapidly evolving technological era. This study coupled a machine learning technique, the random forest model, with WQI and PMF models to enhance their ability to analyze water pollution issues. Monitoring data of 12 water quality indicators from six sites along the Minjiang River from 2015 to 2020 were used to build a WQI model for determining the spatiotemporal water quality characteristics. Then, coupled with the random forest model, the importance of 12 indicators relative to the WQI was assessed. The total phosphorus (TP), total nitrogen (TN), chemical oxygen demand (CODCr), dissolved oxygen (DO), and five-day biochemical oxygen demand (BOD5) were identified as the top five significant parameters influencing water quality in the region. The improved WQI model constructed based on key parameters enabled high-precision (R2 = 0.9696) water quality prediction. Furthermore, the feature importance of the indicators was used as weights to adjust the results of the PMF model, allowing for a more reasonable pollutant source apportionment and revealing potential driving factors of variations in water quality. The final contributions of pollution sources in descending order were agricultural activities (30.26%), domestic sewage (29.07%), industrial wastewater (26.25%), seasonal factors (6.45%), soil erosion (6.19%), and unidentified sources (1.78%). This study provides a new perspective for a comprehensive understanding of the water pollution characteristics of rivers, and offers valuable references for the development of targeted strategies for water quality improvement.

Analysis of dissolved oxygen influencing factors and concentration prediction using input variable selection technique: A hybrid machine learning approach

Accurate quantification of dissolved oxygen (DO) is critically important for the protection and management of aquatic ecosystems. Successful applications have utilized mechanistic and data-driven models to simulate DO content in aquatic ecosystems. However, mechanistic models present challenges due to their complex and difficult-to-solve conditions, making them less portable. Additionally, data-driven model predictions are hindered by the challenge of numerous input variables, impacting both the running speed and prediction performance of the model. To address these challenges, water quality data and meteorological data of the Tanjiang River were obtained. The maximum information coefficient (MIC) input variable selection technique was employed to identify primary environmental factors influencing DO changes. Furthermore, coupled with support vector regression (SVR), two models (SVR and MIC-SVR) were employed to estimate the DO concentration of the Tanjiang River, and the optimal model was established. The results indicated a shift in the primary pollution factor from ammonia nitrogen to total phosphorus after recent treatment in the Tanjiang River. In comparison with the SVR model, the root mean square error (RMSE) of the MIC-SVR model was reduced by 4.46%, and the Nash-efficiency coefficient (NSE) was improved by 45.85%. In addition, study of kernel function selection revealed that considering as many kernel functions as possible is necessary for improving the performance of the SVR model. Conclusively, the proposed MIC-SVR model serves as an effective tool to analyze the relationship between DO and environmental factors, identifying the primary causes of low DO, and accurately predict the DO concentration in the Tanjiang River (especially in its middle and lower reaches), thus providing a reference for governmental decision-making on water environmental protection and water resource management.

Reliable water quality prediction and parametric analysis using explainable AI models

The consumption of water constitutes the physical health of most of the living species and hence management of its purity and quality is extremely essential as contaminated water has to potential to create adverse health and environmental consequences. This creates the dire necessity to measure, control and monitor the quality of water. The primary contaminant present in water is Total Dissolved Solids (TDS), which is hard to filter out. There are various substances apart from mere solids such as potassium, sodium, chlorides, lead, nitrate, cadmium, arsenic and other pollutants. The proposed work aims to provide the automation of water quality estimation through Artificial Intelligence and uses Explainable Artificial Intelligence (XAI) for the explanation of the most significant parameters contributing towards the potability of water and the estimation of the impurities. XAI has the transparency and justifiability as a white-box model since the Machine Learning (ML) model is black-box and unable to describe the reasoning behind the ML classification. The proposed work uses various ML models such as Logistic Regression, Support Vector Machine (SVM), Gaussian Naive Bayes, Decision Tree (DT) and Random Forest (RF) to classify whether the water is drinkable. The various representations of XAI such as force plot, test patch, summary plot, dependency plot and decision plot generated in SHAPELY explainer explain the significant features, prediction score, feature importance and justification behind the water quality estimation. The RF classifier is selected for the explanation and yields optimum Accuracy and F1-Score of 0.9999, with Precision and Re-call of 0.9997 and 0.998 respectively. Thus, the work is an exploratory analysis of the estimation and management of water quality with indicators associated with their significance. This work is an emerging research at present with a vision of addressing the water quality for the future as well.

Water quality assessment and pollution source apportionment using multivariate statistical and PMF receptor modeling techniques in a sub-watershed of the upper Yangtze River, Southwest China

Rapid industrial and agricultural development as well as urbanization affect the water environment significantly, especially in sub-watersheds where the contaminants/constituents present in the pollution sources are complex, and the flow is unstable. Water quality assessment and quantitative identification of pollution sources are the primary prerequisites for improving water management and quality. In this work, 168 water samples were collected from seven stations throughout 2018-2019 along the Laixi River, a vital pollution control unit in the upper reaches of the Yangtze River. Multivariate statistics and positive matrix factorization (PMF) receptor modeling techniques were used to evaluate the characteristics of the river-water quality and reveal the pollution sources. Principal component analysis was employed to screen the crucial parameters and establish an optimized water quality assessment procedure to reduce the analysis cost and improve the assessment efficiency. Cluster analysis further illustrates the spatiotemporal distribution characteristics of river-water quality. Results indicated that high-pollution areas are concentrated in the tributaries, and the high-pollution periods are the spring and winter, which verifies the reliability of the evaluation system. The PMF model identified five and six potential pollution sources in the cold and warm seasons, respectively. Among them, pollution from agricultural activities and domestic wastewater shows the highest contributions (33.2% and 30.3%, respectively) during the cold and warm seasons, respectively. The study can provide theoretical support for pollutant control and water quality improvement in the sub-watershed, avoiding the ecological and health risks caused by the deterioration of water quality.

The ppk-expressing transgenic rice floating bed improves P removal in slightly polluted water

With significant economic advantages, the plant floating bed has been widely utilized in the ecological remediation of eutrophic water because of the excessive phosphorus (P) and nitrogen discharge in China. Previous research has demonstrated that polyphosphate kinase (ppk)-expressing transgenic rice (Oryza sativa L. ssp. japonica) (ETR) can increase the P absorption capacity to support rice growth and boost rice yield. In this study, the floating beds of ETR with single copy line (ETRS) and double copy line (ETRD) are built to investigate their capacity to remove aqueous P in slightly polluted water. Compared with the wild type Nipponbare (WT) floating bed, the ETR floating beds greatly reduce the total P concentration in slightly polluted water though the ETR floating beds have the same removal rates of chlorophyll-a, NO3--N, and total nitrogen in slightly polluted water. The P uptake rate of ETRD on the floating bed is 72.37% in slightly polluted water, which is higher than that of ETRS and WT on the floating beds. Polyphosphate (polyP) synthesis is a critical factor for the excessive phosphate uptake of ETR on the floating beds. The synthesis of polyP decreases the level of free intracellular phosphate (Pi) in ETR on the floating beds, simulating the phosphate starvation signaling. The OsPHR2 expression in the shoot and root of ETR on the floating bed increased, and the corresponding P metabolism gene expression in ETR was changed, which promoted Pi uptake by ETR in slightly polluted water. The Pi accumulation further promoted the growth of ETR on the floating beds. These findings highlight that the ETR floating beds, especially ETRD floating bed, have significant potential for P removal and can be exploited as a novel method for phytoremediation in slightly polluted water.

New insights into pollution source analysis using receptor models in the upper Yangtze river basin: Effects of land use on source identification and apportionment

To effectively control pollution and improve water quality, it is essential to accurately analyze the potential pollution sources in rivers. The study proposes a hypothesis that land use can influence the identification and apportionment of pollution sources and tested it in two areas with different types of water pollution and land use. The redundancy analysis (RDA) results showed that the response mechanisms of water quality to land use differed among regions. In both regions, the results indicated that the water quality response relationship to land use provided important objective evidence for pollution source identification, and the RDA tool optimized the procedure of source analysis for receptor models. Positive matrix decomposition (PMF) and absolute principal component score-multiple linear regression (APCS-MLR) receptor models identified five and four pollution sources along with their corresponding characteristic parameters. PMF attributed agricultural nonpoint sources (23.8%) and domestic wastewater (32.7%) as the major sources in regions 1 and 2, respectively, while APCS-MLR identified mixed sources in both regions. In terms of model performance parameters, PMF demonstrated better-fit coefficients (R²) than APCS-MLR and had a lower error rate and proportion of unidentified sources. The results show that considering the effect of land use in the source analysis can overcome the subjectivity of the receptor model and improve the accuracy of pollution source identification and apportionment. The results of the study can help managers clarify the priorities of pollution prevention and control, and provide a new methodology for water environment management in similar watersheds.

Spatiotemporal analysis and prediction of water quality in Pearl River, China, using multivariate statistical techniques and data-driven model

Identifying spatiotemporal variation patterns and predicting future water quality are critical for rational and effective surface water management. In this study, an exploratory analysis and forecast workflow for water quality in Pearl River, Guangzhou, China, was established based on the 4-h interval dataset selected from 10 stations for water quality monitoring from 2019 to 2021. The multiple statistical techniques, such as cluster analysis (CA), principal component analysis (PCA), correlation analysis (CoA), and redundancy analysis (RDA), as well as data-driven model (i.e., gated recurrent unit (GRU)), were applied for assessing and predicting the water quality in the basin. The investigated sampling stations were classified into 3 categories based on differences in water quality, i.e., low, moderate, and high pollution regions. The average water quality indexes (WQI) values ranged from 38.43 to 92.63. Nitrogen was the most dominant pollutant, with high TN concentrations of 0.81-7.67 mg/L. Surface runoff, atmospheric deposition, and anthropogenic activities were the major contributors affecting the spatiotemporal variations in water quality. The decline in river water quality during the wet season was mainly attributed to increased surface runoff and extensive human activities. Furthermore, the short-term prediction of river water quality was achieved using the GRU model. The result indicated that for both DLCK and DTJ stations, the WQI for the 5-day lead time were predicted with accuracies of 0.82; for the LXH station, the WQI for the 3-day lead time was forecasted with an accuracy of 0.83. The finding of this study will shed a light on an effective reference and systematic support for spatio-seasonal variation and prediction patterns of water quality.

A comprehensive review on modelling the adsorption process for heavy metal removal from waste water using artificial neural network technique

Water is the most necessary and significant element for all life on earth. Unfortunately, the quality of the water resources is constantly declining as a result of population development, industry, and civilization progress. Due to their extreme toxicity, heavy metals removal from water has drawn researchers' attention. A lot of scientific applications use artificial neural networks (ANNs) because of their excellent ability to map nonlinear relationships. ANNs shown excellent modelling capabilities for the water treatment remediation. The adsorption process uses a variety of variables, making the interaction between them nonlinear. Selecting the best technique can produce excellent results; the adsorption approach for removing heavy metals is highly effective. Different studies show that the ANNs modelling approach can accurately forecast the adsorbed heavy metals and other contaminants in order to remove them.

The development of dissolved oxygen forecast model using hybrid machine learning algorithm with hydro-meteorological variables

Dissolved oxygen (DO) forecasting is essential for aquatic managers responsible for maintaining ecosystem health and the management of water bodies affected by water quality parameters. This paper aims to forecast dissolved oxygen (DO) concentration using a multivariate adaptive regression spline (MARS) hybrid model coupled with maximum overlap discrete wavelet transformation (MODWT) as a feature decomposition approach for Surma River water using a set of water quality hydro-meteorological variables. The proposed hybrid model is compared with numerous machine learning methods, namely Bayesian ridge regression (BNR), k-nearest neighbourhood (KNN), kernel ridge regression (KRR), random forest (RF), and support vector regression (SVR). The investigational results show that the proposed model of MODWT-MARS has a better prediction than the comparing benchmark models and individual standalone counter parts. The result shows that the hybrid algorithms (i.e. MODWT-MARS) outperformed the other models (r = 0.981, WI = 0.990, RMAE = 2.47%, and MAE = 0.089). This hybrid method may serve to forecast water quality variables with fewer predictor variables.

A review of the application of machine learning in water quality evaluation

With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments.

An efficient strategy for predicting river dissolved oxygen concentration: application of deep recurrent neural network model

Dissolved oxygen (DO) concentration in water is one of the key parameters for assessing river water quality. Artificial intelligence (AI) methods have previously proved to be accurate tools for DO concentration prediction. This study presents the implementation of a deep learning approach applied to a recurrent neural network (RNN) algorithm. The proposed deep recurrent neural network (DRNN) model is compared with support vector machine (SVM) and artificial neural network (ANN) models, formerly shown to be robust AI algorithms. The Fanno Creek in Oregon (USA) is selected as a case study and daily values of water temperature, specific conductance, streamflow discharge, pH, and DO concentration are used as input variables to predict DO concentration for three different lead times ("t + 1," "t + 3," and "t + 7"). Based on Pearson's correlation coefficient, several input variable combinations are formed and used for prediction. The model prediction performance is evaluated using various indices such as correlation coefficient, Nash-Sutcliffe efficiency, root mean square error, and mean absolute error. The results identify the DRNN model ([Formula: see text]) as the most accurate among the three models considered, highlighting the potential of deep learning approaches for water quality parameter prediction.

Rapid monitoring of heavy metal pollution in lake water using nitrogen and phosphorus nutrients and physicochemical indicators by support vector machine

A novel method of predicting heavy metal concentration in lake water by support vector machine (SVM) model was developed, combined with low-cost, easy to obtain nutrients and physicochemical indicators as input variables. 115 surface water samples were collected from 23 sites in Chaohu Lake, China, during different hydrological periods. The particulate concentrations of heavy metals in water were much higher than the dissolved concentrations. According to Nemerow pollution index (Pi), pollution degrees by Fe, V, Mn and As ranged from heavy (2 ≤ Pi < 4) to serious (Pi ≥ 4). The concentrations of most heavy metals were the highest during the medium-water period and the lowest during the dry season. Non-metric Multidimensional Scaling Analysis confirmed heavy metal concentrations had slight spatial difference but relatively large seasonal variation. Redundancy Analysis indicated the close associations of heavy metals with nutrient and physicochemical indicators. When both nutrient and physicochemical indicators were used as input variables, the simulation effects for most elements in total and particulate were relatively better than those obtained using only nutrient or only physicochemical indicators. The simulation effects for As, Ba, Fe, Ti, V and Zn were generally good, based on their training R values of 0.847, 0.828, 0.856, 0.867, 0.817 and 0.893, respectively, as well as their test R values of 0.811, 0.836, 0.843, 0.873, 0.829 and 0.826, respectively; and meanwhile, in both the training and test stages, these metals also had relatively lower errors. The spatial distribution of heavy metals in Chaohu Lake was then predicted using the fully trained SVM models.

A data-driven framework for spatiotemporal characteristics, complexity dynamics, and environmental risk evaluation of river water quality

To evaluate the evolution of river water quality in a changing environment, measuring the objective water quality is critical for understanding the rules of river water pollution. Based on the sample entropy theory and a nonlinear statistical method, this study aims to identify the spatiotemporal dynamics of water quality and its complexity in the Yangtze River basin using time series data, to separate the contributions of human activity and climate change to water quality, and to establish a data-driven risk assessment framework for the spatial (potential risk) and temporal (direct risk) aspects of water pollution. The results demonstrate that the spatiotemporal dynamics of water quality and sample entropy in each monitoring section are closely related to the characteristics of the corresponding location. The water quality of the main stream is superior, and its complexity is less than that of the tributaries. Cascade reservoir operation and vegetation status, agricultural production, and rainfall patterns exert great influences in the upper, middle, and lower reaches, respectively. Dam construction, urban agglomeration development, and interactions between river and lake are also influencing factors. An attributional analysis found that climate change and human activities negatively contributed to the evolution of NH₃-N concentration in most of the monitored sections, and the average relative contribution rates of human activities to changes in water quality in the main and tributary streams were -55.46% and -48.49%, respectively. In addition, the construction of data-driven risk assessment framework can efficiently and accurately assess the potential and direct water pollution risks of rivers.

Multi-State Load Demand Forecasting Using Hybridized Support Vector Regression Integrated with Optimal Design of Off-Grid Energy Systems—A Metaheuristic Approach

The prediction accuracy of support vector regression (SVR) is highly influenced by a kernel function. However, its performance suffers on large datasets, and this could be attributed to the computational limitations of kernel learning. To tackle this problem, this paper combines SVR with the emerging Harris hawks optimization (HHO) and particle swarm optimization (PSO) algorithms to form two hybrid SVR algorithms, SVR-HHO and SVR-PSO. Both the two proposed algorithms and traditional SVR were applied to load forecasting in four different states of Nigeria. The correlation coefficient (R), coefficient of determination (R2), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE) were used as indicators to evaluate the prediction accuracy of the algorithms. The results reveal that there is an increase in performance for both SVR-HHO and SVR-PSO over traditional SVR. SVR-HHO has the highest R2 values of 0.9951, 0.8963, 0.9951, and 0.9313, the lowest MSE values of 0.0002, 0.0070, 0.0002, and 0.0080, and the lowest MAPE values of 0.1311, 0.1452, 0.0599, and 0.1817, respectively, for Kano, Abuja, Niger, and Lagos State. The results of SVR-HHO also prove more advantageous over SVR-PSO in all the states concerning load forecasting skills. This paper also designed a hybrid renewable energy system (HRES) that consists of solar photovoltaic (PV) panels, wind turbines, and batteries. As inputs, the system used solar radiation, temperature, wind speed, and the predicted load demands by SVR-HHO in all the states. The system was optimized by using the PSO algorithm to obtain the optimal configuration of the HRES that will satisfy all constraints at the minimum cost.

A New Approach for Estimating Dissolved Oxygen Based on a High-Accuracy Surface Modeling Method

Dissolved oxygen (DO) is a direct indicator of water pollution and an important water quality parameter that affects aquatic life. Based on the fundamental theorem of surfaces in differential geometry, the present study proposes a new modeling approach to estimate DO concentrations with high accuracy by assessing the spatial correlation and heterogeneity of DO with respect to explanatory variables. Specifically, a regularization penalty term is integrated into the high-accuracy surface modeling (HASM) method by applying geographically weighted regression (GWR) with some covariates. A modified version of HASM, namely HASM_MOD, is illustrated through a case study of Poyang Lake, China, by comparing the results of HASM, a support vector machine (SVM), and cokriging. The results indicate that HASM_MOD yields the best performance, with a mean absolute error (MAE) that is 38%, 45%, and 42% lower than those of HASM, the SVM, and cokriging, respectively, by using the cross-validation method. The introduction of a regularization penalty term by using GWR with respect to covariates can effectively improve the quality of the DO estimates. The results also suggest that HASM_MOD is able to effectively estimate nonlinear and nonstationary time series and outperforms three other methods using cross-validation, with a root-mean-square error (RMSE) of 0.20 mg/L and R² of 0.93 for the two study sites (Sanshan and Outlet_A stations). The proposed method, HASM_MOD, provides a new way to estimate the DO concentration with high accuracy.

Application of ANN and SVM for prediction nutrients in rivers

This paper presents the results of predicting nutrients in rivers on national level by the use of two artificial intelligence methodologies. Artificial neural network (ANN) and support vector machine (SVM) were used to predict annual concentration of nitrate and phosphate in rivers of eleven European countries. For creation of an optimal model of prediction, 23 industrial, economical and agricultural parameters were used for the period from 2000 to 2011. The data from 2000 to 2010 was used for training, while the data for 2011 was used for model validation. Optimization of different parameters of ANN and SVM was conducted in order to obtain the model with the best performances. Results of created models were evaluated by using statistical performances indicator named coefficient of determination (R²). The obtained results showed that ANN has better results in predicting nitrate and phosphate compared to SVM models. These results suggest that ANN model is a promising tool for prediction of nutrients in rivers.

Mapping the spatial and temporal variability of flood susceptibility using remotely sensed normalized difference vegetation index and the forecasted changes in the future

Accurate runoff forecasting plays a considerable role in the appropriate water resource planning and management. The spatial and temporal evaluation of the flood susceptibility was explored in the Quebec basin, Canada. This study provides a new strategy for runoff modelling as one of the complicated variables by developing new machine learning techniques along with remote sensing. A novel scheme of the Group Method of Data Handling (GMDH) known as the generalized structure of GMDH (GSGGMDH) is developed to overcome this classical approach's limitation. A simple time series based scenario with exogenous variables including precipitation and Normalized Difference Vegetation Index (NDVI) was introduced for runoff forecasting. MODIS data included MOD13Q1 product was employed and a JavaScript code was developed to preprocess collected data in the Google Earth Engine (GEE) environment. Using different seasonal and non-seasonal lags of all input variables, the developed GSGMDH found the most optimum input combination for each station in terms of simplicity and accuracy, simultaneously (average values; SI = 0.554, RMSRE = 1.55, MAE = 5.076). The precipitation values are modelled with the CanEsm2 climate change model. To apply NDVI for runoff forecasting, a simple spatial-temporal GSGMDH based model was developed (average values; SI = 0.27; RMSRE = 8.27, MAE = 0.08). The forecasting results indicated that the months in which the maximum runoff occurred have changed, and these months have increased compared to the historic period. In the historical period, the frequency of maximum runoff was in April and March. Still, for the two forecasting periods (i.e. 2020-2039 and 2040-2059), the months in which the maximum runoff has occurred have changed, and their amount has been reduced and added to other months, especially February and August.

The Use of Artificial Neural Networks to Predict the Physicochemical Characteristics of Water Quality in Three District Municipalities, Eastern Cape Province, South Africa

Reliable prediction of water quality changes is a prerequisite for early water pollution control and is vital in environmental monitoring, ecosystem sustainability, and human health. This study uses Artificial Neural Network (ANN) technique to develop the best model fits to predict water quality parameters by employing multilayer perceptron (MLP) neural network and the radial basis function (RBF) neural network, using data collected from three district municipalities. Two input combination models, MLP-4-5-4 and MLP-4-9-4, were trained, verified, and tested for their predictive performance ability, and their physicochemical prediction accuracy was compared by using each model's observed data with the predicted data. The MLP-4-5-4 model showed a better understanding of the data sets and water quality predictive ability giving an MSE of 39.06589 and a correlation coefficient (R²) of the observed and the predicted water quality of 0.989383 compared to the MLP-4-9-4 model (R² = 0.993532, MSE = 39.03087). These results apply to natural water resources management in South Africa and similar catchment systems. The MLP-4-5-4 system can be scaled up for future water quality prediction of the Waste Water Treatment Plants (WWTPs), groundwater, and surface water while raising awareness among the public and industry on future water quality.

Estimation of daily dissolved oxygen concentration for river water quality using conventional regression analysis, multivariate adaptive regression splines, and TreeNet techniques

The aim of this study was to model the surface water quality of the Broad River Basin, South Carolina. The most suitable two monitoring stations numbered as USGS 02156500 (Near Carlisle) and USGS 02160991 (Near Jenkinsville) were selected for the reason that the river water temperature (WT), pH, and specific conductance (SC), as well as dissolved oxygen (DO) concentration, were simultaneously monitored and recorded at these sites. The monitoring period from September 2016 to August 2017 was taken into account for the modeling studies. The electrical conductivity (EC) values corresponding to the river SC values were calculated. First, the conventional regression analysis (CRA) was applied to three regression forms, i.e., linear, power, and exponential functions, to estimate the river DO concentration. Then, the multivariate adaptive regression splines (MARS) and TreeNet gradient boosting machine (TreeNet) techniques were employed. Three performance statistics, i.e., root means square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe coefficient of efficiency (NS), were used to compare the estimation capabilities of these techniques. The TreeNet technique, which was used for the first time in the modeling of DO concentration, had higher estimation success with the RMSE, MAE, and NS values of 0.182 mg/L, 0.123 mg/L, and 0.990, respectively, for the Carlisle station and 0.313 mg/L, 0.233 mg/L, and 0.965, respectively, for the Jenkinsville station in the training phase. The MARS technique, which had limited availability of its application in the modeling of DO concentration, had higher estimation success with the RMSE, MAE, and NS values of 0.240 mg/L, 0.195 mg/L, and 0.981, respectively, for the Carlisle station and 0.527 mg/L, 0.432 mg/L, and 0.980, respectively, for the Jenkinsville station in the testing phase. Considering the RMSE and MAE values being lower, as well as NS values being higher for the model having an input combination of WT, pH, and EC, the Carlisle station came into prominence. It was concluded that international researchers, who have engaged in the river water quality modeling studies, can favor the MARS and TreeNET techniques without any hesitation and estimate the river DO concentration successfully. The models developed for the Carlisle station were tested with the data sets for the monitoring period from September 2017 to August 2018 at the same station. Similarly, the models developed for the Jenkinsville station were tested with the data sets for the monitoring period from September 2017 to August 2018 at the same station. It was concluded that the models could estimate the river DO concentrations very close to in situ measurements at the same site but for the different monitoring periods, too. Furthermore, the models developed for the Carlisle station were tested with the data sets from the Jenkinsville station for the same monitoring period. Similarly, the models developed for the Jenkinsville station were tested with the data sets from the Carlisle station for the same monitoring period. It was also concluded that the developed models could estimate the river DO concentrations very close to in situ measurements at different monitoring sites but for the same monitoring period on the same river, too. It can be asserted that the models developed for any monitoring site on a river can be employed for another monitoring site on the same river, too, as in the case of the Broad River, South Carolina.

Concentration estimation of dissolved oxygen in Pearl River Basin using input variable selection and machine learning techniques

Dissolved oxygen (DO) concentration is an essential index for water environment assessment. Here, we present a modeling approach to estimate DO concentrations using input variable selection and data-driven models. Specifically, the input variable selection technique, the maximal information coefficient (MIC), was used to identify and screen the primary environmental factors driving variation in DO. The data-driven model, support vector regression (SVR), was then used to construct a robust model to estimate DO concentration. The approach was illustrated through a case study of the Pearl River Basin in China. We show that the MIC technique can effectively screen major local environmental factors affecting DO concentrations. MIC value tended to stabilize when the sample size >3000 and EC had the highest score with an MIC >0.3 at both of the stations. The variable-reduced datasets improved the performance of the SVR model by a reduction of 28.65% in RMSE, and increase of 22.16%, 56.27% in R², NSE, respectively, relative to complete candidate sets. The MIC-SVR model constructed at the tidal river network performed better than nontidal river network by a reduction of approximately 63.01% in RMSE, an increase of 62.36% in NSE, and R² >0.9. Overall, the proposed technique was able to handle nonlinearity among environmental factors and accurately estimate DO concentrations in tidal river network regions.

Predicting the Trend of Dissolved Oxygen Based on the kPCA-RNN Model

Water quality forecasting is increasingly significant for agricultural management and environmental protection. Enormous amounts of water quality data are collected by advanced sensors, which leads to an interest in using data-driven models for predicting trends in water quality. However, the unpredictable background noises introduced during water quality monitoring seriously degrade the performance of those models. Meanwhile, artificial neural networks (ANN) with feed-forward architecture lack the capability of maintaining and utilizing the accumulated temporal information, which leads to biased predictions in processing time series data. Hence, we propose a water quality predictive model based on a combination of Kernal Principal Component Analysis (kPCA) and Recurrent Neural Network (RNN) to forecast the trend of dissolved oxygen. Water quality variables are reconstructed based on the kPCA method, which aims to reduce the noise from the raw sensory data and preserve actionable information. With the RNN’s recurrent connections, our model can make use of the previous information in predicting the trend in the future. Data collected from Burnett River, Australia was applied to evaluate our kPCA-RNN model. The kPCA-RNN model achieved R 2 scores up to 0.908, 0.823, and 0.671 for predicting the concentration of dissolved oxygen in the upcoming 1, 2 and 3 hours, respectively. Compared to current data-driven methods like Feed-forward neural network (FFNN), support vector regression (SVR) and general regression neural network (GRNN), the predictive accuracy of the kPCA-RNN model was at least 8%, 17% and 12% better than the comparative models in these three cases. The study demonstrates the effectiveness of the kPAC-RNN modeling technique in predicting water quality variables with noisy sensory data.

Modeling the Impact of Extreme River Discharge on the Nutrient Dynamics and Dissolved Oxygen in Two Adjacent Estuaries (Portugal)

The Minho and Lima are adjacent estuaries located in the north of Portugal, with high ecological and economic importance. To address gaps in knowledge about changes in nutrient patterns in adjacent estuaries subject to different freshwater inflows, a numerical model, Delft3D, was implemented and developed, using a single domain, which allowed physical communication between estuaries. Calibration and validation of the model was successfully performed. Three numerical simulations were carried out, in which only river flows were varied (1st corresponds to a baseline numerical run, the 2nd a flood scenario, and the 3rd a drought scenario). Under flooding conditions, similar patterns were verified in both estuaries, with high fluvial discharges showing to have a reduced impact on both estuarine dynamics. In this case the nutrients were not a limiting factor for the biota, both for summer and winter seasons, since there was no significant decrease in dissolved oxygen concentration. For the drought scenario, it was observed that the estuary with the lower inflow of freshwater (Lima) was the most affected, with a significant decrease in the concentration of nutrients and oxygen dissolved in the winter season (decrease of 2 mg O2/L). In conclusion, this work reveals that it is essential to continuously monitor dam-controlled estuarine systems, as a significant decrease in river discharge will cause significant changes in the variables analysed (O2, PO4, and NO3) and may cause loss of biodiversity.

Can Decomposition Approaches Always Enhance Soft Computing Models? Predicting the Dissolved Oxygen Concentration in the St. Johns River, Florida

This study evaluates standalone and hybrid soft computing models for predicting dissolved oxygen (DO) concentration by utilizing different water quality parameters. In the first stage, two standalone soft computing models, including multilayer perceptron (MLP) neural network and cascade correlation neural network (CCNN), were proposed for estimating the DO concentration in the St. Johns River, Florida, USA. The DO concentration and water quality parameters (e.g., chloride (Cl), nitrogen oxides (NOx), total dissolved solid (TDS), potential of hydrogen (pH), and water temperature (WT)) were used for developing the standalone models by defining six combinations of input parameters. Results were evaluated using five performance criteria metrics. Overall results revealed that the CCNN model with input combination III (CCNN-III) provided the most accurate predictions of DO concentration values (root mean square error (RMSE) = 1.261 mg/L, Nash-Sutcliffe coefficient (NSE) = 0.736, Willmott’s index of agreement (WI) = 0.919, R2 = 0.801, and mean absolute error (MAE) = 0.989 mg/L) for the standalone model category. In the second stage, two decomposition approaches, including discrete wavelet transform (DWT) and variational mode decomposition (VMD), were employed to improve the accuracy of DO concentration using the MLP and CCNN models with input combination III (e.g., DWT-MLP-III, DWT-CCNN-III, VMD-MLP-III, and VMD-CCNN-III). From the results, the DWT-MLP-III and VMD-MLP-III models provided better accuracy than the standalone models (e.g., MLP-III and CCNN-III). Comparison of the best hybrid soft computing models showed that the VMD-MLP-III model with 4 intrinsic mode functions (IMFs) and 10 quadratic penalty factor (VMD-MLP-III (K = 4 and α = 10)) model yielded slightly better performance than the DWT-MLP-III with Daubechies-6 (D6) and Symmlet-6 (S6) (DWT-MLP-III (D6 and S6)) models. Unfortunately, the DWT-CCNN-III and VMD-CCNN-III models did not improve the performance of the CCNN-III model. It was found that the CCNN-III model cannot be used to apply the hybrid soft computing modeling for prediction of the DO concentration. Graphical comparisons (e.g., Taylor diagram and violin plot) were also utilized to examine the similarity between the observed and predicted DO concentration values. The DWT-MLP-III and VMD-MLP-III models can be an alternative tool for accurate prediction of the DO concentration values.

The Integration of Nature-Inspired Algorithms with Least Square Support Vector Regression Models: Application to Modeling River Dissolved Oxygen Concentration

The current study investigates an improved version of Least Square Support Vector Machines integrated with a Bat Algorithm (LSSVM-BA) for modeling the dissolved oxygen (DO) concentration in rivers. The LSSVM-BA model results are compared with those obtained using M5 Tree and Multivariate Adaptive Regression Spline (MARS) models to show the efficacy of this novel integrated model. The river water quality data at three monitoring stations located in the USA are considered for the simulation of DO concentration. Eight input combinations of four water quality parameters, namely, water temperature, discharge, pH, and specific conductance, are used to simulate the DO concentration. The results revealed the superiority of the LSSVM-BA model over the M5 Tree and MARS models in the prediction of river DO. The accuracy of the LSSVM-BA model compared with those of the M5 Tree and MARS models is found to increase by 20% and 42%, respectively, in terms of the root-mean-square error. All the predictive models are found to perform best when all the four water quality variables are used as input, which indicates that it is possible to supply more information to the predictive model by way of incorporation of all the water quality variables.

Modeling of an activated sludge process for effluent prediction-a comparative study using ANFIS and GLM regression

In this paper, nonlinear system identification of the activated sludge process in an industrial wastewater treatment plant was completed using adaptive neuro-fuzzy inference system (ANFIS) and generalized linear model (GLM) regression. Predictive models of the effluent chemical and 5-day biochemical oxygen demands were developed from measured past inputs and outputs. From a set of candidates, least absolute shrinkage and selection operator (LASSO), and a fuzzy brute-force search were utilized in selecting the best combination of regressors for the GLMs and ANFIS models respectively. Root mean square error (RMSE) and Pearson's correlation coefficient (R-value) served as metrics in assessing the predicting performance of the models. Contrasted with the GLM predictions, the obtained modeling results show that the ANFIS models provide better predictions of the studied effluent variables. The results of the empirical search for the dominant regressors indicate the models have an enormous potential in the estimation of the time lag before a desired effluent quality can be realized, and preempting process disturbances. Hence, the models can be used in developing a software tool that will facilitate the effective management of the treatment operation.

A Time Series Model Comparison for Monitoring and Forecasting Water Quality Variables

The monitoring and prediction of water quality parameters are important tasks in the management of water resources. In this work, the performances of time series statistical models were evaluated to predict and forecast the dissolved oxygen (DO) concentration in several monitoring sites located along the main river Vouga, in Portugal, during the period from January 2002 to May 2015. The models being compared are a regression model with correlated errors and a state-space model, which can be seen as a calibration model. Both models allow the incorporation of water quality variables, such as time correlation or seasonality. Results show that, for the DO variable, the calibration model outperforms the regression model for sample modeling, that is, for a short-term forecast, while the regression model with correlated errors has a better performance for the forecasting h-steps ahead framework. So, the calibration model is more useful for water monitoring using an online or real-time procedure, while the regression model with correlated errors can be applied in order to forecast over a longer period of time.

Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction

This paper presents an application of experimental design for the optimization of artificial neural network (ANN) for the prediction of dissolved oxygen (DO) content in the Danube River. The aim of this research was to obtain a more reliable ANN model that uses fewer monitoring records, by simultaneous optimization of the following model parameters: number of monitoring sites, number of historical monitoring data (expressed in years), and number of input water quality parameters used. Box-Behnken three-factor at three levels experimental design was applied for simultaneous spatial, temporal, and input variables optimization of the ANN model. The prediction of DO was performed using a feed-forward back-propagation neural network (BPNN), while the selection of most important inputs was done off-model using multi-filter approach that combines a chi-square ranking in the first step with a correlation-based elimination in the second step. The contour plots of absolute and relative error response surfaces were utilized to determine the optimal values of design factors. From the contour plots, two BPNN models that cover entire Danube flow through Serbia are proposed: an upstream model (BPNN-UP) that covers 8 monitoring sites prior to Belgrade and uses 12 inputs measured in the 7-year period and a downstream model (BPNN-DOWN) which covers 9 monitoring sites and uses 11 input parameters measured in the 6-year period. The main difference between the two models is that BPNN-UP utilizes inputs such as BOD, P, and PO₄^3-, which is in accordance with the fact that this model covers northern part of Serbia (Vojvodina Autonomous Province) which is well-known for agricultural production and extensive use of fertilizers. Both models have shown very good agreement between measured and predicted DO (with R² ≥ 0.86) and demonstrated that they can effectively forecast DO content in the Danube River.