A generalized predictive model for TiO2-Catalyzed photo-degradation rate constants of water contaminants through artificial neural network

Prediction of chlorination degradation rate of emerging contaminants based on machine learning models

Assessing the degradation of emerging contaminants in water through chlorination is crucial for regulatory monitoring of these contaminants. In this study, we developed a machine learning model to predict the apparent second-order reaction rate constants for organic pollutants undergoing chlorination. The model was trained using second-order reaction rate constants for 587 organic pollutants, with 314 data points obtained from actual experiments, the other data points 273 came from previous studies. We evaluated ten machine learning algorithms with Modred molecular descriptors and MACCS molecular fingerprints, optimizing the hyperparameters through Bayesian optimization to enhance the predictive capability of the model. The optimized model GPR algorithm combined with molecular fingerprint model achieved R2train = 0.866 and R2test = 0.801. Subsequently, the model was fed with chemical features of four organic pollutants, and the predicted results were compared with experimentally obtained values, the deviations between predicted and experimental values were found to be 2.12%, 0.37%, 0.15%, and 14.8%, respectively, further validating the accuracy of the predictive model. SHAP analysis showed that the amino-methyl group CN(C)C had the highest feature value, demonstrating the interpretability of the model in predicting chlorine-degraded pollutants The model established in this study is more representative of real chlorination environments, providing preliminary guidance for chlorination plants on the degradation of numerous emerging contaminants lacking treatment standards and facilitating the refinement of strategies for the prevention and control of emerging contaminants.

Toward the development of an ML-driven decision support system for wastewater treatment: A bacterial inactivation prediction approach in solar photochemical processes

The design of efficient bacterial inactivation treatment in wastewater is challenging due to its numerous parameters and the complex composition of wastewater. Although solar photochemical processes (PCPs) provide energy-saving benefits, a balance must be maintained between bacterial inactivation efficiency and experimental costs. Predictive decision tools for bacterial inactivation under various conditions would significantly contribute to optimizing PCP design resources. This study evaluated four machine learning algorithms (ML) (i.e., Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boost (XGBoost)) for predicting bacterial inactivation behavior, using Escherichia coli, Enterococcus spp., and Salmonella spp. Several oxidant types, bacterial concentrations, and aqueous matrices were evaluated in two scenarios simulating real-world conditions. Results demonstrated that decision tree-based models (RF and XGBoost) outperformed SVM and ANN in accuracy. In Scenario I (prediction of intermediate experimental values over time) the XGBoost model was most effective, achieving a Root Mean Square Error (RMSE) of 0.81, 0.76 and 0.55 and an R2 of 0.84, 0.79, and 0.87 for the three bacteria, respectively. In Scenario II (prediction of full experimental values over time), the RF model excelled for Escherichia coli and Salmonella spp. with an RMSE of 0.88 for both and an R2 of 0.80 and 0.71, respectively. The XGBoost model showed moderate effectiveness for Enterococcus sp. with an RMSE of 1.31 and R2 of 0.50. Overall, the decision tree-based models demonstrated their potential for prediction in tests of a wide range of PCP parameters without requiring additional trials.

Optimization of Brilliant Blue R photocatalytic degradation by silver nanoparticles synthesized using Chlorella vulgaris

Synthesis of silver nanoparticles (Ag NPs) using microalgae is gaining recognition for its environmentally friendly and cost-effective nature while maintaining high activity of NPs. In the present study, Ag NPs were synthesized using a methanolic extract of Chlorella vulgaris and subjected to calcination. The X-ray diffraction (XRD) analysis showed a crystalline nature of the products with Ag2O and Ag phases with an average crystalline size of 16.07 nm before calcination and an Ag phase with 24.61 nm crystalline size after calcination. Fourier transform infrared spectroscopy (FTIR) revealed the capping functional groups on Ag NPs, while scanning electron microscopy (SEM) displayed their irregular morphology and agglomeration after calcination. The organic coating was examined by energy-dispersive X-ray spectroscopy (EDX) and thermogravimetric (TGA) analyses, confirming the involvement of the metabolites. The UV-Vis analysis showed a difference in optical properties due to calcination. Synthesized Ag NPs were applied for the photodegradation of hazardous dye Brilliant Blue R in visible light. Different values of light intensity, catalyst dose, initial dye concentration, and pH were tested to identify the optimal set of operating conditions. The highest degradation efficiency of 90.6% with an apparent rate constant of 0.04402 min-1 was achieved after 90 min of irradiation in the highest tested catalyst dosage.

Application of artificial intelligence for the optimization of advanced oxidation processes to improve the water quality polluted with pharmaceutical compounds

Sulfamethoxazole and metronidazole are emerging pollutants commonly found in surface water and wastewater. These compounds have a significant environmental impact, being necessary in the design of technologies for their removal. Recently, the advanced oxidation process has been proven successful in the elimination of this kind of compounds. In this sense, the present work discusses the application of UV/H2O2 and ozonation for the degradation of both molecules in single and binary systems. Experimental kinetic data from O3 and UV/H2O2 process were adequately described by a first and second kinetic model, respectively. From the ANOVA analysis, it was determined that the most statistically significant variables were the initial concentration of the drugs (0.03 mmol L-1) and the pH = 8 for UV/H2O2 system, and only the pH (optimal value of 6) was significant for degradation with O3. Results showed that both molecules were eliminated with high degradation efficiencies (88-94% for UV/H2O2 and 79-98% for O3) in short reaction times (around 30-90 min). The modeling was performed using a quadratic regression model through response surface methodology representing adequately 90 % of the experimental data. On the other hand, an artificial neural network was used to evaluate a non-linear multi-variable system, a 98% of fit between the model and experimental data was obtained. The identification of degradation byproducts was performed by high-performance liquid chromatography coupled to a time mass detector. After each process, at least four to five stable byproducts were found in the treated water, reducing the mineralization percentage to 20% for both molecules.

Integrative analysis of multi machine learning models for tetracycline photocatalytic degradation with MOFs in wastewater treatment

This study focuses on the utilization of connectionist models, specifically Independent Component Analysis (ICA), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Genetic Algorithm-Particle Swarm Optimization (GAPSO) integrated with a least-squares support vector machine (LSSVM) to forecast the degradation of tetracycline (TC) through photocatalysis using Metal-Organic Frameworks (MOFs). The primary objective of this study was to evaluate the viability and precision of these connectionist models in estimating the efficiency of TC degradation, particularly within the context of wastewater treatment. The input parameters for these models cover essential MOF characteristics, such as pore size and surface area, along with critical operational factors, such as pH, TC concentration, catalyst dosage, and illumination duration, all of which are linked to the photocatalytic performance of MOFs. Sensitivity analysis revealed that the illumination duration is the primary influencer of TC photodegradation with MOF photocatalysts, while the MOFs' surface area is the second crucial parameter shaping the efficiency and dynamics of the TC-MOF photocatalytic system. The developed LSSVM models display impressive predictive capabilities, effectively forecasting the experimental degradation of TC with high accuracy. Among these models, the GAPSO-LSSVM model excels as the top performer, achieving notable evaluation metrics, including STD, RMSE, MSE, MRE, and R2 at values of 3.09, 3.42, 11.71, 5.95, and 0.986, respectively. In comparison, the PSO-LSSVM, ICA-LSSVM, and GA-LSSVM models yield mean relative errors of 6.18%, 7.57%, and 11.37%, respectively. These outcomes highlight the exceptional predictive capabilities of the GAPSO-LSSVM model, solidifying its position as the most accurate and dependable model for predicting TC photodegradation in this study. This study contributes to advancing photocatalytic research and effectively reinforces the importance of leveraging machine learning methodologies for tackling environmental challenges.

Biological 2,4,6-trinitrotoluene removal by extended aeration activated sludge: optimization using artificial neural network

Serious health issues can result from exposure to the nitrogenous pollutant like 2,4,6-trinitrotoluene (TNT), which is emitted into the environment by the munitions and military industries, as well as from TNT-contaminated wastewater. The TNT removal by extended aeration activated sludge (EAAS) was optimized in the current study using artificial neural network modeling. In order to achieve the best removal efficiency, 500 mg/L of chemical oxygen demand (COD), 4 and 6 h of hydraulic retention time (HRT), and 1-30 mg/L of TNT were used in this study. The kinetics of TNT removal by the EAAS system were described by the calculation of the kinetic coefficients K, Ks, Kd, max, MLSS, MLVSS, F/M, and SVI. Adaptive neuro fuzzy inference system (ANFIS) and genetic algorithms (GA) were used to optimize the data obtained through TNT elimination. ANFIS approach was used to analyze and interpret the given data, and its accuracy was around 97.93%. The most effective removal efficiency was determined using the GA method. Under ideal circumstances (10 mg/L TNT concentration and 6 h), the TNT removal effectiveness of the EAAS system was 84.25%. Our findings demonstrated that the artificial neural network system (ANFIS)-based EAAS optimization could enhance the effectiveness of TNT removal. Additionally, it can be claimed that the enhanced EAAS system has the ability to extract wastewaters with larger concentrations of TNT as compared to earlier experiments.

Optimized photodegradation of palm oil agroindustry waste effluent using multivalent manganese-modified black titanium dioxide

This article presents a methodological approach to use manganese (Mn³⁺Mn⁷⁺)-modified black titanium dioxide (Mn/BTiO₂) as a photocatalyst to optimize and improve visible-light-driven photodegradation of treated agro-industrial effluent (TPOME). A modified wet chemical process was used to prepare BTiO₂. The BTiO₂ was then wet impregnated with Mn and calcined at 300 °C for 1 h to produce Mn/BTiO₂. The activity of Mn/BTiO₂ was investigated in terms of photo-assisted elimination of chemical oxygen demand (COD), phenolic compounds (PCs), color, and total organic carbon (TOC). Using the design of experiments (DOE), the conditions of the photocatalytic process, including photocatalyst loading, Mn concentration, hydrogen peroxide (H₂O₂) dose, and irradiation time, were optimized. Under the optimum conditions (0.85 g/L photocatalyst loading, 0.048 mol/L H₂O₂ dose, 0.301 wt.% Mn concentration, and 204 min irradiation time) COD, PCs, color, and TOC removal efficiencies of 88.87%, 86.04%, 62.8%, and 84.66%, respectively, were obtained. Statistical analysis showed that the response variable's removal from TPOME estimation had high R² and low RMSE, MSE, MAD, MAE, and MAPE values, indicating high reliability. This study demonstrated the significant potential of the developed photocatalytic system for the treatment of waste effluent generated by the palm oil industry and other agro-industries, with the ability to simultaneously reduce a number of organic pollution indicators (OPIs).

Photo-Antibacterial Activity of Two-Dimensional (2D)-Based Hybrid Materials: Effective Treatment Strategy for Controlling Bacterial Infection

Bacterial contamination in water bodies is a severe scourge that affects human health and causes mortality and morbidity. Researchers continue to develop next-generation materials for controlling bacterial infections from water. Photo-antibacterial activity continues to gain the interest of researchers due to its adequate, rapid, and antibiotic-free process. Photo-antibacterial materials do not have any side effects and have a minimal chance of developing bacterial resistance due to their rapid efficacy. Photocatalytic two-dimensional nanomaterials (2D-NMs) have great potential for the control of bacterial infection due to their exceptional properties, such as high surface area, tunable band gap, specific structure, and tunable surface functional groups. Moreover, the optical and electric properties of 2D-NMs might be tuned by creating heterojunctions or by the doping of metals/carbon/polymers, subsequently enhancing their photo-antibacterial ability. This review article focuses on the synthesis of 2D-NM-based hybrid materials, the effect of dopants in 2D-NMs, and their photo-antibacterial application. We also discuss how we could improve photo-antibacterials by using different strategies and the role of artificial intelligence (AI) in the photocatalyst and in the degradation of pollutants. Finally, we discuss was of improving the photo-antibacterial activity of 2D-NMs, the toxicity mechanism, and their challenges.

Heterogeneous catalysis mediated by light, electricity and enzyme via machine learning: Paradigms, applications and prospects

Energy crisis and environmental pollution have become the bottleneck of human sustainable development. Therefore, there is an urgent need to develop new catalysts for energy production and environmental remediation. Due to the high cost caused by blind screening and limited valuable computing resources, the traditional experimental methods and theoretical calculations are difficult to meet with the requirements. In the past decades, computer science has made great progress, especially in the field of machine learning (ML). As a new research paradigm, ML greatly accelerates the theoretical calculation methods represented by first principal calculation and molecular dynamics, and establish the physical picture of heterogeneous catalytic processes for energy and environment. This review firstly summarized the general research paradigms of ML in the discovery of catalysts. Then, the latest progresses of ML in light-, electricity- and enzyme-mediated heterogeneous catalysis were reviewed from the perspective of catalytic performance, operating conditions and reaction mechanism. The general guidelines of ML for heterogeneous catalysis were proposed. Finally, the existing problems and future development trend of ML in heterogeneous catalysis mediated by light, electricity and enzyme were summarized. We highly expect that this review will facilitate the interaction between ML and heterogeneous catalysis, and illuminate the development prospect of heterogeneous catalysis.

Using Sono-Electro-Persulfate Process for Atenolol Removal from Aqueous Solutions: Prediction and Optimization with the ANFIS Model and Genetic Algorithm

Atenolol (ATN) is a drug that is widely used to treat some heart diseases, and since it cannot be completely decomposed in the human body, some amounts of it are found in surface water. These amounts may bring risks to the environment and humans, and for this reason, its removal is a must. In the present study, the combined sono-electro-persulfate method was used for ATN removal. Based on the design of the experiment conducted by response surface methodology (RSM), the effects of 5 main factors (pH, time, PS concentration, current intensity, and initial ATN concentration) have been investigated at 5 levels. After passing the test steps in different conditions, the remaining amount of ATN has been measured by high-performance liquid chromatography (HPLC). Finally, an adaptive neuro-fuzzy inference system (ANFIS) with 99.63% accuracy and a genetic algorithm (GA) were used to analyze and interpret data and predict optimal conditions. The obtained results indicate the possibility of a maximum efficiency of 99.8% in the mentioned conditions (Ph of 7.4, time of 18 min, PS concentration of 2000 mg/L, current intensity of 3.35 A, and initial ATN concentration of 11.2 mg/L). According to the obtained results, the initial concentration of ATN can be considered as the most effective factor in this process, and the best Ph range for this experiment was the neutral range. The sono-electro persulfate process can be mentioned as a new and effective method for removing ATN from water sources.

Machine Learning for Electrocatalyst and Photocatalyst Design and Discovery

Electrocatalysts and photocatalysts are key to a sustainable future, generating clean fuels, reducing the impact of global warming, and providing solutions to environmental pollution. Improved processes for catalyst design and a better understanding of electro/photocatalytic processes are essential for improving catalyst effectiveness. Recent advances in data science and artificial intelligence have great potential to accelerate electrocatalysis and photocatalysis research, particularly the rapid exploration of large materials chemistry spaces through machine learning. Here a comprehensive introduction to, and critical review of, machine learning techniques used in electrocatalysis and photocatalysis research are provided. Sources of electro/photocatalyst data and current approaches to representing these materials by mathematical features are described, the most commonly used machine learning methods summarized, and the quality and utility of electro/photocatalyst models evaluated. Illustrations of how machine learning models are applied to novel electro/photocatalyst discovery and used to elucidate electrocatalytic or photocatalytic reaction mechanisms are provided. The review offers a guide for materials scientists on the selection of machine learning methods for electrocatalysis and photocatalysis research. The application of machine learning to catalysis science represents a paradigm shift in the way advanced, next-generation catalysts will be designed and synthesized.

Predicting Active Sites in Photocatalytic Degradation Process Using an Interpretable Molecular-Image Combined Convolutional Neural Network

Machine-learning models have great potential to accelerate the design and performance assessment of photocatalysts, leveraging their unique advantages in detecting patterns and making predictions based on data. However, most machine-learning models are “black-box” models due to lack of interpretability. This paper describes the development of an interpretable neural-network model on the performance of photocatalytic degradation of organic contaminants by TiO2. The molecular structures of the organic contaminants are represented by molecular images, which are subsequently encoded by feeding into a special convolutional neural network (CNN), EfficientNet, to extract the critical structural features. The extracted features in addition to five other experimental variables were input to a neural network that was subsequently trained to predict the photodegradation reaction rates of the organic contaminants by TiO2. The results show that this machine-learning (ML) model attains a higher accuracy to predict the photocatalytic degradation rate of organic contaminants than a previously developed machine-learning model that used molecular fingerprint encoding. In addition, the most relevant regions in the molecular image affecting the photocatalytic rates can be extracted with gradient-weighted class activation mapping (Grad-CAM). This interpretable machine-learning model, leveraging the graphic interpretability of CNN model, allows us to highlight regions of the molecular structure serving as the active sites of water contaminants during the photocatalytic degradation process. This provides an important piece of information to understand the influence of molecular structures on the photocatalytic degradation process.

An insight into tetracycline photocatalytic degradation by MOFs using the artificial intelligence technique

Tetracyclines (TCs) have been extensively used for humans and animal diseases treatment and livestock growth promotion. The consumption of such antibiotics has been ever-growing nowadays due to various bacterial infections and other pathologic conditions, resulting in more discharge into the aquatic environments. This brings threats to ecosystems and human bodies. Up to now, several attempts have been made to reduce TC amounts in the wastewater, among which photocatalysis, an advanced oxidation process, is known as an eco-friendly and efficient technology. In this regard, metal organic frameworks (MOFs) have been known as the promising materials as photocatalysts. Thus, studying TC photocatalytic degradation by MOFs would help scientists and engineers optimize the process in terms of effective parameters. Nevertheless, the costly and time-consuming experimental methods, having instrumental errors, encouraged the authors to use the computational method for a more comprehensive assessment. In doing so, a wide-ranging databank including 374 experimental data points was gathered from the literature. A powerful machine learning method of Gaussian process regression (GPR) model with four kernel functions was proposed to estimate the TC degradation in terms of MOFs features (surface area and pore volume) and operational parameters (illumination time, catalyst dosage, TC concentration, pH). The GPR models performed quite well, among which GPR-Matern model shows the most accurate performance with R², MRE, MSE, RMSE, and STD of 0.981, 12.29, 18.03, 4.25, and 3.33, respectively. In addition, an analysis of sensitivity was carried out to assess the effect of the inputs on the TC photodegradation by MOFs. It revealed that the illumination time and the surface area play a significant role in the decomposition activity.

Photocatalytic degradation of Penicillin G in aqueous solutions: Kinetic, degradation pathway, and microbioassays assessment

The photocatalytic degradation of pharmaceutical micropollutants of Penicillin G (PG) was investigated in a photoreactor at a laboratory scale. The impact of type of catalyst, pH, and initial concentration of PG were studied. Maximum removal efficiency was obtained at pH = 6.8, [ZnO]₀ = 0.8 g L^-1, and [PG]₀ = 5 mg L^-1 and reaction time of 150 min. The addition of persulfate sodium (PPS) enhanced the efficiency of the photocatalytic reaction. The efficiency of photolysis process in the presence of PPS was significantly improved to 72.72% compared to the classical photocatalysis system (56.71%). Optimum concentration of PPS to completely degraded PG was found to be 500 mg L^-1. The QuEChERS extraction, GC-MS/MS method, and concentration technique showed favorable performance identification of the possible mechanism of PG degradation pathway. Toxicity of PG and its by-products were evaluated using microbioassays assessment based on nine selected bacterial strains. Results confirmed the effectiveness of the implemented system and its safe use via the bacteria Bacillus subtilis, which has illustrated significant activity. Due to the high efficiency, facility benefits, and low-cost of the suggested process, the process can be considered for the degradation of various pharmaceutical contaminants in pharmaceutical industry treatment under the optimal conditions.

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.

A Novel Machine Learning Model to Predict the Photo-Degradation Performance of Different Photocatalysts on a Variety of Water Contaminants

This paper describes an innovative machine learning (ML) model to predict the performance of different metal oxide photocatalysts on a wide range of contaminants. The molecular structures of metal oxide photocatalysts are encoded with a crystal graph convolution neural network (CGCNN). The structure of organic compounds is encoded via digital molecular fingerprints (MF). The encoded features of the photocatalysts and contaminants are input to an artificial neural network (ANN), named as CGCNN-MF-ANN model. The CGCNN-MF-ANN model has achieved a very good prediction of the photocatalytic degradation rate constants by different photocatalysts over a wide range of organic contaminants. The effects of the data training strategy on the ML model performance are compared. The effects of different factors on photocatalytic degradation performance are further evaluated by feature importance analyses. Examples are illustrated on the use of this novel ML model for optimal photocatalyst selection and for assessing other types of photocatalysts for different environmental applications.