Deep neural networks for modeling fouling growth and flux decline during NF/RO membrane filtration

Integrating artificial intelligence modeling and membrane technologies for advanced wastewater treatment: Research progress and future perspectives

Membrane technologies have become proficient alternatives for advanced wastewater treatment, ensuring high contaminant removal and sustainable resource recovery. Despite significant progress, ongoing research efforts aim to further optimize treatment performance. Among the challenges faced, membrane fouling persists as a relevant obstacle in membrane technologies, necessitating the development of more effective mitigation strategies. Mathematical models, widely employed for predicting treatment performance, generally exhibit low accuracy and suffer from uncertainties due to the complex and variable nature of wastewater. To overcome these limitations, numerous studies have proposed artificial intelligence (AI) modeling to accurately predict membrane technologies' performance and fouling mechanisms. This approach aims to provide advanced simulations and predictions, thereby enhancing process control, optimization, and intensification. This literature review explores recent advancements in modeling membrane-based wastewater treatment processes through AI models. The analysis highlights the enormous potential of this research field in enhancing the efficiency of membrane technologies. The role of AI modeling in defining optimal operating conditions, developing effective strategies for membrane fouling mitigation, enhancing the performance of novel membrane-based technologies, and improving membrane fabrication techniques is discussed. These enhanced process optimization and control strategies driven by AI modeling ensure improved effluent quality, optimized resource consumption, and minimized operating costs. The potential contribution of this cutting-edge approach to a paradigm shift toward sustainable wastewater treatment is examined. Finally, this review outlines future perspectives, emphasizing the research challenges that require attention to overcome the current limitations hindering the integration of AI modeling in wastewater treatment plants.

Artificial neural network modeling for the prediction, estimation, and treatment of diverse wastewaters: A comprehensive review and future perspective

The application of artificial neural networks (ANNs) in the treatment of wastewater has achieved increasing attention, as it enhances the efficiency and sustainability of wastewater treatment plants (WWTPs). This paper explores the application of ANN-based models in WWTPs, focusing on the latest published research work, by presenting the effectiveness of ANNs in predicting, estimating, and treatment of diverse types of wastewater. Furthermore, this review comprehensively examines the applicability of the ANNs in various processes and methods used for wastewater treatment, including membrane and membrane bioreactors, coagulation/flocculation, UV-disinfection processes, and biological treatment systems. Additionally, it provides a detailed analysis of pollutants viz organic and inorganic substances, nutrients, pharmaceuticals, drugs, pesticides, dyes, etc., from wastewater, utilizing both ANN and ANN-based models. Moreover, it assesses the techno-economic value of ANNs, provides cost estimation and energy analysis, and outlines promising future research directions of ANNs in wastewater treatment. AI-based techniques are used to predict parameters such as chemical oxygen demand (COD) and biological oxygen demand (BOD) in WWTP influent. ANNs have been formed for the estimation of the removal efficiency of pollutants such as total nitrogen (TN), total phosphorus (TP), BOD, and total suspended solids (TSS) in the effluent of WWTPs. The literature also discloses the use of AI techniques in WWT is an economical and energy-effective method. AI enhances the efficiency of the pumping system, leading to energy conservation with an impressive average savings of approximately 10%. The system can achieve a maximum energy savings state of 25%, accompanied by a notable reduction in costs of up to 30%.

Unveiling the spatiotemporal dynamics of membrane fouling: A focused review on dynamic fouling characterization techniques and future perspectives

Membrane technology has emerged as a crucial method for obtaining clean water from unconventional sources in the face of water scarcity. It finds wide applications in wastewater treatment, advanced treatment, and desalination of seawater and brackish water. However, membrane fouling poses a huge challenge that limits the development of membrane-based water treatment technologies. Characterizing the dynamics of membrane fouling is crucial for understanding its development, mechanisms, and effective mitigation. Instrumental techniques that enable in situ or real-time characterization of the dynamics of membrane fouling provide insights into the temporal and spatial evolution of fouling, which play a crucial role in understanding the fouling mechanism and the formulation of membrane control strategies. This review consolidates existing knowledge about the principal advanced instrumental analysis technologies employed to characterize the dynamics of membrane fouling, in terms of membrane structure, morphology, and intermolecular forces. Working principles, applications, and limitations of each technique are discussed, enabling researchers to select appropriate methods for their specific studies. Furthermore, prospects for the future development of dynamic characterization techniques for membrane fouling are discussed, underscoring the need for continued research and innovation in this field to overcome the challenges posed by membrane fouling.

Applications of artificial intelligence (AI) in drinking water treatment processes: Possibilities

In water treatment processes (WTPs), artificial intelligence (AI) based techniques, particularly machine learning (ML) models have been increasingly applied in decision-making activities, process control and optimization, and cost management. At least 91 peer-reviewed articles published since 1997 reported the application of AI techniques to coagulation/flocculation (41), membrane filtration (21), disinfection byproducts (DBPs) formation (13), adsorption (16) and other operational management in WTPs. In this paper, these publications were reviewed with the goal of assessing the development and applications of AI techniques in WTPs and determining their limitations and areas for improvement. The applications of the AI techniques have improved the predictive capabilities of coagulant dosages, membrane flux, rejection and fouling, disinfection byproducts (DBPs) formation and pollutants' removal for the WTPs. The deep learning (DL) technology showed excellent extraction capabilities for features and data mining ability, which can develop an image recognition-based DL framework to establish the relationship among the shapes of flocs and dosages of coagulant. Further, the hybrid techniques (e.g., combination of regression and AI; physical/kinetics and AI) have shown better predictive performances. The future research directions to achieve better control for WTPs through improving these techniques were also emphasized.

Role of inorganic foulants in the aging and deterioration of low-pressure membranes during the chemical cleaning process in surface water treatment: A review

Low-pressure membrane (LPM) filtration, including microfiltration (MF) and ultrafiltration (UF), is a promising technology for the treatment of surface water for drinking and other purposes. Various configurations and operational sequences have been developed to ensure the sustainable provision of clean water by overcoming fouling problems. In the literature, various periodic physical and/or chemical approaches to the cleaning of LPMs have been reported, but little data is available on the aging of MF/UF membranes that results from the interaction between the foulants and the cleaning agent. Periodic physical cleaning of the membrane is expected to return the membrane to its original performance capacity, but it only recovers to a certain level because the remaining foulants cause irreversible fouling. Chemical cleaning can then be employed to recover the membrane from this irreversible fouling but, in the process, it can cause irrecoverable damage to the membrane. In this review, the foulants responsible for irrecoverable damage to MF/UF membranes are summarized, and their interaction with cleaning agents and other foulants is described. The impact of these foulants on various membrane parameters, including filtration efficiency, flux decline, permeability, membrane characterization, and membrane integrity are also summarized and discussed in detail. In addition, mitigation options and future prospects are also discussed with regard to increasing the operational life span of a membrane in a cost-effective manner. Ultimately, this review suggests an advanced control system based on membrane-foulant interactions under the impact of various operational parameters to mitigate the integrity loss of membranes.

A Review on Membrane Fouling Prediction Using Artificial Neural Networks (ANNs)

Membrane fouling is a major hurdle to effective pressure-driven membrane processes, such as microfiltration (MF), ultrafiltration (UF), nanofiltration (NF), and reverse osmosis (RO). Fouling refers to the accumulation of particles, organic and inorganic matter, and microbial cells on the membrane's external and internal surface, which reduces the permeate flux and increases the needed transmembrane pressure. Various factors affect membrane fouling, including feed water quality, membrane characteristics, operating conditions, and cleaning protocols. Several models have been developed to predict membrane fouling in pressure-driven processes. These models can be divided into traditional empirical, mechanistic, and artificial intelligence (AI)-based models. Artificial neural networks (ANNs) are powerful tools for nonlinear mapping and prediction, and they can capture complex relationships between input and output variables. In membrane fouling prediction, ANNs can be trained using historical data to predict the fouling rate or other fouling-related parameters based on the process parameters. This review addresses the pertinent literature about using ANNs for membrane fouling prediction. Specifically, complementing other existing reviews that focus on mathematical models or broad AI-based simulations, the present review focuses on the use of AI-based fouling prediction models, namely, artificial neural networks (ANNs) and their derivatives, to provide deeper insights into the strengths, weaknesses, potential, and areas of improvement associated with such models for membrane fouling prediction.

Removal of natural organic matter from surface water sources by nanofiltration and surface engineering membranes for fouling mitigation - A review

Given that surface water is the primary supply of drinking water worldwide, the presence of natural organic matter (NOM) in surface water presents difficulties for water treatment facilities. During the disinfection phase of the drinking water treatment process, NOM aids in the creation of toxic disinfection by-products (DBPs). This problem can be effectively solved using the nanofiltration (NF) membrane method, however NOM can significantly foul NF membranes, degrading separation performance and membrane integrity, necessitating the development of fouling-resistant membranes. This review offers a thorough analysis of the removal of NOM by NF along with insights into the operation, mechanisms, fouling, and its controlling variables. In light of engineering materials with distinctive features, the potential of surface-engineered NF membranes is here critically assessed for the impact on the membrane surface, separation, and antifouling qualities. Case studies on surface-engineered NF membranes are critically evaluated, and properties-to-performance connections are established, as well as challenges, trends, and predictions for the field's future. The effect of alteration on surface properties, interactions with solutes and foulants, and applications in water treatment are all examined in detail. Engineered NF membranes containing zwitterionic polymers have the greatest potential to improve membrane permeance, selectivity, stability, and antifouling performance. To support commercial applications, however, difficulties related to material production, modification techniques, and long-term stability must be solved promptly. Fouling resistant NF membrane development would be critical not only for the water treatment industry, but also for a wide range of developing applications in gas and liquid separations.

Application of Optical Coherence Tomography (OCT) to Analyze Membrane Fouling under Intermittent Operation

There is increasing interest in membrane systems powered by renewable energy sources, including solar and wind, that are suitable for decentralized water supply in islands and remote regions. These membrane systems are often operated intermittently with extended shutdown periods to minimize the capacity of the energy storage devices. However, relatively little information is available on the effect of intermittent operation on membrane fouling. In this work, the fouling of pressurized membranes under intermittent operation was investigated using an approach based on optical coherence tomography (OCT), which allows non-destructive and non-invasive examination of membrane fouling. In reverse osmosis (RO), intermittently operated membranes were investigated by OCT-based characterization. Several model foulants such as NaCl and humic acids were used, as well as real seawater. The cross-sectional OCT images of the fouling were visualized as a three-dimensional volume using Image J. The OCT images were used to quantitatively measure the thickness of foulants on the membrane surfaces under different operating conditions. The results showed that intermittent operation retarded the flux decrease due to fouling compared to continuous operation. The OCT analysis showed that the foulant thickness was significantly reduced by the intermittent operation. The decrease in foulant layer thickness was found to occur when the RO process was restarted in intermittent operation.

Prediction of forward osmosis membrane engineering factors using artificial intelligence approach

Currently, forward osmosis (FO) is widely studied for wastewater treatment and reuse. However, there are still challenges which need to be addressed for the application of the FO on a commercial scale. In the meantime, with a strong capability to solve the complicated nonlinear relationships and to examine of the relations between multiple variables, artificial intelligence (AI) technique could be a viable tool to improve FO system performance to make it more applicable. This study aims to develop an AI-based model for supporting early control and making decision in the FO membrane system. The results show that the artificial neural networks model is extremely suitable for prediction of water flux, membrane fouling, and removal efficiencies. The most appropriate input dataset for the model was proposed, in which organic matters, sodium ion, and calcium ion concentrations played a vital role in all predictions. The best model architecture was suggested with an optimal hidden layers (2-4 layers), and neurons (10-15 neurons). The developed models for membrane fouling show strong correlation between experimental and predicted data (with R² values for prediction of membrane fouling porosity, thickness, roughness, and density were 0.85, 0.97, 0.97, and 0.98, respectively). The prediction of water flux presented a high R² and low root mean square error (RMSE) of 0.92 and 0.9 L m^-2.h^-1, respectively. Prediction of the contaminant removal exhibits a relatively high correlation between the observed and predicted data with R² values of 0.87 and RMSE values of below 2.7%. The developed models are expected to create a breakthrough in the control and enhancement in a novel FO membrane process used for wastewater treatment by providing us with actionable insights to produce fit-for-future systems in the context of sustainable development.

Assessment of fouling mechanisms on reverse osmosis (RO) membrane during permeation of 17α-ethinylestradiol (EE2) solutions

Fouling mechanisms are mainly caused by the deposition of organic compounds that reduce the removal efficiency on reverse osmosis (RO) membranes. It can be described by mathematical models. The aim of this study was to evaluate the membrane fouling and rejection mechanisms when aqueous solutions containing 17α-ethinylestradiol (EE2) in different concentrations are permeated at 5 and 10 bar in a bench-scale dead-end RO system. Adsorption tests were performed and the fouling mechanism was assessed by Hermia's model for solutions of EE2 at concentrations typically found in the environment (µg L^-1). Fourier transform infrared spectroscopy (FTIR) has indicated the presence of EE2 on the fouled membrane surface. Membrane rejection of EE2 ranged from 90% to 98% and the main rejection mechanism was size exclusion at all experimental conditions. However, for the higher concentration of EE2 permeated at 5 and 10 bar, adsorption of 7 and 32 mg m^-2, respectively, also took place. The rejection was influenced by fouling and concentration polarisation. Fouled membranes present higher rejection of hydrophobic neutral compounds and the concentration polarisation reduces rejection. Hermia's model demonstrated that the permeation values fitted better the standard blocking filtration and cake filtration equations for describing fouling mechanism. This study showed that fouling also occurs in the TFC RO membrane after permeation of EE2, which corroborates with studies using other pollutants.

Artificial intelligence-incorporated membrane fouling prediction for membrane-based processes in the past 20 years: A critical review

Membrane fouling is one of major obstacles in the application of membrane technologies. Accurately predicting or simulating membrane fouling behaviours is of great significance to elucidate the fouling mechanisms and develop effective measures to control fouling. Although mechanistic/mathematical models have been widely used for predicting membrane fouling, they still suffer from low accuracy and poor sensitivity. To overcome the limitations of conventional mathematical models, artificial intelligence (AI)-based techniques have been proposed as powerful approaches to predict membrane filtration performance and fouling behaviour. This work aims to present a state-of-the-art review on the advances in AI algorithms (e.g., artificial neural networks, fuzzy logic, genetic programming, support vector machines and search algorithms) for prediction of membrane fouling. The working principles of different AI techniques and their applications for prediction of membrane fouling in different membrane-based processes are discussed in detail. Furthermore, comparisons of the inputs, outputs, and accuracy of different AI approaches for membrane fouling prediction have been conducted based on the literature database. Future research efforts are further highlighted for AI-based techniques aiming for a more accurate prediction of membrane fouling and the optimization of the operation in membrane-based processes.

Multiparameter Neural Network Modeling of Facilitated Transport Mixed Matrix Membranes for Carbon Dioxide Removal

Membranes for carbon capture have improved significantly with various promoters such as amines and fillers that enhance their overall permeance and selectivity toward a certain particular gas. They require nominal energy input and can achieve bulk separations with lower capital investment. The results of an experiment-based membrane study can be suitably extended for techno-economic analysis and simulation studies, if its process parameters are interconnected to various membrane performance indicators such as permeance for different gases and their selectivity. The conventional modelling approaches for membranes cannot interconnect desired values into a single model. Therefore, such models can be suitably applicable to a particular parameter but would fail for another process parameter. With the help of artificial neural networks, the current study connects the concentrations of various membrane materials (polymer, amine, and filler) and the partial pressures of carbon dioxide and methane to simultaneously correlate three desired outputs in a single model: CO₂ permeance, CH₄ permeance, and CO₂/CH₄ selectivity. These parameters help predict membrane performance and guide secondary parameters such as membrane life, efficiency, and product purity. The model results agree with the experimental values for a selected membrane, with an average absolute relative error of 6.1%, 4.2%, and 3.2% for CO₂ permeance, CH₄ permeance, and CO₂/CH₄ selectivity, respectively. The results indicate that the model can predict values at other membrane development conditions.

Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks

Effluent originating from cheese production puts pressure onto environment due to its high organic load. Therefore, the main objective of this work was to compare the influence of different process variables (transmembrane pressure (TMP), Reynolds number and feed pH) on whey protein recovery from synthetic and industrial cheese whey using polyethersulfone (PES 30 kDa) membrane in dead-end and cross-flow modes. Analysis on the fouling mechanistic model indicates that cake layer formation is dominant as compared to other pore blocking phenomena evaluated. Among the input variables, pH of whey protein solution has the biggest influence towards membrane flux and protein rejection performances. At pH 4, electrostatic attraction experienced by whey protein molecules prompted a decline in flux. Cross-flow filtration system exhibited a whey rejection value of 0.97 with an average flux of 69.40 L/m²h and at an experimental condition of 250 kPa and 8 for TMP and pH, respectively. The dynamic behavior of whey effluent flux was modeled using machine learning (ML) tool convolutional neural networks (CNN) and recursive one-step prediction scheme was utilized. Linear and non-linear correlation indicated that CNN model (R² - 0.99) correlated well with the dynamic flux experimental data. PES 30 kDa membrane displayed a total protein rejection coefficient of 0.96 with 55% of water recovery for the industrial cheese whey effluent. Overall, these filtration studies revealed that this dynamic whey flux data studies using the CNN modeling also has a wider scope as it can be applied in sensor tuning to monitor flux online by means of enhancing whey recovery 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.

Real-time monitoring of forward osmosis membrane fouling in wastewater reuse process performed with a deep learning model

Monitoring fouling behavior for better understanding and control has recently gained increasing attention. However, there is no practical method for observing membrane fouling in real time, especially in the forward osmosis (FO) process. In this article, we used the optical coherence tomography (OCT) technique to conduct real-time monitoring of the membrane fouling layer in the FO process. Fouling tendency of the FO membrane was observed at four distinguished stages for 21 days using a regular membrane cleaning method. In this method, chemical cleaning, which extracts two to three times as much organic matter (OM) as physical cleaning, was used as an effective method. Real-time OCT image observations indicated that a thin, dense, and flat fouling layer was formed (initial stage). On the other hand, a fouling layer with a thick and rough surface was formed later (final stage). A deep learning convolutional neural network model was developed to predict membrane fouling characteristics based on a dataset of real-time fouling images. The model results show a very high correlation between the predicted data and the actual data. R² equals 0.90, 0.86, 0.92, and 0.90 for the thickness, porosity, roughness, and density of the fouling layer, respectively. As a promising approach, real-time monitoring of fouling layers on the surface of FO membranes and the prediction of fouling layer characteristics using deep learning models can characterize and control membrane fouling in FO and other membrane processes.

Deep learning model for simulating influence of natural organic matter in nanofiltration

Controlling membrane fouling in a membrane filtration system is critical to ensure high filtration performance. A forecast of membrane fouling could enable preliminary actions to relieve the development of membrane fouling. Therefore, we established a long short-term memory (LSTM) model to investigate the variations in filtration performance and fouling growth. For data acquisition, we first conducted lab-scale membrane fouling experiments to identify the diverse fouling mechanisms of natural organic matter (NOM) in nanofiltration (NF) systems. Four types of NOMs were considered as model foulants: humic acid, bovine-serum-albumin, sodium alginate, and tannic acid. In addition, real-time 2D images were acquired via optical coherence tomography (OCT) to quantify the cake layer formed on the membrane. Subsequently, experimental data were used to train the LSTM model to predict permeate flux and fouling layer thickness as output variables. The model performance exhibited root mean square errors of <1 L/m²/h for permeate flux and <10 µm for fouling layer thickness in both the training and validation steps. In this study, we demonstrated that deep learning can be used to simulate the influence of NOMs on the NF system and also be applied to simulate other membrane processes.

A Comprehensive Review on Membrane Fouling: Mathematical Modelling, Prediction, Diagnosis, and Mitigation

Membrane-based separation has gained increased popularity over the past few decades, particularly reverse osmosis (RO). A major impediment to the improved performance of membrane separation processes, in general, is membrane fouling. Fouling has detrimental effects on the membrane’s performance and integrity, as the deposition and accumulation of foulants on its surface and/or within its pores leads to a decline in the permeate flux, deterioration of selectivity, and permeability, as well as a significantly reduced lifespan. Several factors influence the fouling-propensity of a membrane, such as surface morphology, roughness, hydrophobicity, and material of fabrication. Generally, fouling can be categorized into particulate, organic, inorganic, and biofouling. Efficient prediction techniques and diagnostics are integral for strategizing control, management, and mitigation interventions to minimize the damage of fouling occurrences in the membranes. To improve the antifouling characteristics of RO membranes, surface enhancements by different chemical and physical means have been extensively sought after. Moreover, research efforts have been directed towards synthesizing membranes using novel materials that would improve their antifouling performance. This paper presents a review of the different membrane fouling types, fouling-inducing factors, predictive methods, diagnostic techniques, and mitigation strategies, with a special focus on RO membrane fouling.

Fully Convolutional Neural Network for Detection and Counting of Diatoms on Coatings after Short-Term Field Exposure

While the use of deep learning is a valuable technology for automatic detection systems for medical data and images, the biofouling community is still lacking an analytical tool for the detection and counting of diatoms on samples after short-term field exposure. In this work, a fully convolutional neural network was implemented as a fast and simple approach to detect diatoms on two-channel (fluorescence and phase-contrast) microscopy images by predicting bounding boxes. The developed approach performs well with only a small number of trainable parameters and a F1 score of 0.82. Counting diatoms was evaluated on a data set of 600 microscopy images of three different surface chemistries (hydrophilic and hydrophobic) and is very similar to counting by humans while demanding only a fraction of the analysis time.