Prediction of organic contaminant rejection by nanofiltration and reverse osmosis membranes using interpretable machine learning models

Utilizing machine learning to evaluate heavy metal pollution in the world's largest mangrove forest

The world's largest mangrove forest (Sundarbans) is facing an imminent threat from heavy metal pollution, posing grave ecological and human health risks. Developing an accurate predictive model for heavy metal content in this area has been challenging. In this study, we used machine learning techniques to model sediment pollution by heavy metals in this vital ecosystem. We collected 199 standardized sediment samples to predict the accumulation of eleven heavy metals using ten different machine learning algorithms. Among them, the extremely randomized tree model exhibited the best performance in predicting Fe (0.87), Cr (0.89), Zn (0.85), Ni (0.83), Cu (0.87), Co (0.62), As (0.68), and V (0.90), achieving notable R2 values. On the other hand, the random forest outperformed for predicting Cd (0.72) and Mn (0.91), whereas the decision tree model showed the best performance for Pb (0.73). The feature attribute analysis identified FeV, CrV, CuZn, CoMn, PbCd, and AsCd relationships resembled with correlation coefficients among them. Based on the established models, the prediction of the contamination factor of metals in sediments showed very high Cd contamination (CF ≥ 6). The Moran's I index for Cd, Cr, Pb, and As were 0.71, 0.81, 0.71, and 0.67, respectively, indicating strong positive spatial autocorrelation and suggesting clustering of similar contamination levels. Conclusively, this research provides a comprehensive framework for predicting heavy metal sediment pollution in the Sundarbans, identifying key areas needing urgent conservation. Our findings support the adoption of integrated management strategies and targeted remedial actions to mitigate the harmful effects of heavy metal contamination in this vital ecosystem.

Enhanced desalination with polyamide thin-film membranes using ensemble ML chemometric methods and SHAP analysis

Addressing global freshwater scarcity requires innovative technological solutions, among which desalination through thin-film composite polyamide membranes stands out. The performance of these membranes plays a vital role in desalination, necessitating advanced predictive modeling for optimization. This study harnesses machine learning (ML) algorithms, including support vector machine (SVM), neural networks (NN), linear regression (LR), and multivariate linear regression (MLR), alongside their ensemble techniques to predict and enhance average water flux (AWF) and average salt rejection (ASR) essential metrics of desalination efficiency. To ensure model interpretability and feature importance analysis, SHapley Additive exPlanations (SHAP) were employed, providing both global and local insights into feature contributions. Initially, the individual models were validated, with NN demonstrating superior performance for both AWF and ASR, achieving the lowest mean absolute error (MAE = 0.001) and root mean squared error (RMSE = 0.0111) for AWF and an MAE = 0.0107 and RMSE = 0.0982 for ASR. The accuracy of predictions improved significantly with ensemble models, as evidenced by the near-perfect Nash-Sutcliffe efficiency (NSE) values. Specifically, the NN ensemble (NN-E) and Linear Regression ensemble (LR-E) reached an MAE and RMSE of 0.001 and 0.0111, respectively, for AWF. For ASR, NN-E reduced the MAE to 0.0013 and the RMSE to 0.0089, while LR-E maintained competitive performance with an MAE of 0.0133 and an RMSE of 0.0936. SHAP analysis revealed that features such as MDP and TMC were critical drivers of performance, with MDP showing the most significant positive impact on ASR. These findings demonstrate the dominance of ensemble methods over individual algorithms in predicting key desalination parameters. The enhanced precision in estimating AWF and ASR offered by these neuro-intelligent ensembles, combined with the interpretability provided by SHAP analysis, can lead to significant environmental and operational improvements in membrane performance, optimizing resource usage and minimizing ecological impacts. This study paves the way for integrating intelligent ML ensembles and SHAP-based interpretability into the practical field of membrane technology, marking a step forward toward sustainable and efficient desalination processes.

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.

Machine learning models for predicting the rejection of organic pollutants by forward osmosis and reverse osmosis membranes and unveiling the rejection mechanisms

While forward osmosis (FO) and reverse osmosis (RO) processes have been proven effective in rejecting organic pollutants, the rejection rate is highly dependent on compound and membrane characteristics, as well as operating conditions. This study aims to establish machine learning (ML) models for predicting the rejection of organic pollutants by FO and RO and providing insights into the underlying rejection mechanisms. Among the 14 ML models established, the random forest model (R2 = 0.85) and extreme gradient boosting model (R2 = 0.92) emerged as the best-performing models for FO and RO, respectively. Shapley additive explanations (SHAP) analysis identified the length of the compound, water flux, and hydrophobicity as the top three variables contributing to the FO model. For RO, in addition to the length of the compound and operating pressure, advanced variables including four molecular descriptors (e.g., ATSC2m and Balaban J) and three fingerprints (e.g., C=C double bond and carbonyl group) significantly contributed to the prediction. Besides, the associations between these highly ranked variables and their SHAP values shed light on the rejection mechanisms, such as size exclusion, adsorption, hydrophobic interaction, and electrostatic interaction, and illustrate the role of the operating parameters, such as the FO permeate water flux and RO operating pressure, in the rejection process. These findings provide interpretable predictive models for the removal of organic pollutants and advance the mechanistic understanding of the rejection mechanisms in the FO and RO processes.

Continuous operation of nano-catalytic ozonation using membrane separation coupling system: Influence factors and mechanism

The application of nano-catalysts in improving the ozonation removal efficiency for refractory organic compounds has been extensively investigated. However, cost-effective nano-catalysts separation remains a challenge. In this study, membrane separation processes were employed to separate nano-MgO catalysts from an ozonation system. A continuous nano-catalytic ozonation membrane separation (nCOMS) coupling system was successfully constructed for treating quinoline. The results showed that long hydraulic retention time (HRT) and high nano-MgO dosage could improve the quinolone removal efficiency but shorten operation cycles. At the optimal operation conditions of HRT = 4 h and nano-MgO dosage = 0.2 g/L, the nCOMS system achieved a stable quinoline removal efficiency of 85.2% for 240 min running with a transmembrane pressure lower than 10 kPa. The quinoline removal efficiency contribution for ozonation, catalysis and membrane separation was 57.1%, 24.9% and 18.0%, respectively. Compared to ozonation membrane separation system, the fouling rate index of the nCOMS system increased by 60% under optimal conditions, but the irreversible fouling was reduced to 28%. In addition, the nCOMS system exhibited reduced adverse effects of coexisting natural organic matter (NOM) on quinoline removal and membrane fouling. In conclusion, the nCOMS system demonstrated higher quinoline removal efficiency, lower irreversible fouling, and reduced adverse effect of coexisting NOM, thereby signifying its potential for practical applications in advanced treatment of industrial wastewater.

Predicting micropollutant removal through nanopore-sized membranes using several machine-learning approaches based on feature engineering

Predicting the efficacy of micropollutant separation through functionalized membranes is an arduous endeavor. The challenge stems from the complex interactions between the physicochemical properties of the micropollutants and the basic principles underlying membrane filtration. This study aimed to compare the effectiveness of a modest dataset on various machine learning tools (ML) tools in predicting micropollutant removal efficiency for functionalized reverse osmosis (RO) and nanofiltration (NF) membranes. The inherent attributes of both the micropollutants and the membranes are utilized as input factors. The chosen ML tools are supervised algorithm (adaptive network-based fuzzy inference system (NF), linear regression framework (linear regression (LR)), stepwise linear regression (SLR) and multivariate linear regression (MVR)), and unsupervised algorithm (support vector machine (SVM) and ensemble boosted tree (BT)). The feature engineering and parametric dependency analysis revealed that characteristics of micropollutants, such as maximum projection diameter (MaxP), minimal projection diameter (MinP), molecular weight (MW), and compound size (CS), exhibited a notably positive impact on the correlation with removal efficiency. Model combination with key variables demonstrated high prediction accuracy in both supervised and unsupervised ML for micropollutant removal efficiency. An NF-grid partitioning (NF-GP) model achieved the highest accuracy with an R 2 value of 0.965, accompanied by low error metrics, specifically an RMSE and MAE of 3.65. It is owed to the handling of the complex spatial and temporal aspects of micropollutant data through division into consistent subsets facilitating improved identification of rejection efficiency and relationships. The inclusion of inputs with both negative and positive correlations introduces variability, amplifies the system responsiveness, and impedes the precision of predictive models. This study identified key micropollutant properties, including MaxP, MinP, MW, and CS, as crucial factors for efficient micropollutant rejection during real-time filtration applications. It also allowed the design of pore size of self-prepared membranes for the enhanced separation of micropollutants from wastewater.

Design and Machine Learning Prediction of In Situ Grown PDA-Stabilized MOF (UiO-66-NH2) Membrane for Low-Pressure Separation of Emulsified Oily Wastewater

Significant progress has been made in designing advanced membranes; however, persistent challenges remain due to their reduced permeation rates and a propensity for substantial fouling. These factors continue to pose significant barriers to the effective utilization of membranes in the separation of oil-in-water emulsions. Metal-organic frameworks (MOFs) are considered promising materials for such applications; however, they encounter three key challenges when applied to the separation of oil from water: (a) lack of water stability; (b) difficulty in producing defect-free membranes; and (c) unresolved issue of stabilizing the MOF separating layer on the ceramic membrane (CM) support. In this study, a defect-free hydrolytically stable zirconium-based MOF separating layer was formed through a two-step method: first, by in situ growth of UiO-66-NH2 MOF into the voids of polydopamine (PDA)-functionalized CM during the solvothermal process, and then by facilitating the self-assembly of UiO-66-NH2 with PDA using a pressurized dead-end assembly. A stable MOF separating layer was attained by enriching the ceramic support with amines and hydroxyl groups using PDA, which assisted in the assembly and stabilization of UiO-66-NH2. The PDA-s-UiO-66-NH2-CM membrane displayed air superhydrophilicity and underwater superoleophobicity, demonstrating its oil resistance and high antifouling behavior. The PDA-s-UiO-66-NH2-CM membrane has shown exceptionally high permeability and separation capacity for challenging oil-in-water emulsions. This is attributed to numerous nanochannels from the membrane and its high resistance to oil adhesion. The membranes showed excellent stability over 15 continuous test cycles, which indicates that the developed MOFs separating layers have a low tendency to be clogged by oil droplets during separation. Machine learning-based Gaussian process regression (GPR) models as nonparametric kernel-based probabilistic models were employed to predict the performance efficiency of the PDA-s-UiO-66-NH2-CM membrane in oil-in-water separation. The outcomes were compared with the support vector machine (SVM) and decision tree (DT) algorithm. This efficiency includes various metrics related to its separation accuracy, and the models were developed through feature engineering to identify and utilize the most significant factors affecting the membrane's performance. The results proved the reliability of GPR optimization with the highest prediction accuracy in the validation phase. The average percentage increase of the GPR model compared to the SVM and DT model was 6.11 and 42.94%, respectively.

Understanding Rejection Mechanisms of Trace Organic Contaminants by Polyamide Membranes via Data-Knowledge Codriven Machine Learning

Data-driven machine learning (ML) provides a promising approach to understanding and predicting the rejection of trace organic contaminants (TrOCs) by polyamide (PA). However, various confounding variables, coupled with data scarcity, restrict the direct application of data-driven ML. In this study, we developed a data-knowledge codriven ML model via domain-knowledge embedding and explored its application in comprehending TrOC rejection by PA membranes. Domain-knowledge embedding enhanced both the predictive performance and the interpretability of the ML model. The contribution of key mechanisms, including size exclusion, charge effect, hydrophobic interaction, etc., that dominate the rejections of the three TrOC categories (neutral hydrophilic, neutral hydrophobic, and charged TrOCs) was quantified. Log D and molecular charge emerge as key factors contributing to the discernible variations in the rejection among the three TrOC categories. Furthermore, we quantitatively compared the TrOC rejection mechanisms between nanofiltration (NF) and reverse osmosis (RO) PA membranes. The charge effect and hydrophobic interactions possessed higher weights for NF to reject TrOCs, while the size exclusion in RO played a more important role. This study demonstrated the effectiveness of the data-knowledge codriven ML method in understanding TrOC rejection by PA membranes, providing a methodology to formulate a strategy for targeted TrOC removal.

Micropollutant rejection by nanofiltration membranes: A mini review dedicated to the critical factors and modelling prediction

Nanofiltration (NF) membranes, extensively used in advanced wastewater treatment, have broad application prospects for the removal of emerging trace organic micropollutants (MPs). The treatment performance is affected by several factors, such as the properties of NF membranes, characteristics of target MPs, and operating conditions of the NF system concerning MP rejection. However, quantitative studies on different contributors in this context are limited. To fill the knowledge gap, this study aims to assess critical impact factors controlling MP rejection and develop a feasible model for MP removal prediction. The mini-review firstly summarized membrane pore size, membrane zeta potential, and the normalized molecular size (λ = rs/rp), showeing better individual relationships with MP rejection by NF membranes. The Lindeman-Merenda-Gold model was used to quantitatively assess the relative importance of all summarized impact factors. The results showed that membrane pore size and operating pressure were the high impact factors with the highest relative contribution rates to MP rejection of 32.11% and 25.57%, respectively. Moderate impact factors included membrane zeta potential, solution pH, and molecular radius with relative contribution rates of 10.15%, 8.17%, and 7.83%, respectively. The remaining low impact factors, including MP charge, molecular weight, logKow, pKa and crossflow rate, comprised all the remaining contribution rates of 16.19% through the model calculation. Furthermore, based on the results and data availabilities from references, the machine learning-based random forest regression model was trained with a relatively low root mean squared error and mean absolute error of 12.22% and 6.92%, respectively. The developed model was then successfully applied to predict MPs' rejections by NF membranes. These findings provide valuable insights that can be applied in the future to optimize NF membrane designs, operation, and prediction in terms of removing micropollutants.

Pressure-driven membrane filtration technology for terminal control of organic DBPs: A review

Disinfection by-products (DBPs), a series of undesired secondary contaminants formed during the disinfection processes, deteriorate water quality, threaten human health and endanger ecological safety. Membrane-filtration technologies are commonly used in the advanced water treatment and have shown a promising performance for removing trace contaminants. In order to gain a clearer understanding of the behavior of DBPs in membrane-filtration processes, this work dedicated to: (1) comprehensively reviewed the retention efficiency of microfiltration (MF), ultrafiltration (UF), nanofiltration (NF) and reverse osmosis (RO) for DBPs. (2) summarized the mechanisms involved size exclusion, electrostatic repulsion and adsorption in the membrane retention of DBPs. (3) In conjunction with principal component analysis, discussed the influence of various factors (such as the characteristics of membrane and DBPs, feed solution composition and operating conditions) on the removal efficiency. In general, the characteristics of the membranes (salt rejection, molecular weight cut-off, zeta potential, etc.) and DBPs (molecular size, electrical property, hydrophobicity, polarity, etc.) fundamentally determine the membrane-filtration performance on retaining DBPs, and the actual operating environmental factors (such as solute concentration, coexisting ions/NOMs, pH and transmembrane pressure) exert a positive/negative impact on performance to some extent. Current researches indicate that NF and RO can be effective in removing DBPs, and looking forward, we recommend that multiple factors should be taken into account that optimize the existed membrane-filtration technologies, rationalize the selection of membrane products, and develop novel membrane materials targeting the removal of DBPs.

Contribution of molecular structures and quantum chemistry technique to root concentration factor: An innovative application of interpretable machine learning

Root concentration factor (RCF) is a significant parameter to characterize uptake and accumulation of hazardous organic contaminants (HOCs) by plant roots. However, complex interactions among chemicals, plant roots and soil make it challenging to identify underlying mechanisms of uptake and accumulation of HOCs. Here, nine machine learning techniques were applied to investigate major factors controlling RCF based on variable combinations of molecular descriptors (MD), MACCS fingerprints, quantum chemistry descriptors (QCD) and three physicochemical properties related to chemical-soil-plant system. Compared to models with variables including MACCS fingerprints or solitary physicochemical properties, the XGBoost-6 model developed by the variable combination of MD, QCD and three physicochemical properties achieved the most remarkable performance, with R2 of 0.977. Model interpretation achieved by permutation variable importance and partial dependence plots revealed the vital importance of HOCs lipophilicity, lipid content of plant roots, soil organic matter content, the overall deformability and the molecular dispersive ability of HOCs for regulating RCF. The integration of MD and QCD with physicochemical properties could improve our knowledge of underlying mechanisms regarding HOCs accumulation in plant roots from innovative structural perspectives. Multiple variables combination-oriented performance improvement of model can be extended to other parameters prediction in environmental risk assessment field.

A new S-scheme heterojunction of 1D ZnGa2O4/ZnO nanofiber for efficient photocatalytic degradation of TC-HCl

One-dimensional shaped ZnGa₂O₄, ZnO and ZnGa₂O₄/ZnO nanofibers were successfully prepared by electrostatic spinning technique and the photocatalytic degradation performance of tetracycline hydrochloride (TC-HCl) were studied. It was found that the S-scheme heterojunction formed in the ZnGa₂O₄/ZnO could greatly reduce the recombination of the photogenerated carriers and therefore improve the photocatalytic performance. By optimizing the ratio of the ZnGa₂O₄ and ZnO, the largest degradation rate could reach 0.0573 min^-1, which was 20 times of the self-degradation rate of TC-HCl. It was verified that the h⁺ played the key role in the reactive groups for the high performance decomposition of TC-HCl by capture experiments. This work provides a new method for the highly efficient photocatalytic degradation of TC-HCl.

Experiments and machine learning-based modeling for haloacetic acids rejection by nanofiltration: Influence of solute properties and operating conditions

Because of potential risks to public health, the presence of haloacetic acids (HAAs) in drinking water is a major concern. Nanofiltration (NF) has shown potential for HAAs rejection, and several factors, namely, membrane properties, solute properties, and operating conditions, have been revealed key roles. However, knowledge of NF separation mechanism by quantifying these factors is limited. This study investigated and modeled NF performance on HAAs rejection. NF performance was experimentally investigated under various transmembrane pressure (TMP), cross-flow velocity (CV), temperature, pH, ionic strength (IS), and HAAs initial feed concentration (C_in). We used machine learning (ML) to understand the mechanism from the perspective of HAAs properties and operating conditions. Multiple linear regression (MLR), support vector machine (SVM), multsilayer perceptron (MLP), extreme gradient boosting (XGBoost), and random forest (RF) models were used. The MLP, XGBoost and RF models achieved significant performance with high R² (0.970, 0.973, and 0.980) and low RMSE (4.71, 4.41, and 3.84). These three models were analyzed using the Shapley Additive explanation (SHAP) to quantify relative contributions of HAAs properties and operating conditions. XGBoost-SHAP produced the most logical results and was the best-performing model for selecting optimal input variables combinations. The results showed that Stokes radius (r_s), logarithmic octanol-water partitioning coefficient (logK_ow), molecular weight (MW), pH, TMP, and temperature are key variables for interpreting NF process. The effects of HAAs properties were ranked as r_s > logK_ow > MW, suggesting significance of size exclusion and hydrophobic interaction. The impact of the operational conditions followed the order pH > TMP > temperature, illustrating that pH was the major influencing operating condition. This study demonstrated significant capacity of ML, which reduced amount of experimental work. In addition, the main operating conditions can be evaluated in terms of their contributions, making ML an efficient tool for risk management and process optimization.