Vertical flow constructed wetlands using expanded clay and biochar for wastewater remediation: A comparative study and prediction of effluents using machine learning

New challenge: Mitigation and control of antibiotic resistant genes in aquatic environments by biochar

With an increase of diverse contaminants in the environment, particularly antibiotics, the maintenance and propagation of antibiotic resistance genes (ARGs) are promoted by co-selection mechanisms. ARGs are difficult to degrade, cause long-lasting pollution, and are widely transmitted in aquatic environments. Biochar is frequently used to remove various pollutants during environmental remediation. Thus, this review provides a thorough analysis of the current state of ARGs in the aquatic environment as well as their removal by using biochar. This article summarizes the research and application of biochar and modified biochar to remove ARGs in aquatic environments, in order to refine the following contents: 1) fill gaps in the research on the various ARG behaviors mediated by biochar and some influence factors, 2) further investigate the mechanisms involved in effects of biochar on extracellular ARGs (eARGs) and intracellular ARGs (iARGs) in aquatic environments, including direct and the indirect effects, 3) describe the propagation process and resistance mechanisms of ARGs, 4) propose the challenges and prospects of feasibility of application and subsequent treatment in actual aquatic environment. Here we highlight the most recent research on the use of biochar to remove ARGs from aquatic environments and suggest future directions for optimization, as well as current perspectives to guide future studies on the removal of ARGs from aquatic environments.

Machine learning-based exploration of biochar for environmental management and remediation

Biochar has a wide range of applications, including environmental management, such as preventing soil and water pollution, removing heavy metals from water sources, and reducing air pollution. However, there are several challenges associated with the usage of biochar for these purposes, resulting in an abundance of experimental data in the literature. Accordingly, the purpose of this study is to examine the use of machine learning in biochar processes with an eye toward the potential of biochar in environmental remediation. First, recent developments in biochar utilization for the environment are summarized. Then, a bibliometric analysis is carried out to illustrate the major trends (demonstrating that the top three keywords are heavy metal, wastewater, and adsorption) and construct a comprehensive perspective for future studies. This is followed by a detailed review of machine learning applications, which reveals that adsorption efficiency and capacity are the primary utilization targets in biochar utilization. Finally, a comprehensive perspective is provided for the future. It is then concluded that machine learning can help to detect hidden patterns and make accurate predictions for determining the combination of variables that results in the desired properties which can be later used for decision-making, resource allocation, and environmental management.

Estimating ammonium changes in pilot and full-scale constructed wetlands using kinetic model, linear regression, and machine learning

Constructed wetlands (CWs) are a widely utilized nature-based wastewater treatment method for various effluents. However, their application has been more focused on pilot and full-scale CWs with substantial surface areas and extended operation times, which hold greater relevance in practical scenarios. This study used kinetics, linear regression (LR), and machine learning (ML) models to estimate effluent ammonium in pilot and full-scale CWs. From screening 1476 papers, 24 pilot and full-scale CW studies were selected to extract data containing 15 features and 975 data points. Nine models were fit to this data, revealing that linear models were less effective in capturing CW effluent compared to nonlinear ML algorithms. For training data, the Monod kinetic model predicted the poorest performance with an RMSE of 41.84 mg/L and R2 of 0.34, followed by simple LR (RMSE 24.29 mg/L and R2 0.77) and multiple LR (RMSE 22.63 mg/L and R2 0.80). In contrast, Cubist and Random Forest achieved high performances, with an average RMSE of 12.01 ± 5.38 and an average R2 of 0.93 ± 0.07 for Cubist, and an average RMSE of 15.94 ± 10.69 and an average R2 of 0.91 ± 0.08 for RF. The trained Random Forest performed the best for new data, with an R2 of 0.93 and RMSE of 13.48 mg/L. This ML-based model is a valuable tool for efficiently estimating effluent ammonium concentration in pilot and full-scale CWs, thereby facilitating the design of systems.

Biodegradation and sorption of nutrients and endocrine disruptors in a novel concrete-based substrate in vertical-flow constructed wetlands

Removing phosphorus and endocrine-disruptors (EDC) is still challenging for low-cost sewage treatment systems. This study investigated the efficiency of three vertical-flow constructed wetlands (VFCW) vegetated with Eichhornia crassipes onto red clay (CW-RC), autoclaved aerated concrete (CW-AC), and composite from the chemical activation of autoclaved aerated concrete with white cement (CW-AAC) in the removal of organic matter, nutrients, and estrone, 17β-estradiol, and 17α-ethinylestradiol. The novelty aspect of this study is related to selecting these clay and cementitious-based materials in removing endocrine disruptors and nutrients in VFCW. The subsurface VFCW were operated in sequencing-batch mode (cycles of 48-48-72 h), treating synthetic wastewater for 308 days. The operation consisted of Stages I and II, different by adding EDC in Stage II. The presence of EDC increased the competition for dissolved oxygen (DO) and reduced the active sites available for adsorption, diminishing the removal efficiencies of TKN and TAN and total phosphorus in the systems. CW-RC showed a significant increase in COD removal from 65% to 91%, while CW-AC and CW-AAC maintained stable COD removal (84%-82% and 78%-81%, respectively). Overall, the substrates proved effective in removing EDC, with CW-AC and CW-AAC achieving >60% of removal. Bacteria Candidatus Brocadia and Candidatus Jettenia, responsible for carrying out the Anammox process, were identified in assessing the microbial community structure. According to the mass balance analysis, adsorption is the main mechanism for removing TP in CW-AC and CW-AAC, while other losses were predominant in CW-RC. Conversely, for TN removal, the adsorption is more representative in CW-RC, and the different metabolic routes of microorganisms, biofilm assimilation, and partial ammonia volatilization in CW-AC and CW-AAC. The results suggest that the composite AAC is the most suitable material for enhancing the simultaneous removal of organic matter, nutrients, and EDC in VFCW under the evaluated operational conditions.

Virtual sample generation empowers machine learning-based effluent prediction in constructed wetlands

The design of constructed wetlands (CWs) is critical to ensure effective wastewater treatment. However, limited availability of reliable data can hamper the accuracy of CW effluent predictions, thus increasing design costs and time. In this study, a novel effluent prediction framework for CWs is proposed, utilizing data dimensionality reduction and virtual sample generation. By using four the machine learning algorithms (Cubist, random forest, support vector regression, and extreme learning machine), important features of CW design are identified and used to build prediction models. The extreme learning machine algorithm achieved the highest determination coefficient and lowest error, identifying it as the most suitable algorithm for effluent prediction. A multi-distribution mega-trend-diffusion algorithm with particle swarm optimization was employed to generate virtual samples. These virtual samples were then combined with real samples to retrain the prediction model and verify the optimization effect. Comparative analysis demonstrated that the integration of virtual samples significantly improved the prediction accuracy for ammonium and chemical oxygen demand. The root mean square error decreased by averages of 60.5% and 42.1%, respectively, and the mean absolute percentage error by averages of 21.5% and 23.8%, respectively. Finally, a CW design process is proposed based on prediction models and virtual samples. This integrated forward prediction and reverse design tool can efficiently support CW design when sample sizes are limited, ultimately leading to more accurate and cost-effective design solutions.

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

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

Enhanced benzofluoranthrene removal in constructed wetlands with iron- modified biochar: Mediated by dissolved organic matter and microbial response

Polycyclic aromatic hydrocarbons (PAHs) pose a high risk to ecosystems owing to their adverse environmental effects. The use of biochar in constructed wetlands (CWs) to remove PAH has received increased interest, but is frequently challenging because of saturation adsorption. To enhance the microbial degradation, electron acceptors are provided. This study aimed to remove a representative PAH, benzofluoranthrene (BbF), using iron-modified biochar as a supplement to the CW substrate. Results revealed that iron-mediated biochar based CWs increased the removal of BbF by 20.4 % and ammonium by 25.6 %. The BbF retained in substrate with biochar (36.6 % higher content) and further removed with iron modification (40.6 % lower content). Iron-modified biochar increased dissolved organic carbon content, particularly low-aromaticity, and low-molecular-weight organic matters (25.7 % higher tryptophan-like material), which contributed to PAH degradation by microorganisms. Microbial analysis confirmed that iron-mediated biochar enriched the abundance of microbes (e.g., Cellulomonas, Actinotalea, and Sphingomonas) and key enzymes (e.g., catA, lipV, and sdhA) that are involved in PAH degradation. Higher proportion of iron-reducing bacteria (e. g., Thiobacillus, Rhodobacter) played a significant role in driving microbial iron cycle, which was beneficial for PAHs removal. Based on the results, we confirmed that the use of iron-modified biochar in CWs enhance PAH removal.

Artificial intelligence and machine learning-based monitoring and design of biological wastewater treatment systems

Artificial intelligence (AI) and machine learning (ML) are currently used in several areas. The applications of AI and ML based models are also reported for monitoring and design of biological wastewater treatment systems (WWTS). The available information is reviewed and presented in terms of bibliometric analysis, model's description, specific applications, and major findings for investigated WWTS. Among the applied models, artificial neural network (ANN), fuzzy logic (FL) algorithms, random forest (RF), and long short-term memory (LSTM) were predominantly used in the biological wastewater treatment. These models are tested by predictive control of effluent parameters such as biological oxygen demand (BOD), chemical oxygen demand (COD), nutrient parameters, solids, and metallic substances. Following model performance indicators were mainly used for the accuracy analysis in most of the studies: root mean squared error (RMSE), mean square error (MSE), and determination coefficient (DC). Besides, outcomes of various models are also summarized in this study.

A hybrid data-driven framework for diagnosing contributing factors for soil heavy metal contaminations using machine learning and spatial clustering analysis

The efficacy of source apportionment is often limited by a lack of information on natural and anthropogenic contributing factors influencing soil heavy metal (HM) contaminations. To overcome this limitation and develop the data mining methods, a novel hybrid data-driven framework was proposed to diagnose the contributing factors in an industrialized region in Guangdong Province, China, mainly using a combination of naive Bayes (NB), random forest (RF), and bivariate local Moran's I (BLMI) on the basis of the multi-source big data. The medium industry types of enterprises from the freely available Baidu point of interest data were successfully classified, and then the 250 contaminating enterprises as a contributing factor were identified by the optimized NB classifier. The quantitative contributions of the nine contributing factors for the As, Cd, and Hg concentrations were determined by the optimized RF. The twelve spatial clustering maps between the three HM concentrations and the four key contributing factors were generated by BLMI, explicitly revealing their mutual interactions and internal effects and also intuitively showing the "high-high" areas and their distributions. This framework can obtain rich information on contributing factors such as medium industry types, contribution rates, spatial clusters, and spatial distributions.

Recent advances of carbon-based nanomaterials (CBNMs) for wastewater treatment: Synthesis and application

Carbon-based nanomaterials (CBNMs) have attracted significant alert due to the affluent science underpinning their implementations associated with a novel mixture of high aspect proportions, greater thermal and electrical performance, outstanding optical features, and high exterior area. CBNMs not only bear assurance in a broad range of implementations in medication, nano and microelectronics, and ecological remedies but may also be utilized in practical laboratory determinations. More specifically, CBNMs perform as an outstanding adsorbent in terminating heavy metal ions (HMI) from wastewater. There is presently a deficiency of powerful threat inspection instruments owing to their complex detection and related deficit in the health risk database. Therefore, our present review concentrates on spreading CBNMs to release pollutants from wastewater. The article wraps the effect of these contaminants and photocatalytic strategies towards treating these mixtures in wastewater, along with their restrictions and challenges, convincing resolutions, and possibilities of these approaches.

Prediction of heterogeneous Fenton process in treatment of melanoidin-containing wastewater using data-based models

Predictive capability of response surface methodology (RSM) and ant colony optimization combined with support vector regression (ACO-SVR) models are applied for determining optimal parameters in the process of heterogeneous Fenton oxidation of melanoidin, a high molecular weight polymer widely produced during fermentation processes generating large quantities of wastewater with intense brown color and extremely high chemical oxygen demand (COD). Prediction of the performance of nano zero-valent iron supported on activated carbon cloth-chitosan (ACC-CH-nZVI) catalysts was carried out using Box-Behnken design (BBD) and analysis of variance to evaluate the interaction of independent variables involved in heterogeneous Fenton reaction. The optimized condition with minimal consumption of H₂O₂ (173 mM) resulted in 77.1% decolorization of melanoidin-contaminated water corresponding to 74.4% COD removal at pH 3 (600 mg/l Fe dosage) for 90 min reaction time. The corresponding weight ratio of H₂O₂ to COD was 0.98, much lower than the stoichiometric value 2.125, indicating the effectiveness of ACC-CH-nZVI as a heterogeneous Fenton-like catalyst. In comparison to previously published experimental results, ACO-SVR model shows higher coefficient of determination (R²; 0.9983) but lower root mean squared error (RMSE) and mean absolute error (MAE) than those of RSM model, indicating relative superiority in prediction capability. Besides, ACO algorithm appears to be a promising tool for improving forecasting accuracy of SVR model. This work demonstrates the applicability of ACO-SVR model in predicting the performance of wastewater treatment using Fenton process with limited number of experiment and exhibits satisfactory prediction results.

The state of art on the prediction of efficiency and modeling of the processes of pollutants removal based on machine learning

During the last few years, important advances have been made in big data exploration, complex pattern recognition and prediction of complex variables. Machine learning (ML) algorithms can efficiently analyze voluminous data, identify complex patterns and extract conclusions. In chemical engineering, the application of machine learning approaches has become highly attractive due to the growing complexity of this field. Machine learning allows computers to solve problems by learning from large data sets and provides researchers with an excellent opportunity to enhance the quality of predictions for the output variables of a chemical process. Its performance has been increasingly exploited to overcome a wide range of challenges in chemistry and chemical engineering, including improving computational chemistry, planning materials synthesis and modeling pollutant removal processes. In this review, we introduce this discipline in terms of its accessible to chemistry and highlight studies that illustrate in-depth the exploitation of machine learning. The main aim of the review paper is to answer these questions by analyzing physicochemical processes that exploit machine learning in organic and inorganic pollutants removal. In general, the purpose of this review is both to provide a summary of research related to the removal of various contaminants performed by ML models and to present future research needs in ML for contaminant removal.

Potential application of machine learning for exploring adsorption mechanisms of pharmaceuticals onto biochars

The increasing accumulation of pharmaceuticals in aquatic ecosystems could impair freshwater quality and threaten human health. Despite the adsorption of pharmaceuticals on biochars is one of the most cost-effective and eco-friendly removal methods, the wide variation of experimental designs and research aims among previous studies pose significant challenge in selecting biochar for optimal removal. In this work, literature data of 1033 sets with 21 variables collected from 267 papers over ten years (2010-2020) covering 19 pharmaceuticals onto 88 biochars were assessed by different machine learning (ML) algorithms i.e., Linear regression model (LM), Feed-forward neural networks (NNET), Deep neutral networks (DNN), Cubist, K-nearest neighbor (KNN), and Random forest (RF), to predict equilibrium adsorption capacity (Q_e) and explore adsorption mechanisms. LM showed the best performance on ranking importance of input variables. Except for initial concentration of pharmaceuticals, Q_e was strongly governed by biochars' properties including specific surface area (BET), pore volume (PV), and pore structure (PS) rather than pharmaceuticals' properties and experimental conditions. The most accurate model for estimating Q_e was achieved by Cubist, followed by KNN, RF, KNN, NNET and LM. The generalization ability was observed by the tuned Cubist with 26 rules for the prediction of the unseen data. This study not only provides an insightful evidence for data-based adsorption mechanisms of pharmaceuticals on biochars, but also offers a potential method to accurately predict the biochar adsorption performance without conducting any experiments, which will be of high interests in practice in terms of water/wastewater treatment using biochars.