Integrating water quality and operation into prediction of water production in drinking water treatment plants by genetic algorithm enhanced artificial neural network

A Review of Computational Modeling in Wastewater Treatment Processes

Wastewater treatment companies are facing several challenges related to the optimization of energy efficiency, meeting more restricted water quality standards, and resource recovery potential. Over the past decades, computational models have gained recognition as effective tools for addressing some of these challenges, contributing to the economic and operational efficiencies of wastewater treatment plants (WWTPs). To predict the performance of WWTPs, numerous deterministic, stochastic, and time series-based models have been developed. Mechanistic models, incorporating physical and empirical knowledge, are dominant as predictive models. However, these models represent a simplification of reality, resulting in model structure uncertainty and a constant need for calibration. With the increasing amount of available data, data-driven models are becoming more attractive. The implementation of predictive models can revolutionize the way companies manage WWTPs by permitting the development of digital twins for process simulation in (near) real-time. In data-driven models, the structure is not explicitly specified but is instead determined by searching for relationships in the available data. Thus, the main objective of the present review is to discuss the implementation of machine learning models for the prediction of WWTP effluent characteristics and wastewater inflows as well as anomaly detection studies and energy consumption optimization in WWTPs. Furthermore, an overview considering the merging of both mechanistic and machine learning models resulting in hybrid models is presented as a promising approach. A critical assessment of the main gaps and future directions on the implementation of mathematical modeling in wastewater treatment processes is also presented, focusing on topics such as the explainability of data-driven models and the use of Transfer Learning processes.

Coastal groundwater quality prediction using objective-weighted WQI and machine learning approach

The water quality index (WQI) is a globally accepted guideline to indicate the water quality standard of any groundwater resource. Water levels in existing groundwater sources are declining in several coastal zones. Therefore, for monitoring water quality and improving water management, the prediction and identification of groundwater status by an effective technique with higher accuracy is urgently needed. Therefore, this research aims to find an effective model for WQI prediction by comparing entropy and critic weight-based WQI (ENW-WQI and CRITIC-WQI) with multi-layer perceptron artificial neural network (MLP-ANN) technique and also to identify contaminated zones using GIS. Initially, 1000 water sampling datasets with concentrations of several water quality parameters of different coastal blocks of eastern India during 2018 to 2022 are considered for the estimation of ENW-WQI and CRITIC-WQI. It shows 65% and 67% of the samples are excellent to good for drinking. ENW-WQI and CRITIC-WQI-based MLP-ANN models have been established considering different data portioning and hidden neuron numbers. Input variables and appropriate dataset partitioning with hidden neurons for models obtained from correlation and trial-error analysis. Spatial distribution maps are also produced for calculated WQIs using inverse distance weighted interpolation approaches. Three fitting models are obtained: ENW-WQI-MLP-ANN, CRITIC-WQI-MLP-ANN-I and CRITIC-WQI-MLP-ANN-II. CRITIC-WQI-MLP-ANN-II model (data ratio 85:15, network structure 6-12-1, R2 = 0.986, NSE = 0.98, and error rate 0.49%) provides the best accuracy in WQI prediction. The GIS-based WQI maps record several areas related to drinking water quality. The results of this research can help in planning the provision of safe drinking water in the future.

A hybrid deep learning approach to improve real-time effluent quality prediction in wastewater treatment plant

Wastewater treatment plant (WWTP) operation is usually intricate due to large variations in influent characteristics and nonlinear sewage treatment processes. Effective modeling of WWTP effluent water quality can provide valuable decision-making support to facilitate their operations and management. In this study, we developed a novel hybrid deep learning model by combining the temporal convolutional network (TCN) model with the long short-term memory (LSTM) network model to improve the simulation of hourly total nitrogen (TN) concentration in WWTP effluent. The developed model was tested in a WWTP in Jiangsu Province, China, where the prediction results of the hybrid TCN-LSTM model were compared with those of single deep learning models (TCN and LSTM) and traditional machine learning model (feedforward neural network, FFNN). The hybrid TCN-LSTM model could achieve 33.1 % higher accuracy as compared to the single TCN or LSTM model, and its performance could improve by 63.6 % comparing to the traditional FFNN model. The developed hybrid model also exhibited a higher power prediction of WWTP effluent TN for the next multiple time steps within eight hours, as compared to the standalone TCN, LSTM, and FFNN models. Finally, employing model interpretation approach of Shapley additive explanation to identify the key parameters influencing the behavior of WWTP effluent water quality, it was found that removing variables that did not contribute to the model output could further improve modeling efficiency while optimizing monitoring and management strategies.

Automated machine learning-based models for predicting and evaluating antibiotic removal in constructed wetlands

Machine learning models can improve antibiotic removal performance in constructed wetlands (CWs) by optimizing the operation process. However, robust modeling approaches for revealing the complex biochemical treatment process of antibiotics in CWs are still lacking. In this study, two automated machine learning (AutoML) models achieved good performance with different sizes of the training dataset (mean absolute error = 9.94-13.68, coefficient of determination = 0.780-0.877), demonstrating the ability to predict antibiotic removal performance without human intervention. Explainable analysis results (the variable importance and Shapley additive explanations) revealed that the variable substrate type was more influential than the variables of influent wastewater quality and plant type. This study proposed a potential approach to comprehensively understanding the complex effects of key operational variables on antibiotic removal, which serve as a reference for optimizing operational adjustments in the CW process.

Modeling the Chlorine Series from the Treatment Plant of Drinking Water in Constanta, Romania

Ensuring good drinking water quality, which does not damage the population's health, should be a priority of decision factors. Therefore, water treatment must be carried out to remove the contaminants. Chlorination is one of the most used treatment procedures. Modeling the free chlorine residual concentration series in the water distribution network provides the water supply managers with a tool for predicting residual chlorine concentration in the networks. With regard to this idea, this article proposes alternative models for the monthly free chlorine residual concentration series collected at the Palas Constanta Water Treatment Plant, in Romania, from January 2013 to December 2018. The forecasts based on the determined models are provided, and the best results are highlighted.

Water treatment and artificial intelligence techniques: a systematic literature review research

As clean water can be considered among the essentials of human life, there is always a requirement to seek its foremost and high quality. Water primarily becomes polluted due to organic as well as inorganic pollutants, including nutrients, heavy metals, and constant contamination with organic materials. Predicting the quality of water accurately is essential for its better management along with controlling pollution. With stricter laws regarding water treatment to remove organic and biologic materials along with different pollutants, looking for novel technologic procedures will be necessary for improved control of the treatment processes by water utilities. Linear regression-based models with relative simplicity considering water prediction have been typically used as available statistical models. Nevertheless, in a majority of real problems, particularly those associated with modeling of water quality, non-linear patterns will be observed, requiring non-linear models to address them. Thus, artificial intelligence (AI) can be a good candidate in modeling and optimizing the elimination of pollutants from water in empirical settings with the ability to generate ideal operational variables, due to its recent considerable advancements. Management and operation of water treatment procedures are supported technically by these technologies, leading to higher efficiency compared to sole dependence on human operations. Thus, establishing predictive models for water quality and subsequently, more efficient management of water resources would be critically important, serving as a strong tool. A systematic review methodology has been employed in the present work to investigate the previous studies over the time interval of 2010-2020, while analyzing and synthesizing the literature, particularly regarding AI application in water treatment. A total number of 92 articles had addressed the topic under study using AI. Based on the conclusions, the application of AI can obviously facilitate operations, process automation, and management of water resources in significantly volatile contexts.

Operational parameter prediction of electrocoagulation system in a rural decentralized water treatment plant by interpretable machine learning model

Electrocoagulation (EC) is a promising alternative for decentralized drinking water treatment in rural areas as a chemical-free technology. However, seasonal fluctuations of water quality in influent remain a significant challenge for rural decentralized water supply, which was a potential threat to water safety. The frequent operation was required to ensure the effluent water quality by the experienced technicians, who were in shortage in rural areas. If the operational parameters prediction model based on water quality could be established, it might reduce the dependence on technicians. Therefore, an artificial neural network (ANN) model combined with genetic algorithm (GA) was used to establish a prediction model for unattended intelligent operation. Data on water quality and operational parameters were collected from a practical EC system in a decentralized water treatment plant. Seven water quality parameters (e.g., turbidity, temperature, pH and conductivity) were selected as input variables and the operational current was employed as the output. A non-linear relationship between water quality parameters and the operational current was verified by correlation analysis and principal component analysis (PCA). The mean squared error (MSE) and coefficient of determination (R²) were used as evaluation indexes to optimize the structure of the GA-ANN model. Influent turbidity was identified to be crucial in the GA-ANN model by model interpretation using sensitivity analysis and scenario analysis. The Garson weight of turbidity in the seven input variables achieved 45.4%. The predictive accuracy of the GA-ANN model sharply declined from 90% to 67.1% when influent turbidity data were absent. In addition, it was estimated that energy consumption savings of the GA-ANN method declined by 14.2% in comparison with the gradient control method. This study verifies the feasibility and stability of machine learning strategy for unattended operation in the rural decentralized water treatment plant.

Adopting improved Adam optimizer to train dendritic neuron model for water quality prediction

As one of continuous concern all over the world, the problem of water quality may cause diseases and poisoning and even endanger people's lives. Therefore, the prediction of water quality is of great significance to the efficient management of water resources. However, existing prediction algorithms not only require more operation time but also have low accuracy. In recent years, neural networks are widely used to predict water quality, and the computational power of individual neurons has attracted more and more attention. The main content of this research is to use a novel dendritic neuron model (DNM) to predict water quality. In DNM, dendrites combine synapses of different states instead of simple linear weighting, which has a better fitting ability compared with traditional neural networks. In addition, a recent optimization algorithm called AMSGrad (Adaptive Gradient Method) has been introduced to improve the performance of the Adam dendritic neuron model (ADNM). The performance of ADNM is compared with that of traditional neural networks, and the simulation results show that ADNM is better than traditional neural networks in mean square error, root mean square error and other indicators. Furthermore, the stability and accuracy of ADNM are better than those of other conventional models. Based on trained neural networks, policymakers and managers can use the model to predict the water quality. Real-time water quality level at the monitoring site can be presented so that measures can be taken to avoid diseases caused by water quality problems.

Existing Filtration Treatment on Drinking Water Process and Concerns Issues

Water is one of the main sources of life's survival. It is mandatory to have good-quality water, especially for drinking. Many types of available filtration treatment can produce high-quality drinking water. As a result, it is intriguing to determine which treatment is the best. This paper provides a review of available filtration technology specifically for drinking water treatment, including both conventional and advanced treatments, while focusing on membrane filtration treatment. This review covers the concerns that usually exist in membrane filtration treatment, namely membrane fouling. Here, the parameters that influence fouling are identified. This paper also discusses the different ways to handle fouling, either based on prevention, prediction, or control automation. According to the findings, the most common treatment for fouling was prevention. However, this treatment required the use of chemical agents, which will eventually affect human health. The prediction process was usually used to circumvent the process of fouling development. Based on our reviews up to now, there are a limited number of researchers who study membrane fouling control based on automation. Frequently, the treatment method and control strategy are determined individually.

Water and wastewater quality prediction: current trends and challenges in the implementation of artificial neural network

Traditional freshwater supplies have been over-abstracted in the current global problem of water scarcity. Through the analysis of complex experimental and real-time data, to improve the activity of water and wastewater treatment (WWT) systems, an artificial neural network (ANN), a computational model inspired by the human brain, and its variants were created. This review paper focuses on recent trends and advances in modeling and simulating different water and wastewater systems using ANN. This study uses ANN in watershed management, impurity removal from wastewater, and wastewater treatment plants. According to the literature review, ANN can predict nonlinear, linear, and complex systems with high accuracy and well control. Finally, the limitations and future scope of ANNs were discussed. ANN proved itself in the prediction of various water and WWT processes. Still, implementation has practical challenges, which include a lack of data availability, poorly built models, timely updates in developed models, and low repeatability. The use of a proper toolbox, faster computing power, and proper domain knowledge makes the practical implementation of ANN successful. As a result, ANN can build a solid foundation for attracting and motivating investigators to work in this region in the forthcoming.

Groundwater Quality: The Application of Artificial Intelligence

Humans and all other living things depend on having access to clean water, as it is an indispensable essential resource. Therefore, the development of a model that can predict water quality conditions in the future will have substantial societal and economic value. This can be accomplished by using a model that can predict future water quality circumstances. In this study, we employed a sophisticated artificial neural network (ANN) model. This study intends to develop a hybrid model of single exponential smoothing (SES) with bidirectional long short-term memory (BiLSTM) and an adaptive neurofuzzy inference system (ANFIS) to predict water quality (WQ) in different groundwater in the Al-Baha region of Saudi Arabia. Single exponential smoothing (SES) was employed as a preprocessing method to adjust the weight of the dataset, and the output from SES was processed using the BiLSTM and ANFIS models for predicting water quality. The data were randomly divided into two phases, training (70%) and testing (30%). Efficiency statistics were used to evaluate the SES-BiLSTM and SES-ANFIS models' prediction abilities. The results showed that while both the SES-BiLSTM and SES-ANFIS models performed well in predicting the water quality index (WQI), the SES-BiLSTM model performed best with accuracy (R = 99.95% and RMSE = 0.00910) at the testing phase, where the performance of the SES-ANFIS model was R = 99.95% and RMSE = 2.2941 × 100-07. The findings support the idea that the SES-BilSTM and SES-ANFIS models can be used to predict the WQI with high accuracy, which will help to enhance WQ. The results demonstrated that the SES-BiLSTM and SES-ANFIS models' forecasts are accurate and that both seasons' performances are consistent. Similar investigations of groundwater quality prediction for drinking purposes should benefit from the proposed SES-BiLSTM and SES-ANFIS models. Consequently, the results demonstrate that the proposed SES-BiLSTM and SES-ANFIS models are useful tools for predicting whether the groundwater in Al-Baha city is suitable for drinking and irrigation purposes.

Evaluation of water quality using a Takagi-Sugeno fuzzy neural network and determination of heavy metal pollution index in a typical site upstream of the Yellow River

Assessment of river water quality is very important for understanding the impact of human activities on aquatic ecosystems. As the second-largest river in China, the Yellow River's water environment is closely related to the social development and water security of northern China. The Huangshui River is a major tributary of the upper Yellow River, and it supplies water to cities in the lower reaches. In this study, a Takagi-Sugeno (T-S) fuzzy neural network was used to evaluate water quality of the Huangshui River, and pollutant sources were analyzed. The heavy metal pollution index (HPI) was calculated to assess the heavy metal pollution level, and the health risks posed by heavy metal elements were assessed. The results indicated that the main contaminants in the Huangshui River were ammonia nitrogen (NH₃-N) and total phosphorus (TP), which was affected by various activities of industry, agriculture, and urbanization, and the maximum concentration of NH₃-N and TP was 5.90 mg/L and 0.36 mg/L, respectively. The T-S evaluation results of some points in the middle reaches were 3.317 and 3.197, which belonged to Level Ⅳ and the water quality was poor. The concentrations of Cu, Zn and Cr in the river were 0.57-44.58 μg/L, 10-122.50 μg/L and 2-28.67 μg/L, respectively, and they were relatively large. The T-S fuzzy neural network could evaluate water quality, avoiding extreme evaluation results by using fuzzy rules to reduce the influence of pollutant concentrations that are too high or too low. In addition to qualitative categorization of water quality, this approach can also quantitatively assess water quality within a single category. The results of water quality assessment could provide a scientific data support for river management.

Non-invasive prediction of microsatellite instability in colorectal cancer by a genetic algorithm-enhanced artificial neural network-based CT radiomics signature

OBJECTIVE

The stratification of microsatellite instability (MSI) status assists clinicians in making treatment decisions for colorectal cancer (CRC) patients. This study aimed to establish a CT-based radiomics signature to predict MSI status in patients with CRC.

METHODS

A total of 837 CRC patients who underwent preoperative enhanced CT and had available MSI status data were recruited from two hospitals. Radiomics features were extracted from segmented tumours, and a series of data balancing and feature selection strategies were used to select MSI-related features. Finally, an MSI-related radiomics signature was constructed using a genetic algorithm-enhanced artificial neural network model. Combined and clinical models were constructed using multivariate logistic regression analyses by integrating the clinical factors with or without the signature. A Kaplan-Meier survival analysis was conducted to explore the prognostic information of the signature in patients with CRC.

RESULTS

Ten features were selected to construct a signature which showed robust performance in both the internal and external validation cohorts, with areas under the curves (AUC) of 0.788 and 0.775, respectively. The performance of the signature was comparable to that of the combined model (AUCs of 0.777 and 0.767, respectively) and it outperformed the clinical model constituting age and tumour location (AUCs of 0.768 and 0.623, respectively). Survival analysis demonstrated that the signature could stratify patients with stage II CRC according to prognosis (HR: 0.402, p = 0.029).

CONCLUSIONS

This study built a robust radiomics signature for identifying the MSI status of CRC patients, which may assist individualised treatment decisions.

KEY POINTS

• Our well-designed modelling strategies helped overcome the problem of data imbalance caused by the low incidence of MSI. • Genetic algorithm-enhanced artificial neural network-based CT radiomics signature can effectively distinguish the MSI status of CRC patients. • Kaplan-Meier survival analysis demonstrated that our signature could significantly stratify stage II CRC patients into high- and low-risk groups.

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.

A novel approach on water resource management with Multi-Criteria Optimization and Intelligent Water Demand Forecasting in Saudi Arabia

Ever-increasing demands for freshwater resources have elevated the likelihood of severe water stress in several places of Saudi Arabia during the last several decades. With effective decision-making processes, development objectives on water resource management emerge. In the following series of research articles, recent innovations in various objective demand forecasting systems are examined and contrasted in terms of their utility in resolving tough challenges in water resource management. Hence, this study proposes a novel approach to water resource management integrating Multi-Criteria Optimization and Intelligent Water Demand Forecasting (MCO-IWDF). This framework addresses the challenges in allocating various water resources to multiple water sectors in a future changing environment. In order to plan for future water needs, water managers use a variety of tools. When forecasting future water demand, the most common method is to estimate current per-capita consumption (gpcd) and multiply this by the expected population growth. Conserving water in the Kingdom of Saudi Arabia to improve irrigation issues. This research analyzes the current situation of available water resources and the water demand in Saudi Arabia. The machine intelligence and big data analytic approach improve the proposed water resource management scheme. The simulation analysis identifies the highest performance in demand prediction accuracy of 98.96% and optimization ratio of 97.87% compared to the existing models. Over time, a mathematical model is used to conduct simulation experiments. Studying the problem, creating a model and collecting data are just some of the steps involved in simulation research. Response analysis and a simulation report are also part of this process. The case study analysis results in a significant satisfactory level of 99.23%.

Enhancing Real-Time Prediction of Effluent Water Quality of Wastewater Treatment Plant Based on Improved Feedforward Neural Network Coupled with Optimization Algorithm

To provide real-time prediction of wastewater treatment plant (WWTP) effluent water quality, a machine learning (ML) model was developed by combining an improved feedforward neural network (IFFNN) with an optimization algorithm. Data used as input variables of the IFFNN included hourly influent water quality parameters, influent flow rate and WWTP process monitoring and operational parameters. Additionally, input variables included historical effluent water quality parameters for future prediction. The model was demonstrated in a WWTP in Jiangsu Province, China, where prediction of effluent chemical oxygen demand (COD) and total nitrogen (TN) with large variations were tested. Relative to the traditional feedforward neural network (FFNN) model without considering historical effluent water quality parameter input, the IFFNN enhanced prediction performance by 52.3% (COD) and 72.6% (TN) based on the mean absolute percentage errors of test datasets, after its model structure was optimized with a genetic algorithm (GA). The problem of over-fitting could also be overcome through the use of the IFFNN, with the determination of coefficient increased from 0.20 to 0.76 for test datasets of effluent COD. The GA-IFFNN model, which was efficient in capturing complex non-linear relationships and extrapolation, could be a useful tool for real-time direction of regulatory changes in WWTP operations.

Multi-Expression Programming (MEP): Water Quality Assessment Using Water Quality Indices

Water contamination is indeed a worldwide problem that threatens public health, environmental protection, and agricultural productivity. The distinctive attributes of machine learning (ML)-based modelling can provide in-depth understanding into increasing water quality challenges. This study presents the development of a multi-expression programming (MEP) based predictive model for water quality parameters, i.e., electrical conductivity (EC) and total dissolved solids (TDS) in the upper Indus River at two different outlet locations using 360 readings collected on a monthly basis. The optimized MEP models were assessed using different statistical measurements i.e., coefficient-of-determination (R2), root-mean-square error (RMSE), mean-absolute error (MAE), root-mean-square-logarithmic error (RMSLE) and mean-absolute-percent error (MAPE). The results show that the R2 in the testing phase (subjected to unseen data) for EC-MEP and TDS-MEP models is above 0.90, i.e., 0.9674 and 0.9725, respectively, reflecting the higher accuracy and generalized performance. Also, the error measures are quite lower. In accordance with MAPE statistics, both the MEP models shows an “excellent” performance in all three stages. In comparison with traditional non-linear regression models (NLRMs), the developed machine learning models have good generalization capabilities. The sensitivity analysis of the developed MEP models with regard to the significance of each input on the forecasted water quality parameters suggests that Cl and HCO3 have substantial impacts on the predictions of MEP models (EC and TDS), with a sensitiveness index above 0.90, although the influence of the Na is the less prominent. The results of this research suggest that the development of intelligence models for EC and TDS are cost effective and viable for the evaluation and monitoring of the quality of river water.

Development of artificial neural networks software for arsenic adsorption from an aqueous environment

Arsenic contamination is a global problem, as it affects the health of millions of people. For this study, data-driven artificial neural network (ANN) software was developed to predict and validate the removal of As(V) from an aqueous solution using graphene oxide (GO) under various experimental conditions. A reliable model for wastewater treatment is essential in order to predict its overall performance and to provide an idea of how to control its operation. This model considered the adsorption process parameters (initial concentration, adsorbent dosage, pH, and residence time) as the input variables and arsenic removal as the only output. The ANN model predicted the adsorption efficiency with high accuracy for both training and testing datasets, when compared with the available response surface methodology (RSM) model. Based on the best model synaptic weights, user-friendly ANN software was created to predict and analyze arsenic removal as a function of adsorption process parameters. We developed various graphical user interfaces (GUI) for easy use of the developed model. Thus, a researcher can efficiently operate the software without an understanding of programming or artificial neural networks. Sensitivity analysis and quantitative estimation were carried out to study the function of adsorption process parameter variables on As(V) removal efficiency, using the GUI of the model. The model prediction shows that the adsorbent dosages, initial concentration, and pH are the most influential parameters. The efficiency was increased as the adsorbent dosages increased, decreasing with initial concentration and pH. The result show that the pH 2.0-5.0 is optimal for adsorbent efficiency (%).

Machine learning in natural and engineered water systems

Water resources of desired quality and quantity are the foundation for human survival and sustainable development. To better protect the water environment and conserve water resources, efficient water management, purification, and transportation are of critical importance. In recent years, machine learning (ML) has exhibited its practicability, reliability, and high efficiency in numerous applications; furthermore, it has solved conventional and emerging problems in both natural and engineered water systems. For example, ML can predict various water quality indicators in situ and real-time by considering the complex interactions among water-related variables. ML approaches can also solve emerging pollution problems with proven rules or universal mechanisms summarized from the related research. Moreover, by applying image recognition technology to analyze the relationships between image information and physicochemical properties of the research object, ML can effectively identify and characterize specific contaminants. In view of the bright prospects of ML, this review comprehensively summarizes the development of ML applications in natural and engineered water systems. First, the concept and modeling steps of ML are briefly introduced, including data preparation, algorithm selection and model evaluation. In addition, comprehensive applications of ML in recent studies, including predicting water quality, mapping groundwater contaminants, classifying water resources, tracing contaminant sources, and evaluating pollutant toxicity in natural water systems, as well as modeling treatment techniques, assisting characterization analysis, purifying and distributing drinking water, and collecting and treating sewage water in engineered water systems, are summarized. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of ML algorithms for different studies, as well as prospects on the application and development of ML in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

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.

Magnetic properties and its application in the prediction of potentially toxic elements in aquatic products by machine learning

Magnetic measurement was provided to substitute for time-consuming conventional methods for determination of potentially toxic elements. Both the concentrations of 12 elements and 9 magnetic parameters were determined in 700 muscle tissue samples from the snail Bellamya aeruginosa, shrimp species Exopalaemon modestus and Macrobrachium nipponense, and fish species Hemisalanx prognathous Regan, Coilia ectenes taihuensis, and Culer alburnus Basilewsky collected from Chaohu Lake during different hydrological periods. Spherical and irregular iron oxide particles were observed in the muscle tissues of the studied aquatic products. A field survey of the exposure parameters in humans, such as per capita intake dose of local aquatic products, found no evidence that consumption of the tested species poses a potential health risk. Redundancy analysis revealed different degrees of correlation between the magnetic parameters and concentrations of elements in aquatic products. Back-propagation artificial neural network (BP-ANN) and support vector machine (SVM) models were applied to predict elemental concentrations in aquatic products, using magnetic parameters as input. SVM models performed well in predicting the presence of Cr and Ni, with R and index of agreement values of >0.8 in both training and validation stages as well as relatively low errors. The BP-ANN and SVM models both performed relatively poorly in predicting the presence of Cd and Zn in aquatic products, with R values between 0.333 and 0.718 for Cd and between 0.454 and 0.664 for Zn in training and validation stages. For most of the elements, a better R value was obtained with the SVM than with BP-ANN model. The R of Co, Cr, Cu, Ni, and Ti in the training and validation stages of snail in the SVM model were >0.8. This study is a first step in developing a novel approach allowing the rapid monitoring of potentially toxic elements concentrations in aquatic products.

Rapid diagnosis of heavy metal pollution in lake sediments based on environmental magnetism and machine learning

Environmental magnetism in combination with machine learning can be used to monitor heavy metal pollution in sediments. Magnetic parameters and heavy metal concentrations of sediments from Chaohu Lake (China) were analyzed. The magnetic measurements, high- and low-temperature curves, and hysteresis loops showed the primary magnetic minerals were ferrimagnetic minerals in sediments. For most metals, their concentrations were highest during the wet season and lowest during the medium-water period. Cd, Hg, and Zn were moderately enriched and Cd and Hg posed a considerable ecological risk. A redundancy analysis indicated a relationship between physicochemical indexes and magnetic parameters and heavy metal concentrations. An artificial neural network (ANN) and support vector machine (SVM) were used to construct six models to predict the heavy metal concentrations and ecological risk index. The inclusion of both the physicochemical indexes and magnetic parameters as input factors in the models were significantly ameliorated the simulation accuracy for the majority of heavy metals. The training and test R, for Be, Fe, Pb, Zn, As, Cu, and Cr were > 0.8. The SVM showed better performance and hence it has potential for the efficient and economical long-term tracking and monitoring of heavy metal pollution in lake sediments.

Artificial neural networks modeling for lead removal from aqueous solutions using iron oxide nanocomposites from bio-waste mass

Heavy metal ions in aqueous solutions are taken into account as one of the most harmful environmental issues that ominously affect human health. Pb(II) is a common pollutant among heavy metals found in industrial wastewater, and various methods were developed to remove the Pb(II). The adsorption method was more efficient, cheap, and eco-friendly to remove the Pb(II) from aqueous solutions. The removal efficiency depends on the process parameters (initial concentration, the adsorbent dosage of T-Fe3O4 nanocomposites, residence time, and adsorbent pH). The relationship between the process parameters and output is non-linear and complex. The purpose of the present study is to develop an artificial neural networks (ANN) model to estimate and analyze the relationship between Pb(II) removal and adsorption process parameters. The model was trained with the backpropagation algorithm. The model was validated with the unseen datasets. The correlation coefficient adj.R² values for total datasets is 0.991. The relationship between the parameters and Pb(II) removal was analyzed by sensitivity analysis and creating a virtual adsorption process. The study determined that the ANN modeling was a reliable tool for predicting and optimizing adsorption process parameters for maximum lead removal from aqueous solutions.

Construction Schedule Risk Assessment and Management Strategy for Foreign General Contractors Working in the Ethiopian Construction Industry

Construction project schedule delay is a worldwide concern and especially severe in the Ethiopian construction industry. This study developed a Construction Schedule Risk Assessment Model (CSRAM) and a management strategy for foreign general contractors (FGCs). 94 construction projects with schedule delay were collected and a questionnaire survey of 75 domain experts was conducted to systematically select 22 risk factors. In CSRAM, the artificial neural network (ANN) inference model was developed to predict the project schedule delay. Integrating it with the Garson algorithm (GA), the relative weights of risk factors with rankings were calculated and identified. For comparison, the Relative Importance Index (RII) method was also applied to rank the risk factors. Management strategies were developed to improve the three highest-ranked factors identified using the GA (change order, corruption/bribery, and delay in payment), and the RII (poor resource management, corruption/bribery, and delay in material delivery). Moreover, the improvement results were used as inputs for the trained ANN to conduct a sensitivity analysis. The findings of this study indicate that improvements in the factors that considerably affect the construction schedule can significantly reduce construction schedule delays. This study acts as an important reference for FGCs who plan to enter or work in the Ethiopian construction industry.

Predictive Modeling Approach for Surface Water Quality: Development and Comparison of Machine Learning Models

Water pollution is an increasing global issue that societies are facing and is threating human health, ecosystem functions and agriculture production. The distinguished features of artificial intelligence (AI) based modeling can deliver a deep insight pertaining to rising water quality concerns. The current study investigates the predictive performance of gene expression programming (GEP), artificial neural network (ANN) and linear regression model (LRM) for modeling monthly total dissolved solids (TDS) and specific conductivity (EC) in the upper Indus River at two outlet stations. In total, 30 years of historical water quality data, comprising 360 TDS and EC monthly records, were used for models training and testing. Based on a significant correlation, the TDS and EC modeling were correlated with seven input parameters. Results were evaluated using various performance measure indicators, error assessment and external criteria. The simulated outcome of the models indicated a strong association with actual data where the correlation coefficient above 0.9 was observed for both TDS and EC. Both the GEP and ANN models remained the reliable techniques in predicting TDS and EC. The formulated GEP mathematical equations depict its novelty as compared to ANN and LRM. The results of sensitivity analysis indicated the increasing trend of input variables affecting TDS as HCO3− (22.33%) > Cl− (21.66%) > Mg2+ (16.98%) > Na+ (14.55%) > Ca2+ (12.92%) > SO42− (11.55%) > pH (0%), while, in the case of EC, it followed the trend as HCO3− (42.36%) > SO42−(25.63%) > Ca2+ (13.59%) > Cl− (12.8%) > Na+ (5.01%) > pH (0.61%) > Mg2+ (0%). The parametric analysis revealed that models have incorporated the effect of all the input parameters in the modeling process. The external assessment criteria confirmed the generalized outcome and robustness of the proposed approaches. Conclusively, the outcomes of this study demonstrated that the formulation of AI based models are cost effective and helpful for river water quality assessment, management and policy making.

Pore-scale identification of residual morphology and genetic mechanisms of nano emulsified vegetable oil in porous media using 3D X-ray microtomography

The application of emulsified vegetable oil (EVO) has attracted widespread attention in environmental remediation. Residual morphology is an important factor affecting its migration and mass transfer. However, proper identification of the EVO residual morphology at pore-scale has still remained a challenging task. Hence, this study aimed to identify the residual morphology of nanoscale EVO (NEVO) through developing a method combining natural breaks with 3D X-ray microtomography, then further explore the genetic mechanism of each residual morphology to verify the rationality of this method. The results showed that the natural breaks method can effectively classify the residual morphology of NEVO. Four morphologies including cluster, throat, corner, and membrane state were obtained from coarse, medium, and fine sands with a total proportion of 18.3%, 26.2%, and 30.8%. The cluster state was the main residual morphology, accounting for 10.0- 16.2%, then followed by corner-throat state and membrane state. Pore radius, throat radius, and length were confirmed providing sufficient evidences for cluster residues, because these factors determined the connectivity of porous media for the trapping of droplets. Comparison of the theoretical and actual results implied that capillarity coupling pore-throat shape jointly controlled corner and throat residues. Grain surface roughness and specific surface area were the main factors of membrane residue. The different residual morphologies of NEVO identified by the natural breaks method can reasonably explain their magnitude and controlling mechanisms, which in turn confirms the rationality of this method. Although the proportions of each form are related to the experimental conditions, the classification method and mechanism are of great significance for understanding NEVO residues.

Proposed formulation of surface water quality and modelling using gene expression, machine learning, and regression techniques

The rising water pollution from anthropogenic factors motivates further research in developing water quality predicting models. The available models have certain limitations due to limited timespan data and the incapability to provide empirical expressions. This study is devoted to model and derive empirical equations for surface water quality of upper Indus river basin using a 30-year dataset with machine learning techniques and then to determine the most reliable model capable to accurately predict river water quality. Total dissolve solids (TDS) and electrical conductivity (EC) were used as dependent variables, whereas eight parameters were used as independent variables with 70 and 30% data for model training and testing, respectively. Various evaluation criteria, i.e., Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE), coefficient of determination (R²), and mean absolute error (MAE), were used to assess the performance of models. The data is also validated with the help of k-fold cross-validation using R² and RMSE. The results indicated a strong correlation with NSE and R² both above 0.85 for all the developed models. Gene expression programming (GEP) outperformed both artificial neural network (ANN) and linear and non-linear regression models for TDS and EC. The sensitivity and parametric analyses revealed that bicarbonate is the most sensitive parameter influencing both TDS and EC models. Two equations were derived and formulated to represent the novel results of GEP model to help authorities in the effective monitoring of river water quality.

Tracing nitrogenous byproducts during ozonation in the presence of bromide and ammonia using stable isotope labeling and high resolution mass spectrometry

Ammonia has been widely used to inhibit bromate formation during ozonation. However, our recent study found that during ozonation in the presence of bromide and ammonia, toxicity increased under certain conditions that might be attributed to the formation of nitrogenous byproducts. Herein, a typical structural moiety of natural organic matter (NOM), hydroquinone, was evaluated for its potential to form nitrogenous byproducts. During ozonation of the hydroquinone solution containing bromide and ammonia, toxicity of organic byproducts increased significantly. As organic bromine was hardly detected, organic nitrogen was responsible for the increased toxicity. An effective method combining ultra-performance liquid chromatography in tandem with high resolution mass spectrometry (UPLC-HRMS) with an isotope labeling strategy was used to trace nitrogenous byproducts. Four newly formed nitrogenous byproducts were detected, two of which were also detected in Suwannee River natural organic matter (SRNOM) solution treated under the same ozonation condition. Furthermore, the molecular structures and formation pathways of these nitrogenous byproducts were proposed. This study highlights that, despite the widespread use, adding ammonia to inhibit bromate formation during ozonation might increase the toxicity posed by nitrogenous byproducts. During ozonation in the presence of bromide and ammonia, particular attention should be paid to nitrogenous byproducts.

Developing a framework for classifying water lead levels at private drinking water systems: A Bayesian Belief Network approach

The presence of lead in drinking water creates a public health crisis, as lead causes neurological damage at low levels of exposure. The objective of this research is to explore modeling approaches to predict the risk of lead at private drinking water systems. This research uses Bayesian Network approaches to explore interactions among household characteristics, geological parameters, observations of tap water, and laboratory tests of water quality parameters. A knowledge discovery framework is developed by integrating methods for data discretization, feature selection, and Bayes classifiers. Forward selection and backward selection are explored for feature selection. Discretization approaches, including domain-knowledge, statistical, and information-based approaches, are tested to discretize continuous features. Bayes classifiers that are tested include General Bayesian Network, Naive Bayes, and Tree-Augmented Naive Bayes, which are applied to identify Directed Acyclic Graphs (DAGs). Bayesian inference is used to fit conditional probability tables for each DAG. The Bayesian framework is applied to fit models for a dataset collected by the Virginia Household Water Quality Program (VAHWQP), which collected water samples and conducted household surveys at 2,146 households that use private water systems, including wells and springs, in Virginia during 2012 and 2013. Relationships among laboratory-tested water quality parameters, observations of tap water, and household characteristics, including plumbing type, source water, household location, and on-site water treatment are explored to develop features for predicting water lead levels. Results demonstrate that Naive Bayes classifiers perform best based on recall and precision, when compared with other classifiers. Copper is the most significant predictor of lead, and other important predictors include county, pH, and on-site water treatment. Feature selection methods have a marginal effect on performance, and discretization methods can greatly affect model performance when paired with classifiers. Owners of private wells remain disadvantaged and may be at an elevated level of risk, because utilities and governing agencies are not responsible for ensuring that lead levels meet the Lead and Copper Rule for private wells. Insight gained from models can be used to identify water quality parameters, plumbing characteristics, and household variables that increase the likelihood of high water lead levels to inform decisions about lead testing and treatment.

Simulating a combined lysis-cryptic and biological nitrogen removal system treating domestic wastewater at low C/N ratios using artificial neural network

In this study, a combined alkaline (ALK) and ultrasonication (ULS) sludge lysis-cryptic pretreatment and anoxic/oxic (AO) system (AO + ALK/ULS) was developed to enhance biological nitrogen removal (BNR) in domestic wastewater with a low carbon/nitrogen (C/N) ratio. A real-time control strategy for the AO + ALK/ULS system was designed to optimize the sludge lysate return ratio (R_SLR) under variable sludge concentrations and variations in the influent C/N (⩽ 5). A multi-layered backpropagation artificial neural network (BPANN) model with network topology of 1 input layer, 3 hidden layers, and 1 output layer, using the Levenberg-Marquardt algorithm, was developed and validated. Experimental and predicted data showed significant concurrence, verified with a high regression coefficient (R² = 0.9513) and accuracy of the BPANN. The BPANN model effectively captured the complex nonlinear relationships between the related input variables and effluent output in the combined lysis-cryptic + BNR system. The model could be used to support the real-time dynamic response and process optimization control to treat low C/N domestic wastewater.

Application of neural network and time series modeling to study the suitability of drain water quality for irrigation: a case study from Egypt

Limited water resources are one of the major challenges facing Egypt during the current stage. The agricultural drainage water is an important water resource which can be reused for agriculture. Thus, the current study aims to assess the quality of drainage water for irrigation purpose through monitoring and predicting its suitability for irrigation. The chemical composition of Bahr El-Baqr water drain, especially salinity, as well as ions are mainly involved in calculating indicators of water suitability for irrigation, i.e., Ca²⁺, Mg²⁺, Na⁺, K⁺, HCO^-3, Cl^-, and SO₄^2-. Further analysis was carried out to evaluate the irrigation water quality index (IWQI) through integrated approaches and artificial neural network (ANN) model. Further, ARIMA models were developed to forecast IWQI of Bahr El-Baqr drain in Egypt. The results indicated that the computed IWQI values ranged between 46 and 81. Around 11% of the samples were classified as excellent water, while 89% of the samples were categorized as good water. The results of IWQI showed a standard deviation of 8.59 with a mean of 62.25, indicating that IWQI varied by 13.79% from the average. ANN model showed much higher prediction accuracy in IWQI modeling with R² value greater than 0.98 during training, testing and validation. A relatively good correlation was obtained, between the actual and forecasted IWQI based on the Akaike information criterion (AIC); the best fit models were ARIMA (1,0) (0,0) without seasonality. The determination coefficient (R²) of ARIMA models was 0.23. Accordingly, 23% of IWQI variability could be explained by different model parameters. These findings will support the water resources managers and decision-makers to manage the irrigation water resources that can be implemented in the future.

Multi-Model Coupling Water Demand Prediction Optimization Method for Megacities Based on Time Series Decomposition

The water supply in megacities can be affected by the living habits and population mobility, so the fluctuation degree of daily water supply data is acute, which presents a great challenge to the water demand prediction. This is because that non-stationarity of daily data can have a large influence on the generalization ability of models. In this study, the Hodrick-Prescott (HP) and wavelet transform (WT) methods were used to carry out decomposition of daily data to solve the non-stationarity problem. The bidirectional long short term memory (BLSTM), seasonal autoregressive integrated moving average (SARIMA) and Gaussian radial basis function neural network (GRBFNN) were developed to carry out prediction of different subseries. The ensemble learning was introduced to improve the generalization ability of models, and prediction interval was generated based on student's t-test to cope with the variation of water supply laws. This study method was applied to the daily water demand prediction in Shenzhen and cross-validation was performed. The results show that WT is superior to HP decomposition method, but maximum decomposition level of WT should not be set too high, otherwise the trend characteristics of subseries will be weakened. Although the corona virus disease 2019 (COVID-19) outbreak caused a variation in water supply laws, this variation is still within the prediction interval. The WT and coupling models accurately predict water demand and provide the optimal mean square error (0.17%), Nash-Sutcliffe efficiency (97.21%), mean relative error (0.1), mean absolute error (3.32%), and correlation coefficient (0.99).

Towards urban resilience through Sustainable Drainage Systems: A multi-objective optimisation problem

The necessity of incorporating a resilience-informed approach into urban planning and its decision-making is felt now more than any time previously, particularly in low and middle income countries. In order to achieve a successful transition to sustainable, resilient and cost-effective cities, there is a growing attention given to more effective integration of nature-based solutions, such as Sustainable Drainage Systems (SuDS), with other urban components. The experience of SuDS integration with urban planning, in developed cities, has proven to be an effective strategy with a wide range of advantages and lower costs. The effective design and implementation of SuDS requires a multi-objective approach by which all four pillars of SuDS design (i.e., water quality, water quantity, amenity and biodiversity) are considered in connection to other urban, social, and economic aspects and constraints. This study develops a resilience-driven multi-objective optimisation model aiming to provide a Pareto-front of optimised solutions for effective incorporation of SuDS into (peri)urban planning, applied to a case study in Brazil. This model adopts the SuDS's two pillars of water quality and water quantity as the optimisation objectives with its level of spatial distribution as decision variables. Also, an improved quality of life index (iQoL) is developed to re-evaluate the optimal engineering solutions to encompass the amenity and biodiversity pillars of SuDS. Rain barrels, green roofs, bio-retention tanks, vegetation grass swales and permeable pavements are the suitable SuDS options identified in this study. The findings show that the most resilient solutions are costly but this does not guarantee higher iQoL values. Bio-retention tanks and grass swales play effective roles in promotion of water quality resilience but this comes with considerable increase in costs. Permeable pavements and green roofs are effective strategies when flood resilience is a priority. Rain barrel is a preferred solution due to the dominance of residential areas in the study area and the lower cost of this option.

Efficiency evaluation of reverse osmosis desalination plant using hybridized multilayer perceptron with particle swarm optimization

The scarcity of freshwater causes the necessity for water delineation of brackish water. Reverse osmosis (RO) is one of the popular strategies characterized with lower cost and simple processing procedure compared to the other desalination techniques. The current research is conducted to investigate the efficiency the RO process based on one-week advance prediction of total dissolved solids (TDS) and permeate flow rate for Sistan and Bluchistan provinces located in Iran region. The water parameters including pH, feed pressure temperature, and conductivity are used to construct the prediction matrix. A newly hybrid data-intelligence (DI) model called multilayer perceptron hybridized with particle swarm optimization (MLP-PSO) is developed for the investigation. The potential of the proposed MLP-PSO model is validated against two predominate DI models including support vector machine (SVM) and M5Tree (M5T) models. The results evidenced the potential of the proposed MLP-PSO model over the SVM and M5T models in predicting the TDS and permeate flow rate. In addition, the proposed model attained lower uncertainty for the simulated data. Overall, the feasibility of the hybridized MLP-PSO achieved remarkable predictability for the RO process.

Using Machine-Learning Algorithms for Eutrophication Modeling: Case Study of Mar Menor Lagoon (Spain)

The Mar Menor is a hypersaline coastal lagoon with high environmental value and a characteristic example of a highly anthropized hydro-ecosystem located in the southeast of Spain. An unprecedented eutrophication crisis in 2016 and 2019 with abrupt changes in the quality of its waters caused a great social alarm. Understanding and modeling the level of a eutrophication indicator, such as chlorophyll-a (Chl-a), benefits the management of this complex system. In this study, we investigate the potential machine learning (ML) methods to predict the level of Chl-a. Particularly, Multilayer Neural Networks (MLNNs) and Support Vector Regressions (SVRs) are evaluated using as a target dataset information of up to nine different water quality parameters. The most relevant input combinations were extracted using wrapper feature selection methods which simplified the structure of the model, resulting in a more accurate and efficient procedure. Although the performance in the validation phase showed that SVR models obtained better results than MLNNs, experimental results indicated that both ML algorithms provide satisfactory results in the prediction of Chl-a concentration, reaching up to 0.7 R²_CV (cross-validated coefficient of determination) for the best-fit models.