Multivariate data-based optimization of membrane adsorption process for wastewater treatment: Multi-layer perceptron adaptive neural network versus adaptive neural fuzzy inference system

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.

A Novel Modeling Optimization Approach for a Seven-Channel Titania Ceramic Membrane in an Oily Wastewater Filtration System Based on Experimentation, Full Factorial Design, and Machine Learning

This comprehensive study looks at how operational conditions affect the performance of a novel seven-channel titania ceramic ultrafiltration membrane for the treatment of produced water. A full factorial design experiment (23) was conducted to study the effect of the cross-flow operating factors on the membrane permeate flux decline and the overall permeate volume. Eleven experimental runs were performed for three important process operating variables: transmembrane pressure (TMP), crossflow velocity (CFV), and filtration time (FT). Steady final membrane fluxes and permeate volumes were recorded for each experimental run. Under the optimized conditions (1.5 bar, 1 m/s, and 2 h), the membrane performance index demonstrated an oil rejection rate of 99%, a flux of 297 L/m2·h (LMH), a 38% overall initial flux decline, and a total permeate volume of 8.14 L. The regression models used for the steady-state membrane permeate flux decline and overall permeate volume led to the highest goodness of fit to the experimental data with a correlation coefficient of 0.999. A Multiple Linear Regression method and an Artificial Neural Network approach were also employed to model the experimental membrane permeate flux decline and analyze the impact of the operating conditions on membrane performance. The predictions of the Gaussian regression and the Levenberg-Marquardt backpropagation method were validated with a determination coefficient of 99% and a Mean Square Error of 0.07.

Application and innovation of artificial intelligence models in wastewater treatment

At present, as the problem of water shortage and pollution is growing serious, it is particularly important to understand the recycling and treatment of wastewater. Artificial intelligence (AI) technology is characterized by reliable mapping of nonlinear behaviors between input and output of experimental data, and thus single/integrated AI model algorithms for predicting different pollutants or water quality parameters have become a popular method for simulating the process of wastewater treatment. Many AI models have successfully predicted the removal effects of pollutants in different wastewater treatment processes. Therefore, this paper reviews the applications of artificial intelligence technologies such as artificial neural networks (ANN), adaptive network-based fuzzy inference system (ANFIS) and support vector machine (SVM). Meanwhile, this review mainly introduces the effectiveness and limitations of artificial intelligence technology in predicting different pollutants (dyes, heavy metal ions, antibiotics, etc.) and different water quality parameters such as biochemical oxygen demand (BOD), chemical oxygen demand (COD), total nitrogen (TN) and total phosphorus (TP) in wastewater treatment process, involving single AI model and integrated AI model. Finally, the problems that need further research together with challenges ahead in the application of artificial intelligence models in the field of environment are discussed and presented.

Prediction of adsorption performance of ZIF-67 for malachite green based on artificial neural network using L-BFGS algorithm

Given the necessity and urgency in removing organic pollutants such as malachite green (MG) from the environment, it is vital to screen high-capacity adsorbents using artificial neural network (ANN) methods quickly and accurately. In this study, a series of ZIF-67 were synthesized, which adsorption properties for organic pollutants, especially MG, were systematically evaluated and determined as 241.720 mg g-1 (25 ℃, 2 h). The adsorption process was more consistent with pseudo-second-order kinetics and Langmuir adsorption isotherm, which correlation coefficients were 0.995 and 0.997, respectively. The chemisorption mechanism was considered to be π-π stacking interaction between imidazole and aromatic ring. Then, a Python-based neural network model using the Limited-memory BFGS algorithm was constructed by collecting the crucial structural parameters of ZIF-67 and the experimental data of batch adsorption. The model, optimized extensively, outperformed similar Matlab-based ANN with a coefficient of determination of 0.9882 and mean square error of 0.0009 in predicting ZIF-67 adsorption of MG. Furthermore, the model demonstrated a good generalization ability in the predictive training of other organic pollutants. In brief, ANN was successfully separated from the Matlab platform, providing a robust framework for high-precision prediction of organic pollutants and guiding the synthesis of adsorbents.

Integrated AI-driven optimization of Fenton process for the treatment of antibiotic sulfamethoxazole: Insights into mechanistic approach

Antibiotics, as a class of environmental pollutants, pose a significant challenge due to their persistent nature and resistance to easy degradation. This study delves into modeling and optimizing conventional Fenton degradation of antibiotic sulfamethoxazole (SMX) and total organic carbon (TOC) under varying levels of H2O2, Fe2+ concentration, pH, and temperature using statistical and artificial intelligence techniques including Multiple Regression Analysis (MRA), Support Vector Regression (SVR) and Artificial Neural Network (ANN). In statistical metrics, the ANN model demonstrated superior predictive accuracy compared to its counterparts, with lowest RMSE values of 0.986 and 1.173 for SMX and TOC removal, respectively. Sensitivity showcased H2O2/Fe2+ ratio, time and pH as pivotal for SMX degradation, while in simultaneous SMX and TOC reduction, fine tuning the time, pH, and temperature was essential. Leveraging a Hybrid Genetic Algorithm-Desirability Optimization approach, the trained ANN model revealed an optimal desirability of 0.941 out of 1000 solutions which yielded a 91.18% SMX degradation and 87.90% TOC removal under following specific conditions: treatment time of 48.5 min, Fe2+: 7.05 mg L-1, H2O2: 128.82 mg L-1, pH: 5.1, initial SMX: 97.6 mg L-1, and a temperature: 29.8 °C. LC/MS analysis reveals multiple intermediates with higher m/z (242, 270 and 288) and lower m/z (98, 108, 156 and 173) values identified, however no aliphatic hydrocarbon was isolated, because of the low mineralization performance of Fenton process. Furthermore, some inorganic fragments like NH4+ and NO3- were also determined in solution. This comprehensive research enriches AI modeling for intricate Fenton-based contaminant degradation, advancing sustainable antibiotic removal strategies.

Multiple design and modelling approaches for the optimisation of carbon felt electro-Fenton treatment of dye laden wastewater

This study utilizes artificial intelligence and statistical modelling to optimize the operating parameters of a carbon-based electro-Fenton process for purifying model dye (RB19)-contaminated wastewater. Multilevel experimental Box-Behnken and uniform deisgns (BBD, UD) with four variables were analysed using polynomial regression analysis (PRA) and artificial neural networks (ANN), while the process optimisation was done using desirability function. For the given testing range but different design matrices and runs, both designs predicted a maximum RB19 removal (RB19-RR) of 90 ± 2.1% at lowest energy consumption (EC) of 0.44 ± 2.5 Wh, when voltage, Na2SO4, FeSO4, and time were maintained as follows: 4-5.3 V, 7-11 mM, 0.4-0.6 mM, and 35-40 min, respectively. All the design-model combinations portrayed the similar senitivity analyses, revealing that RB19 degradation and EC are primarily influenced by electrolysis time and voltage. The performance assessment demonstrated that all the design-model combinations also excellently predicted for unseen conditions as the maximum root mean squared error (RMSE) value for RB19-RR was 4.07, while it was 0.072 for EC, however, BBD-ANN performance proved to be slightly better than others. Having ∼57% less experimentation, UD based models managed to accurately predict the results for unseen conditions as the statistical errors were quite insignificant, even in some cases, RMSE found to be less for UD compared to BBD, elucidating the potential of uniform design as an alternative of conventional factorial designs. Nevertheless, the prediction accuracy is also dependent on modelling approach, as in some cases ANN failed to predict the response precisely specially when dealing with small data. Furthermore, techno-economic evaluation results spell out the efficacy of carbon felt based enhanced electro-Fenton process as promising environmental remediation technology and highlight its practical implication from view of operational cost.

Construction of chitosan-based supramolecular biofilm material for wound dressing based on natural deep eutectic solvents

Bacterial infection is still one of the main problems observed in the clinical process of wound healing, so the development of new multifunctional biocompatible materials is an urgent clinical need. A kind of supramolecular biofilm crosslinked by hydrogen bond between natural deep eutectic solvent and chitosan was studied and successfully prepared to reduce bacterial infection. Its killing rates of Staphylococcus aureus and Escherichia coli can reach 98.86 % ± 1.90 % and 99.69 % ± 0.53 %, and it can be degraded in both soil and water, showing excellent biocompatibility and biodegradability. In addition, the supramolecular biofilm material also has the UV barrier property, which can effectively avoid the secondary injury of UV to the wound. Interestingly, the cross-linking effect of hydrogen bond makes the biofilm have a more compact structure and rough surface, and gives the biofilm strong tensile properties. Overall, owing to these unique advantages, NADES-CS supramolecular biofilm has great potential for medical applications, laying the foundation for the realization of sustainable polysaccharide materials.

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.

Modeling, optimization and understanding of adsorption process for pollutant removal via machine learning: Recent progress and future perspectives

It is crucial to reduce the concentration of pollutants in water environment to below safe levels. Some cost-effective pollutant removal technologies have been developed, among which adsorption technology is considered as a promising solution. However, the batch experiments and adsorption isotherms widely employed at present are inefficient and time-consuming to some extent, which limits the development of adsorption technology. As a new research paradigm, machine learning (ML) is expected to innovate traditional adsorption models. This reviews summarized the general workflow of ML and commonly employed ML algorithms for pollutant adsorption. Then, the latest progress of ML for pollutant adsorption was reviewed from the perspective of all-round regulation of adsorption process, including adsorption efficiency, operating conditions and adsorption mechanism. General guidelines of ML for pollutant adsorption were presented. Finally, the existing problems and future perspectives of ML for pollutant adsorption were put forward. We highly expect that this review will promote the application of ML in pollutant adsorption and improve the interpretability of ML.

Microwave-assisted Synthesis, Characterization, Photocatalytic Degradation of Antibiotics, and Fluorometric Selective Sensing Activity of g-C3N4 Supported CuO Composites

Herein, we have designed for the fabrication of a series of g-C₃N₄/CuO composite by using one-step microwave-assisted synthesis for the degradation of antibiotics and detection of nano-molar range of toxic heavy metal ions. The synthesized g-C₃N₄/CuO composites were analyzed and characterized to know the structure, phase, surface area, absorption region, bandgap, and size of the composites. From the observation of TEM and XRD measurements, g-C₃N₄/CuO composites have hexagonal shape with average diameter of the particles is 25 ± 5 nm. The observed band gap values from UV-vis DRS for g-C₃N₄ nanosheets and CuO NPs are 2.64 eV and 1.72 eV. The synthesized g-C₃N₄/CuO composite has prodigious specific surface area (32.47 m²/g), which is the evident for superior heterogeneous catalytic applications. Therefore, the synthesized g-C₃N₄/CuO composites were tested for the degradation of antibiotics such as tetracycline (TC) and ciprofloxacin (CIP) under UV light illumination, it shows 88.02% and 90.01% degradation was observed within 1 h due to the matching optical band gap and internal charge transfer of excitons with in the heterojunction surface among g-C₃N₄ and CuO in the composite than the individual components (g-C₃N₄ and CuO) due to the high surface area and tiny particles of CuO were randomly deposited on the surface of g-C₃N₄ nanosheets. The catalytic reduction reaction follows as pseudo-first order equation and reused for 5 consecutive cycles without remarkable loss of catalytic activity. Moreover, the synthesized CuO NPs and g-C₃N₄/CuO composites were used as a prominent fluorescence sensing probe for the selective detection of Pb²⁺ in nano-molar range of concentration with K_sv is 1.38 × 10⁴ mol^- 1dm³. It was observed as a linear relationship based on the change in intensity, the limit of detection was determined to be 0.184 nM.

Smart instrumental Odour Monitoring Station for the efficient odour emission management and control in wastewater treatment plants

Odour emission assessment in wastewater treatment plants (WWTP) is a key aspect that needs to be improved in the plant management to avoid complaints and guarantee a sustainable environment. The research presents a smart instrumental odour monitoring station (SiOMS) composed of an advanced instrumental odour monitoring system (IOMS) integrated with other measurement units, for the continuous characterization and measurement of the odour emissions, with the aim of managing the potential odour annoyance causes in real time, in order to avoid negative effects. The application and on-site validation procedure of the trained IOMS is discussed. Experimental studies have been conducted at a large-scale WWTP. Fingerprint analysis has been applied to analyze and identify the principal gaseous compounds responsible for the odour annoyance. The artificial neural network has been adopted to elaborate and dynamically update the odour monitoring classification and quantification models (OMMs) of the IOMS. The results highlight the usefulness of a real-time measurement and control system to provide continuous and different information to the plant operators, thus allowing the identification of the odour sources and the most appropriate mitigation actions to be implemented. The paper provides important information for WWTP operators, as well as for the regulating bodies, authorities, manufacturers and end-users of odour monitoring systems involved in environmental odour impact management.

Multi-object optimization of Navy-blue anodic oxidation via response surface models assisted with statistical and machine learning techniques

This study aims to model, analyze, and compare the electrochemical removal of Navy-blue dye (NB, %) and subsequent energy consumption (EC, Wh) using the integrated response surface modelling and optimization approaches. The Box-Behnken experimental design was exercised using current density, electrolyte concentration, pH and oxidation time as inputs, while NB removal and EC were recorded as responses for the implementation and analysis of multiple linear regression, support vector regression and artificial neural network models. The dual-response optimization using genetic algorithm generated multi-Pareto solutions for maximized NB removal at minimum energy cost, which were further ranked by employing the desirability function approach. The optimal parametric solution having total desirability of 0.804 is found when pH, current density, Na₂SO₄ concentration and electrolysis time were 6.4, 11.89 mA cm^-2, 0.055 M and 21.5 min, respectively. At these conditions, NB degradation and EC were 83.23% and 3.64 Wh, respectively. Sensitivity analyses revealed the influential patterns of variables on simultaneous optimization of NB removal and EC to be current density followed by treatment time and finally supporting electrolyte concentration. Statistical metrics of modeling and validation confirmed the accuracy of artificial neural network model followed by support vector regression and multiple linear regression anlaysis. The results revealed that statistical and computational modeling is an effective approach for the optimization of process variables of an electrochemical degradation process.

Chitin and derivative chitosan-based structures - Preparation strategies aided by deep eutectic solvents: A review

The high molecular weight of chitin, as a biopolymer, challenges its extraction due to its insolubility in the solvents. Also, chitosan, as the N-deacetylated form of chitin, can be employed as a primary material for different industries. The low mechanical stability and poor plasticity of chitosan films, as a result of incompatible interaction between chitosan and the used solvent, have limited its industrialization. Deep eutectic solvents (DESs), as novel solvents, can solve the extraction difficulties of chitin, and the low mechanical stability and weak plasticity of chitosan films. Also, DESs can be considered for the different chitosan and chitin productions, including chitin nanocrystal and nanofiber, N,N,N-trimethyl-chitosan, chitosan-based imprinted structures, and DES-chitosan-based beads and monoliths. This review aims to focus on the preparation and characterization (chemistry and morphology) of DES-chitin-based and DES-chitosan-based structures to understand the influence of the incorporation of DESs into the chitin and chitosan structure.

Prediction of HER2 expression in breast cancer by combining PET/CT radiomic analysis and machine learning

BACKGROUND

Human epidermal growth factor receptor 2 (HER2) expression status determination significantly contributes to HER2-targeted therapy in breast cancer (BC). The purpose of this study was to evaluate the role of radiomics and machine learning based on PET/CT images in HER2 status prediction, and to identify the most effective combination of machine learning model and radiomic features.

METHODS

A total of 217 BC patients who underwent PET/CT examination were involved in the study and randomly divided into a training set (n = 151) and a testing set (n = 66). For all four models, the model parameters were determined using a threefold cross-validation in the training set. Each model's performance was evaluated on the independent testing set using the receiver operating characteristic (ROC) curve, and AUC was calculated to get a quantified performance measurement of each model.

RESULTS

Among the four developed machine learning models, the XGBoost model outperformed other machine learning models in HER2 status prediction. Furthermore, compared to the XGBoost model based on PET alone or CT alone radiomic features, the predictive power for HER2 status by using XGBoost model based on PET/CTmean or PET/CTconcat radiomic fusion features was dramatically improved with an AUC of 0.76 (95% confidence interval [CI] 0.69-0.83) and 0.72 (0.65-0.80), respectively.

CONCLUSIONS

The established machine learning classifier based on PET/CT radiomic features is potentially predictive of HER2 status in BC.