Predicting membrane fouling in a high solid AnMBR treating OFMSW leachate through a genetic algorithm and the optimization of a BP neural network model

Machine learning algorithms for predicting membrane bioreactors performance: A review

Membrane bioreactors (MBR) are recognized as a sustainable technology for treating polluted effluents. Machine learning (ML) algorithms have emerged as a modeling option to predict pollutant removal and operational variables such as membrane fouling, permeability, and energy consumption, which are significant challenges for MBR application. This review examines the use of ML algorithms in MBR-based wastewater treatment, focusing on the prediction of nitrogen and organic matter removal, and operational parameters related to membrane fouling. It presents the structures and fit quality of each model, noting that artificial neural networks (ANNs) are the most commonly used algorithm, appearing in 88 % of the 57 analyzed articles. Additionally, the review identified studies using random forests, support vector machines, k-nearest neighbors and boosting techniques, among other ML algorithms, although these were less frequently encountered. The review suggests potential in exploring less-utilized models for MBR data and identifies a gap in predicting membrane lifespan and replacement with ML models. This study aims to guide the development of new models for optimizing MBR performance by highlighting effective variables and algorithms, enhancing process control, real-time data analysis, parameter adjustment, and operational efficiency.

Application of artificial intelligence tools in wastewater and waste gas treatment systems: Recent advances and prospects

The non-linear complex relationships among the process variables in wastewater and waste gas treatment systems possess a significant challenge for real-time systems modelling. Data driven artificial intelligence (AI) tools are increasingly being adopted to predict the process performance, cost-effective process monitoring, and the control of different waste treatment systems, including those involving resource recovery. This review presents an in-depth analysis of the applications of emerging AI tools in physico-chemical and biological processes for the treatment of air pollutants, water and wastewater, and resource recovery processes. Additionally, the successful implementation of AI-controlled wastewater and waste gas treatment systems, along with real-time monitoring at the industrial scale are discussed.

Predicting thermodynamic adhesion energies of membrane fouling in planktonic anammox MBR via backpropagation neural network model

Predicting thermodynamic adhesion energies was a critical strategy for mitigating membrane fouling. This study utilized a backpropagation (BP) neural network model to predict the thermodynamic adhesion energies associated with membrane fouling in a planktonic anammox MBR. Acid-base (ΔGAB), electrostatic double layer (ΔGEL), and Lifshitz-van der Waals (ΔGLW) energies were selected as output variables, the training dataset was collected by the advanced Derjaguin-Landau-Verwey-Overbeek (XDLVO) method. Optimization results identified "7-10-3″ as the optimal network structure for the BP model. The prediction results demonstrated a high degree of fit between the predicted and experimental values of thermodynamic adhesion energy (R2 ≥ 0.9278), indicating a robust predictive capability of the model in this study. Overall, the study presented a practical BP neural network model for predicting thermodynamic adhesion energies, significantly enhancing the prediction tool for adhesive fouling behavior in anammox MBRs.

Prediction of municipal solid waste generation and analysis of dominant variables in rapidly developing cities based on machine learning - a case study of China

Prediction of municipal solid waste (MSW) generation plays an essential role in effective waste management. The main objectives of this study were to develop models for accurate prediction of MSW generation (MSWG) and analyze the influence of dominant variables on MSWG. To elevate the model's prediction accuracy, more than 50 municipal variables were considered original variables, which were selected from 12 categories. According to the screening results, the dominant variables are classified into four categories: urban greening, population size and residential density, regional economic development and resident income and expenditure. Among the seven machine learning methods, back propagation (BP) neural network has the best model evaluation effect. The R2 of the BP neural network model of Jiangsu, Zhejiang and Shandong provinces were 0.969, 0.941 and 0.971 respectively. The prediction accuracy of Shandong province (93.8%) was the best, followed by Jiangsu province (92.3%) and Zhejiang province (72.7%). The correlation between dominant variables and the MSWG was mined, suggesting that regional GDP and the total retail sales of consumer goods were the most important dominant variables affecting MSWG. Moreover, the MSWG might not absolutely associate with the population size and residential density. The method used in this study is a practical tool for policymakers on regional/local waste management and MSWG control.

Artificial intelligence optimization and controllable slow-release iron sulfide realizes efficient separation of copper and arsenic in strongly acidic wastewater

Iron sulfide (FeS) is a promising material for separating copper and arsenic from strongly acidic wastewater due to its S2- slow-release effect. However, uncertainties arise because of the constant changes in wastewater composition, affecting the selection of operating parameters and FeS types. In this study, the aging method was first used to prepare various controllable FeS nanoparticles to weaken the arsenic removal ability without affecting the copper removal. Orthogonal experiments were conducted, and the results identified the Cu/As ratio, H2SO4 concentration, and FeS dosage as the three main factors influencing the separation efficiency. The backpropagation artificial neural network (BP-ANN) model was established to determine the relationship between the influencing factors and the separation efficiency. The correlation coefficient (R) of overall model was 0.9923 after optimizing using genetic algorithm (GA). The BP-GA model was also solved using GA under specific constraints, predicting the best solution for the separation process in real-time. The predicted results show that the high temperature and long aging time of FeS were necessary to gain high separation efficiency, and the maximum separation factor can reached 1,400. This study provides a suitable sulfurizing material and a set of methods and models with robust flexibility that can successfully predict the separation efficiency of copper and arsenic from highly acidic environments.

Predictive modeling based on artificial neural networks for membrane fouling in a large pilot-scale anaerobic membrane bioreactor for treating real municipal wastewater

Membrane fouling is the primary obstacle to applying anaerobic membrane bioreactors (AnMBRs) in municipal wastewater treatment. This issue holds critical significance as efficient wastewater treatment serves as a cornerstone for achieving environmental sustainability. This study uses machine learning to predict membrane fouling, taking advantage of rapid computational and algorithmic advances. Based on the 525-day operation data of a large pilot-scale AnMBR for treating real municipal wastewater, regression prediction was realized using multilayer perceptron (MLP) and long short-term memory (LSTM) artificial neural networks under substantial variations in operating conditions. The models involved employing the organic loading rate, suspended solids concentration, protein concentration in extracellular polymeric substance (EPSp), polysaccharide concentration in EPS (EPSc), reactor temperature, and flux as input features, and transmembrane pressure as the prediction target output. Hyperparameter optimization enhanced the regression prediction accuracies, and the rationality and utility of the MLP model for predicting large-scale AnMBR membrane fouling were confirmed at global and local levels of interpretability analysis. This work not only provides a methodological advance but also underscores the importance of merging environmental engineering with computational advancements to address pressing environmental challenges.

The intelligent prediction of membrane fouling during membrane filtration by mathematical models and artificial intelligence models

Recently, membrane separation technology has been widely utilized in filtration process intensification due to its efficient performance and unique advantages, but membrane fouling limits its development and application. Therefore, the research on membrane fouling prediction and control technology is crucial to effectively reduce membrane fouling and improve separation performance. This review first introduces the main factors (operating condition, material characteristics, and membrane structure properties) and the corresponding principles that affect membrane fouling. In addition, mathematical models (Hermia model and Tandem resistance model), artificial intelligence (AI) models (Artificial neural networks model and fuzzy control model), and AI optimization methods (genetic algorithm and particle swarm algorithm), which are widely used for the prediction of membrane fouling, are summarized and analyzed for comparison. The AI models are usually significantly better than the mathematical models in terms of prediction accuracy and applicability of membrane fouling and can monitor membrane fouling in real-time by working in concert with image processing technology, which is crucial for membrane fouling prediction and mechanism studies. Meanwhile, AI models for membrane fouling prediction in the separation process have shown good potential and are expected to be further applied in large-scale industrial applications for separation and filtration process intensification. This review will help researchers understand the challenges and future research directions in membrane fouling prediction, which is expected to provide an effective method to reduce or even solve the bottleneck problem of membrane fouling, and to promote the further application of AI modeling in environmental and food fields.

Enhanced digestion of sludge via co-digestion with food waste in a high-solid anaerobic membrane bioreactor: Performance evaluation and microbial response

A 15 L high-solid mesophilic AnMBR was operated for the digestion of food waste, primary sludge and excess sludge. The digestion performance was evaluated from the perspective of methane generation, permeate quality and organic reduction. Furthermore, the change in the microbial community was investigated by 16S rRNA gene analysis. The results showed that the introduction of sludge decreased the H2S levels in biogas compared with the mono-digestion of food waste and the co-digestion with food waste increased biogas and methane production compared with the mono-digestion of sludge. A substitution ratio of 25 % became a turning point of permeate composition and reaction rates. The energy recovery ratios of the mesophilic AnMBR were over 75 % based on stoichiometric analysis. In reaction kinetics analysis, hydrolysis as the first step of anaerobic digestion was found to be most influenced by the composition of the substrate. Finally, the microbial community structures were stable under tested conditions while the evolutionary relationships within the dominant phyla were observed. In the archaea community, Methanosaeta was the dominant methanogen regardless sludge ratio in the substrate.

A Mechanistic Model for Hydrogen Production in an AnMBR Treating High Strength Wastewater

In the global race to produce green hydrogen, wastewater-to-H2 is a sustainable alternative that remains unexploited. Efficient technologies for wastewater-to-H2 are still in their developmental stages, and urgent process intensification is required. In our study, a mechanistic model was developed to characterize hydrogen production in an AnMBR treating high-strength wastewater (COD > 1000 mg/L). Two aspects differentiate our model from existing literature: First, the model input is a multi-substrate wastewater that includes fractions of proteins, carbohydrates, and lipids. Second, the model integrates the ADM1 model with physical/biochemical processes that affect membrane performance (e.g., membrane fouling). The model includes mass balances of 27 variables in a transient state, where metabolites, extracellular polymeric substances, soluble microbial products, and surface membrane density were included. Model results showed the hydrogen production rate was higher when treating amino acids and sugar-rich influents, which is strongly related to higher EPS generation during the digestion of these metabolites. The highest H2 production rate for amino acid-rich influents was 6.1 LH2/L-d; for sugar-rich influents was 5.9 LH2/L-d; and for lipid-rich influents was 0.7 LH2/L-d. Modeled membrane fouling and backwashing cycles showed extreme behaviors for amino- and fatty-acid-rich substrates. Our model helps to identify operational constraints for H2 production in AnMBRs, providing a valuable tool for the design of fermentative/anaerobic MBR systems toward energy recovery.

A BPNN-based ecologically extended input-output model for virtual water metabolism network management of Kazakhstan

In this study, a back-propagation-neural-network-based ecologically extended input-output model (abbreviated as BPNN-EIOM) is developed for virtual water metabolism network (VWMN) management. BPNN-EIOM can identify key consumption sectors, simulate performance of VWMN, and predict water consumption. BPNN-EIOM is then applied to analyzing VWMN of Kazakhstan, where multiple scenarios under different gross domestic production (GDP) growth rates, sectoral added values, and final demands are designed for determining the optimal management strategies. The major findings are (i) Kazakhstan typically relies on net virtual water import (reaching 1497.9 × 10⁶ m³ in 2015); (ii) agriculture is the major exporter and advanced manufacture is the major importer; (iii) by 2025, Kazakhstan's water consumption would increase to [19322, 22016] × 10⁶ m³ under multiple scenarios; (iv) when Kazakhstan's GDP growth rate, manufacturing's added value, and final demand are scheduled to 5.5%, 8.5%, and 5.8%, its VWMN can reach the optimum. The findings are useful for decision makers to optimize Kazakhstan's industrial structure, mitigate the national water scarcity, and promote its socio-economic sustainable development.

Prolonging the Life Span of Membrane in Submerged MBR by the Application of Different Anti-Biofouling Techniques

The membrane bioreactor (MBR) is an efficient technology for the treatment of municipal and industrial wastewater for the last two decades. It is a single stage process with smaller footprints and a higher removal efficiency of organic compounds compared with the conventional activated sludge process. However, the major drawback of the MBR is membrane biofouling which decreases the life span of the membrane and automatically increases the operational cost. This review is exploring different anti-biofouling techniques of the state-of-the-art, i.e., quorum quenching (QQ) and model-based approaches. The former is a relatively recent strategy used to mitigate biofouling. It disrupts the cell-to-cell communication of bacteria responsible for biofouling in the sludge. For example, the two strains of bacteria Rhodococcus sp. BH4 and Pseudomonas putida are very effective in the disruption of quorum sensing (QS). Thus, they are recognized as useful QQ bacteria. Furthermore, the model-based anti-fouling strategies are also very promising in preventing biofouling at very early stages of initialization. Nevertheless, biofouling is an extremely complex phenomenon and the influence of various parameters whether physical or biological on its development is not completely understood. Advancing digital technologies, combined with novel Big Data analytics and optimization techniques offer great opportunities for creating intelligent systems that can effectively address the challenges of MBR biofouling.