Next Article in Journal
Gated Fusion Networks for Multi-Modal Violence Detection
Previous Article in Journal
Data Preprocessing and Feature Engineering for Data Mining: Techniques, Tools, and Best Practices
Previous Article in Special Issue
Advances and Optimization Trends in Photovoltaic Systems: A Systematic Review
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

Artificial Intelligence-Guided Supervised Learning Models for Photocatalysis in Wastewater Treatment

by
Asma Rehman
1,
Muhammad Adnan Iqbal
1,2,*,
Mohammad Tauseef Haider
1 and
Adnan Majeed
1
1
Department of Chemistry, University of Agriculture Faisalabad, Faisalabad 38040, Pakistan
2
Organometallic & Coordination Chemistry Laboratory, Department of Chemistry, University of Agriculture Faisalabad, Faisalabad 38040, Pakistan
*
Author to whom correspondence should be addressed.
AI 2025, 6(10), 258; https://doi.org/10.3390/ai6100258
Submission received: 30 July 2025 / Revised: 30 August 2025 / Accepted: 9 September 2025 / Published: 3 October 2025

Abstract

Artificial intelligence (AI), when integrated with photocatalysis, has demonstrated high predictive accuracy in optimizing photocatalytic processes for wastewater treatment using a variety of catalysts such as TiO2, ZnO, CdS, Zr, WO2, and CeO2. The progress of research in this area is greatly enhanced by advancements in data science and AI, which enable rapid analysis of large datasets in materials chemistry. This article presents a comprehensive review and critical assessment of AI-based supervised learning models, including support vector machines (SVMs), artificial neural networks (ANNs), and tree-based algorithms. Their predictive capabilities have been evaluated using statistical metrics such as the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE), with numerous investigations documenting R2 values greater than 0.95 and RMSE values as low as 0.02 in forecasting pollutant degradation. To enhance model interpretability, Shapley Additive Explanations (SHAP) have been employed to prioritize the relative significance of input variables, illustrating, for example, that pH and light intensity frequently exert the most substantial influence on photocatalytic performance. These AI frameworks not only attain dependable predictions of degradation efficiency for dyes, pharmaceuticals, and heavy metals, but also contribute to economically viable optimization strategies and the identification of novel photocatalysts. Overall, this review provides evidence-based guidance for researchers and practitioners seeking to advance wastewater treatment technologies by integrating supervised machine learning with photocatalysis.

1. Introduction

Artificial intelligence (AI) is transforming the modern world through its unmatched capabilities in analytical forecasting, optimization, and data-driven decision-making [1]. Its capacity to tackle complex worldwide issues is especially noticeable in the area of ecological sustainability [2,3]. Among these challenges, wastewater treatment and management stand out as vital objectives. Innovative and practical solutions are urgently needed to safeguard water resources from the increasing demands of industrialization, population growth, and climate change. AI has emerged as a powerful tool in both technology and environmental science [2,4,5]. The use of AI to optimize and enhance the performance of several wastewater treatment procedures, such as photocatalysis, has grown in recent years [6]. Machine learning algorithms and deep learning models are examples of AI-based models that have been utilized to predict and improve the photocatalytic degradation of pollutants, as well as to determine the best operating parameters [7]. Several AI models, such as support vector machines, decision trees, random forests, and neural networks, have been applied in the field of photocatalysis [8]. These models are trained on extensive experimental datasets and are capable of accurately predicting the performance of photocatalytic systems under varying operational conditions. The integration of AI with photocatalysis holds significant promise for revolutionizing wastewater treatment by enabling the design of more effective, efficient, and environmentally sustainable treatment strategies [9]. AI can lower energy usage, enhance treatment results, and optimize the design and operation of photocatalytic systems. AI may also be used to forecast the performance of novel photocatalytic materials and processes under various operating situations. Overall, the application of AI in photocatalysis is expected to revolutionize wastewater treatment and facilitates the development of more efficient and sustainable methods [10,11].
Water is one of the most vital resources for sustaining life on Earth. However, various human activities have significantly contributed to environmental degradation. The discharge of untreated or inadequately treated wastewater introduces a wide range of contaminants into natural water bodies, posing serious threats to both ecological balance and human health worldwide [12,13]. In response, integrated wastewater management has emerged as a sustainable solution, especially in ecologically sensitive regions. For example, studies conducted in the Andean páramo communities highlight the effectiveness of decentralized, nature-based treatment systems in preserving environmental integrity and promoting sustainable development [14]. To minimize environmental pollution and safeguard public health [15], it is important to learn the origins, composition, and efficient treatment techniques of wastewater. Increasing levels of urbanization, industrialization [16], and human activity have led to wastewater becoming a major global issue [17]. Pathogens in wastewater can cause waterborne illnesses like gastroenteritis, typhoid, and cholera, especially in communities lacking access to safe drinking water and sanitation [18]. Many other types of contaminants can be found in wastewater, such as microplastics, heavy metals, pathogens (viruses, bacteria), nutrients (phosphorus, nitrogen), and organic substances (pesticides, medications). Ecosystems and human health are at particular risk from each of these contaminants [19].
Wastewater treatment involves several sequential processes designed to remove contaminants and pollutants from wastewater before it is safely discharged back into the environment. These processes typically include physical, chemical, biological, and electrochemical treatment [20,21,22]. Primary sedimentation tanks operate by allowing gravity to separate solid materials from wastewater, resulting in the formation of sludge at the bottom and scum at the surface. Following this, biological treatment processes, such as activated sludge systems, trickling filters, and sequencing batch reactors, employ microorganisms to decompose organic matter into carbon dioxide, water, and biomass. Electrochemical techniques such as electrooxidation and electrocoagulation can provide environmentally suitable chemical-free wastewater treatment. They are efficient against persistent pollutants, dyes, and heavy metals while producing minimal sludge [20]. Disinfection methods such as chlorination, ultraviolet irradiation, ozone treatment, or a combination of these are then applied to ensure microbiological safety before discharge [23]. By increasing energy efficiency and pollutant removal, recent advancements in membrane technologies have enhanced wastewater treatment. Cutting-edge materials like nanotechnology and graphene oxide improve durability and lessen fouling. Superior performance is demonstrated by hybrid membrane systems that combine biological or photocatalytic processes. For real-world applications, scalability, cost, and long-term stability continue to be major obstacles [24].
The recently developed method of photocatalytic degradation presents a promising technological solution for wastewater treatment. Semiconductors are widely employed as photocatalysts due to their exceptional material properties. These include a high refractive index, strong UV absorption, excellent incident photoelectric conversion efficiency, and a favorable dielectric constant. Additionally, their outstanding photocatalytic activity, photostability, chemical stability, long-term corrosion resistance, and non-toxic nature make them ideal candidates for converting solar energy into chemical energy [25,26]. Photocatalysis, an advanced oxidation process, has garnered significant attention in wastewater treatment due to its ability to effectively degrade a wide range of organic contaminants [27]. To produce reactive species that can degrade pollutants, this technique uses photocatalysts, which are usually metal oxides like CdS, ZrO, TiO2, and ZnO that are activated by light [28]. Despite their potential, conventional photocatalysts are constrained by issues such as electron–hole recombination and large band gaps. Recent research has focused on improving photocatalytic performance through various strategies, including doping and the development of new materials [29,30].
This review article presents a comprehensive overview of recent advances and emerging trends in photocatalysis research. It highlights the integration of AI models, particularly supervised learning techniques, for predicting photocatalytic performance and assessing the influence of various operational parameters. The review also synthesizes the current literature on AI-driven methodologies for the degradation of diverse environmental contaminants. In addition, it critically evaluates key challenges hindering the commercial scalability of photocatalytic systems, including catalyst stability, economic viability, and regulatory barriers. Finally, the article offers forward-looking perspectives aimed at guiding the future development and practical implementation of AI-assisted photocatalytic technologies.

2. Photocatalysis Mechanisms and Dynamics

Photocatalysis refers to a chemical reaction initiated by the absorption of light by one or more reactive species. Catalysts such as CeO2, ZnO, CuO, Mn3O4, TiO2, Fe2O3, SnO2, WO3, SiO2/TiO2, ZnO/TiO2, and MgO/ZnO have been employed under UV or visible light to facilitate the photocatalytic degradation of pollutants [31,32]. Semiconductor materials are commonly used as sensitizers in light-induced redox reactions due to their electronic structure, characterized by a filled valence band and an empty conduction band [33,34]. Figure 1 illustrates the photocatalytic mechanism and the process through which the catalyst removes contaminants from wastewater. When the energy of incident photons equals or exceeds the band gap of the photocatalyst, the material absorbs light, exciting electrons from the valence band to the conduction band and generating electron–hole pairs. The separation of these charge carriers is essential to prevent recombination. This separation can occur through interaction with adsorbed reactants or via surface processes on the catalyst. The photogenerated holes in the valence band oxidize adsorbed water molecules, producing highly reactive hydroxyl radicals, while the excited electrons in the conduction band reduce dissolved oxygen into superoxide radicals [35,36,37,38,39,40,41]. After that, these reactive oxygen species (ROS) take part in a sequence of oxidation and reduction reactions that break down a variety of pollutants, such as organic compounds, heavy metals, dyes, biological contaminants, and pharmaceutical residues. Figure 2 illustrates the process by which contaminants are adsorbed onto the surface and then broken down by superoxide and hydroxyl radicals [39,42,43]. Despite being reusable over several cycles and not being consumed in the reaction, photocatalysts may lose some of their effectiveness over time due to sintering, agglomeration, or surface fouling.

3. Operational Parameters Effects on Artificial Intelligence-Driven Photocatalysis

The main factors affecting photocatalytic efficiency and their function in AI-based prediction models are depicted in Figure 3. The effectiveness of the photocatalytic process is significantly influenced by several variables, including the characteristics of the photocatalyst, the types of contaminants present, chemical additives, reactant concentration, catalyst dosage, temperature, light intensity and wavelength, and pH [44,45,46,47]. To forecast and maximize photocatalytic performance, these variables are crucial input parameters for evaluating and training the AI model. These parameters are commonly used as input features in AI-based models to predict photocatalytic degradation efficiency. Once processed by supervised learning algorithms, the models output predicted degradation efficiencies and identify optimal conditions for enhanced performance. The integration of such variables into AI frameworks allows for accurate modeling and optimization of photocatalytic processes in wastewater treatment applications [41,48,49]. To estimate the effectiveness of photocatalytic dye degradation, four machine learning models, Ensemble Learning Tree (ELT), GPR, SVM, and DT, were used in conjunction with GA and particle PSO. With an RMSE of 2.6410 × 10−4 and an R2 value of 0.992, the ELT-PSO hybrid model outperformed DT, GPR, and SVM by far, being the most accurate of these. The most important elements influencing degradation were dye type, bandgap, initial dye concentration, solution volume, and reaction time, according to an investigation of parameter influence using partial dependence graphs, Shapley analysis, and sensitivity testing [50]. To predict the photocatalytic degradation of Rhodamine B using ZnO doped with 19 elements, eleven machine learning models were evaluated; CatBoost achieved the highest accuracy (R2 = 0.96, RMSE = 0.0579). The most important factors were determined to be reaction time, dopant type, calcination temperature, and light wavelength since they directly affect charge transfer, crystallinity, and photon absorption. Reaction circumstances accounted for the greatest portion (70.7%), followed by catalyst characteristics (22.1%) and preparation conditions (7.2%) [51].

3.1. pH

The pH significantly influences photocatalytic processes, affecting both the efficiency of photocatalysts and the degradation rates of organic compounds, and is therefore commonly included as an input in AI models [52]. Degradation rates can be affected by pH variations because they can change the way organic molecules adsorb onto the photocatalyst surfaces [53]. Marfur and his colleagues demonstrated that pH plays a crucial role in the degradation efficiency of 2,4-dichlorophenol using Cu-ZnO and Ag-ZnO photocatalysts, with both showing optimal performance in acidic conditions, particularly at pH 3 [54]. The photocatalytic activity of cerium oxide nanoparticles (CeO2) is also strongly influenced by the pH of the synthesis medium. Studies have shown that CeO2 synthesized at pH 8 exhibits the highest photocatalytic activity [55]. Similarly, the efficiency of dye degradation using iron oxide nanoparticles is strongly pH-dependent. For example, rhodamine B (RhB) degrades most effectively at neutral pH (6.5), while brilliant green (BG) shows maximum degradation at pH 9. In contrast, methyl red (MR) and indigo carmine (IC) degrade most efficiently under acidic conditions, specifically at pH 3. A lower pH environment reduces the interaction between the photocatalyst and positively charged dyes like RhB due to increased H+ concentration. Conversely, higher pH levels can negatively affect the degradation of dyes like IC due to unfavorable charge interactions [56].

3.2. Light Intensity and Wavelength

The rate of photocatalysis in certain materials is strongly affected by variations in light intensity. In AI-based predictive models, light intensity and wavelength are often used as key input parameters to determine optimal conditions for maximum photocatalytic performance. Research has shown that the photocatalytic rate constant generally increases with higher energy flux density. For instance, under intensified UV irradiation, the rate constant may rise from 0.038 to 0.055 h−1, reflecting improved performance up to a certain point [57]. However, this relationship is not always linear, as some materials exhibit saturation thresholds beyond which additional increases in light intensity yield no further improvement. In specific cases, photocatalytic response is highly dependent on both the wavelength and intensity of light. For example, in the photocatalytic reduction of formic acid using graphene oxide, a high-intensity red wavelength triggered the fastest initial reaction rate, while maximum conversion was achieved under a low-intensity white light source [58]. Similarly, the photocatalytic activity of TiO2 nanostructures was shown to be strongly influenced by light intensity, with additional interactions noted between light intensity and the stirring rate, indicating complex dependencies [59]. According to Khataee and coworkers’ study, UV light plays a critical role in photocatalytic dye degradation. Their study on C.I. Basic Red 46 (BR46) revealed that the decolorization rate increased with higher UV light intensity. This enhancement was attributed to greater photon absorption by TiO2, which facilitated the generation of more electron–hole pairs and hydroxyl radicals, thereby accelerating the dye removal process [60].

3.3. Temperature

The rate of photocatalysis is significantly influenced by temperature. The photocatalytic activity of TiO2-based catalysts with various cocatalysts was strongly influenced by the reaction temperature. While Pd/TiO2 was more effective at higher temperatures up to 50 °C, after which its efficiency fell, Cu/TiO2 demonstrated higher activity at lower temperatures, such as room temperature [61]. The impact of heat on photocatalysis showed that, when the room temperature rises to 75 or 90 °C, semiconductor photocatalysts such as TiO2 experience a modification in their band structure. This resulted in an alteration in the action spectrum towards lower energy levels, which allowed for the photocatalytic reaction to utilize a greater number of incident photons. These datasets were used in the modeling of an AI model design for prediction [62].

3.4. Number of Catalysts

The rate at which photocatalysis occurs is largely dependent on the catalyst quantity. According to a study, increasing the catalyst concentration could speed up the reaction. In this condition, a low concentration of catalyst (0.4 g/L) increased the reaction rate up to 50% by making the wall reflectivity reach 98% [63]. Furthermore, the addition of tungsten to TiO2 catalysts demonstrated increased photocatalytic activity with each cycle, increasing the rate by 1.7 times after the first cycle and 3.1 times after the second [64].

3.5. Concentration of Reactants

Reactant concentration is a key factor that affects the speed of photocatalysis. When employing a Pt/Ni(OH)2/CdZnS photocatalyst for photocatalytic hydrogen generation, the reaction rate was dependent on the amounts of sodium hydroxide and ethanol in different data point sets, as varied by changing the concentration, and an AI model was used to determine the optimal performance [65]. Furthermore, in the context of a photoreactor using titanium dioxide as a photocatalyst, it was found that varying the catalyst concentration and wall reflectivity can significantly increase the reaction rate, with a 50% increase observed at low catalyst concentrations and high wall reflectivity levels [63]. Moreover, the use of an ion-concentration-polarization-assisted photocatalytic reactor demonstrated that altering the electric field through concentration polarization could lead to an 85.5% increase in the reaction rate, showcasing the impact of reactant concentration on photocatalytic efficiency [66].

3.6. Chemical Additives

The incorporation of chemical additives (doping) significantly influences the photocatalytic performance of materials like TiO2. Various studies have highlighted the impact of additives on photocatalytic reactions. For instance, the presence of BaSO4 in TiO2-based materials enhanced photocatalytic activity by scattering UV light, leading to high photonic efficiencies [67]. The incorporation of both organic and inorganic additives could highlight the complex and variable impacts of additives on the overall photocatalytic process by either promoting or restricting the photocatalytic efficiency of particular pollutants [68].

3.7. Contaminants

The effectiveness of photocatalytic degradation was impacted by the presence of contaminants such as acetylsalicylic acid, ethinyl estradiol, ibuprofen, and paracetamol. It has been demonstrated that non-calcined Nb2O5 catalysts have better activity in reducing these new pollutants [69]. The interaction of pollutants with photocatalysts such as TiO2 in visible light initiated the photocatalytic destruction of bacteria, showing how visible light absorption by pollutants plays a critical role in enhancing photocatalysis [70].

3.8. Properties of Photocatalysts

Materials used in photocatalysis are essential to the effectiveness of photocatalysis procedures. AI has been used in a selection of suitable materials for maximum efficiency in photocatalysis. Studies have indicated that the structure and composition have a big influence on how well they work. A photocatalysis material consisting of titanium dioxide, cerium dioxide, and an outer layer of silver exhibited antibacterial properties [71]. The photocatalytic activity of a photocatalyst was largely dependent on its surface area. Lukic et al.’s study discovered that the β-Ga2O3 nanoparticles’ specific surface area, which was obtained using chemical vapor synthesis, affected their photocatalytic efficacy in both overall water splitting (OWS) and aqueous methanol reforming [72]. Transition metal oxides like ZnO, TiO2, WOx, Nb2O5, and CeO2 are commonly used as photocatalysts, with composites like ZnO–ceria and titania–tungsten oxide showing enhanced photoactivity due to smaller crystallite size and increased surface area [73]. A photocatalyst’s structure and morphology were important factors in determining how active it is. Variations in the surfaces and morphologies of crystals may have a significant effect on the effectiveness of photocatalysis [74,75].

4. Shaping the Future of Photocatalytic Materials

Doping, the process of introducing impurities to enhance a material’s properties, is a key to optimizing photocatalyst performance. AI has revolutionized this field by enabling more efficient and innovative approaches to photocatalyst design and optimization [76,77]. Several doping techniques were investigated to improve the photocatalytic abilities of various substances. Doping is utilized in photocatalysts to improve band gap engineering [78], surface properties [79], charge separation [80], and light absorption [81]. The types of doping used in photocatalysis include the following: co-doping, which involves combining non-metal and metal dopants [82]; interstitial doping [83]; surface doping [46]; non-metal doping with carbon, nitrogen, or sulfur doping [84]; and metal doping with transition metal and rare earth metal doping [85]. Studies have revealed that incorporating transition metals and nonmetals into TiO2 can greatly improve its band gap, including carrying capacity and light absorption [86]. ML was employed to predict the energy band gap of doped ZnO at various doping concentrations. Among the models tested, GPR achieved the highest accuracy (CC = 98.97%, RMSE = 0.0022, MAE = 0.0020), outperforming SVM and RF. These results demonstrate that GPR is highly effective for capturing the influence of doping on ZnO properties, emphasizing the role of model selection in designing functional photocatalytic materials for energy applications [87]. This study developed copper-doped TiO2 (Cu–TiO2) nanoparticles for cetirizine hydrochloride (CTZ-H) degradation. The best performance, 93% removal, was obtained with 0.5 wt% Cu–TiO2 at pH 4.9, 100 mg/L catalyst, and 10 mg/L pollutant concentration. Among predictive models, the SVM optimized with the Improved Grey Wolf Optimizer (IGWO) showed the highest accuracy, R2 = 0.9999. Degradation efficiency was mainly influenced by copper loading, solution pH, catalyst dosage, and initial pollutant concentration [88]. Research shows that by combining green-synthesized ZnO with Ni-doped ZnO photocatalysts, machine learning can be used to predict the hazardous pollutant (PRM) degradation efficiency. While linear models such as Ridge regression demonstrated less flexibility, Gradient Boosting and XGBoost optimized with GridSearchCV achieved the best performance among the models under investigation R2 > 0.99, low MSE/MAE) [89]. The integration of AI, particularly ANNs, allows for efficient modeling and prediction of photocatalytic performance, significantly improving the treatment of various pollutants. Figure 4 compares the degradation efficiency of methylene blue using different AI models combined with various dopants in photocatalytic wastewater treatment. The data highlights the influence of AI-driven optimization and dopant selection on the degradation process. Table 1 shows the dopants used in methylene blue degradation for AI-based photocatalytic efficiency prediction.

5. Research Methodology

This review adopts a structured, innovation-driven approach to explore the growing integration of AI in optimizing photocatalytic wastewater treatment processes. As photocatalytic systems become increasingly complex and multi-variable, AI offers powerful capabilities in modeling, prediction, and data-driven decision-making to enhance pollutant degradation efficiency. To ensure comprehensive and reproducible findings, a four-phase systematic review protocol, comprising planning, searching, screening, and reporting, was implemented by PRISMA guidelines [95,96]. During the planning phase, the scope was refined to focus exclusively on AI-powered optimization strategies, such as support vector machines, deep learning, artificial neural networks, and hybrid ensemble models, applied in both simulated and experimental photocatalytic degradation studies. Particular emphasis was placed on identifying research utilizing AI models to address key aspects such as reaction kinetics, catalyst selection, light intensity optimization, and parameter sensitivity analysis.
A comprehensive literature search was conducted to identify relevant studies on the application of artificial intelligence (AI) in photocatalytic wastewater treatment. Three large databases were searched: Google Scholar (n = 1590), PubMed (n = 13), and ScienceDirect (n = 599), using the combined search terms “artificial intelligence” photocatalysis “wastewater treatment.” The search on Google Scholar returned far more records compared to the other databases. This aspect can be explained by the fact that it has broad indexing capability, including journals, conference proceedings, theses, and non-traditional scholarly output. In contrast, PubMed and ScienceDirect index only peer-reviewed biomedical and scientific literature. Following the consolidation of all the records (n = 2202), the cases of duplication were identified and then removed (n = 600), leaving 1602 unique articles. The remaining studies were screened using titles and abstracts, and those not relevant to the AI-based photocatalysis of wastewater treatment were discarded. Additionally, studies written in a language other than English, non-peer-reviewed articles, book chapters, editorial articles, and articles with inaccessible full texts were discarded. The inclusion criteria were specifically aimed at studies employing the use of artificial intelligence or machine learning models to optimize, predict, or improve photocatalytic processes in wastewater treatment. Experimental studies and computational modeling articles were both eligible, as long as they reported quantifiable results like degradation efficiency, optimization parameters, or mechanistic understanding. Following a stringent selection process, 230 articles were found to be eligible and were considered for the final appraisal. The stepwise screening and selection process is evident from the PRISMA diagram in Figure 5, which provides a stepwise summary of identification phases, screening, eligibility assessment, and inclusion.

5.1. Artificial Intelligence Models in Photocatalysis

AI is essential for improving photocatalysis reaction efficiency because it helps with catalyst design, performance prediction, and reaction optimization. Research has shown that AI algorithms have been used to design photocatalysts, forecast their performance, and optimize reaction conditions, all of which can save development time and costs while increasing efficiency [46,91,97]. Photocatalysis aided by AI has great potential for some industrial uses, especially in wastewater treatment and environmental purification procedures. Photocatalysts were designed and their efficacy was predicted with high accuracy through the use of intelligent algorithms, which reduced development time and costs [46]. The three categories of AI methods based on learning approaches (supervised, unsupervised, and reinforcement learning), application types (predictive modeling, optimization, and classification), and specific purposes (real-time monitoring and sensor fusion) have been developed in Figure 6. Each branch highlights commonly used techniques, showcasing the versatility and scope of AI in enhancing wastewater treatment processes. Optimization of photocatalytic processes using AI models can enhance the degradation of pollutants like MB and 2,6-dichlorophenol, resulting in cost-effective and sustainable treatment solutions [26,77].
In supervised learning (SL), a branch of algorithmic learning, models are trained on labeled datasets in order to categorize or predict data. This method is used in the field of photocatalysis to find active sites, forecast the efficiency of photocatalysts, and optimize material characteristics for particular reactions [76]. Unsupervised learning (UNSL) techniques use no previous classifications to find patterns and connections in data. Patterns in complicated datasets associated with pollutant degradation can be identified with this technique. Unsupervised learning enhances guided machine learning by offering perspectives that labeled data might not be able to provide. Reinforcement learning (RL), which provides creative ways to maximize treatment plans and boost productivity, is being included in water treatment procedures more and more. These technologies are used in many different areas of water treatment, such as improved control mechanisms for wastewater treatment and decision support systems (DSS) for drinking water treatment facilities. Furthermore, the possibility of using semiconductor photocatalysis to remediate water contaminants has been studied [98,99]. The advancement of photocatalysis has been significantly supported by AI, particularly in the design and performance prediction of photocatalytic materials. Various AI models have been applied in the context of environmental pollution treatment, aiming to enhance the efficiency and accuracy of photocatalytic processes. Among these, artificial neural networks (ANNs) and attention-based deep learning models, such as PhotoCat, have demonstrated notable success in accurately predicting photocatalytic reactions. These approaches, along with other AI techniques, offer powerful tools for modeling complex reaction pathways, optimizing operational parameters, and accelerating the development of next-generation photocatalysts [46,83]. Reinforcement learning, unsupervised learning, and supervised learning comprise the majority of AI models. Support vector machines, artificial neural networks, random forests, decision trees, gradient boosting, and XG Boost are all components of supervised learning [100,101].

5.2. Support Vector Machines

A powerful class of supervised machine learning algorithms, support vector machines (SVMs) are primarily used for tasks involving regression and classification [102]. They are valuable tools for enhancing the decolorization process in wastewater treatment applications that have handled both linearly separable and non-separable cases, resulting in accurate estimations. SVMs were used to effectively analyze process operational conditions, molecular properties, and catalytic properties of compounds under study in practical photocatalysis applications by minimizing abstract mathematical theories and providing concrete numerical data [103,104,105]. SVM emerged as a powerful tool in photocatalysis, particularly in predicting the efficiency of photocatalytic processes. Its ability to analyze and forecast pollutant degradation in photocatalytic processes was employed to forecast the breakdown of the pharmaceutically active compounds diclofenac, caffeine, ibuprofen, and organic dyes, as well as heavy metals in water [105,106]. Biochar–ZnO nanocomposites were developed and employed as photocatalysts to degrade atrazine (93%) and 2,4-D (90%) in 90 min. Several operational factors were tuned to verify their efficacy. SVM, RF, and ANN are examples of machine learning models that were used to predict deterioration performance. Of all of them, SVM was the most accurate (R2 = 0.95, RMSE = 4.93, MAE = 4.38) [107]. SVMs are an area of machine learning algorithms that apply kernel functions to translate data into higher-dimensional feature spaces [108]. SVMs, as part of machine learning frameworks, can analyze large datasets to identify patterns and relationships among variables, leading to more reliable predictions of photocatalytic performance [109]. A functioning principle of support vector machines (SVMs) is shown in Figure 7. A hyperplane is built to efficiently classify several classes when dealing with linearly separable data. In situations when the dataset cannot be separated linearly, the data is projected into a higher-dimensional space using kernel functions, which allows for the construction of an appropriate hyperplane. SVM aims to find the optimal hyperplane that separates data points from different classes in a feature space. The hyperplane has been defined by Equation (3).
WTx + b = 0
In Equation (1), x is the input feature vector that represents the properties of the photocatalytic material and reaction conditions, and b is the bias term that modifies the position of the hyperplane. W is the weight vector that defines the orientation of the hyperplane, and WT is the sum of all weighted vectors used in the hyperplane [110,111]. The WTx + b > 0 is classified as a positive class, the data point is classified into one category (e.g., high photocatalytic efficiency), or WTx + b < 0 is classified as a negative class; it belongs to another category (e.g., low photocatalytic efficiency). The goal of SVM is to maximize the margin between the closest support vectors of different classes. Maximizing this margin enhances the model’s robustness and generalization capabilities. The margin can be expressed as Equation (2). In Equation (3), optimal hyperplane is used to formulate the optimization problem. Once the optimization is solved, the decision function for a new point x is given in Equation (4) [109].
Margin = W 2
Minimize = 1 / 2 W 2
f(x) = sign (WTx + b)
SVM’s strength is its use of kernel functions to manage nonlinear interactions. SVM may project the original feature space onto a higher-dimensional space where linear separation is possible by using a kernel technique. For nonlinear data sets, common kernel functions include the linear kernel in Equation (5), the polynomial kernel in Equation (6), and the radial basis function kernel in Equation (7). Function approximation issues are resolved by SVM using a training set that is represented as pairs of instances, (Xi,Xj), where Xi and Xj are the input samples [102,112].
(xi,xj) = xiTxj
K(xi,xj) = (xiTxj + 1)d
K ( xi , xj ) = ( exp y x i x j 2 )

5.3. Artificial Neural Networks (ANNs)

Artificial neural networks (ANNs) are digital representations of the human brain that are made up of layers of interconnected nodes. They are made to identify trends and gain knowledge from information. The high prediction accuracy of the optimized ANN architecture suggests that it is effective in improving photocatalytic processes [113]. The ANN model is made up of an input layer that receives experimental features (such as catalyst dose and dye concentration), numerous hidden layers that perform nonlinear transformations using weighted connections and activation functions, and an output layer that predicts degradation efficiency. Bias nodes improve learning flexibility, while training changes weights to reduce errors. The study report used genetic algorithms in conjunction with ANNs to forecast and optimize dye photodegradation through nano ZnO-anchored glass fiber exposure to sun radiation [114]. In addition, ANNs were essential for forecasting photocatalytic process performance, which helped create effective environmental purification photocatalysts [46]. Researchers could improve the overall sustainability of photocatalysis processes for energy-efficient applications, anticipate degradation rates with high accuracy, and optimize process parameters by utilizing ANNs [115]. In Figure 8, the fundamental unit of an ANN was the artificial neuron, which had a single output, a weighted input, and a transfer function. Three layers make up a typical neural network architecture: input layers, which analyze information; one or more hidden layers, which carry out the majority of internal processing and are in charge of identifying patterns; and output layers, which produce and display the network’s final outputs as depicted [60,104,116]. Each neuron was activated by the weighted sum of its inputs. The activation signal then passes via a transfer function to produce a single output. The design, learning rule, and transfer function of a neural network determine its overall behavior [117]. ANNs were used for pollutant degradation forecasting in photocatalysis. ANNs offer effective modeling of nonlinear processes and reaction condition optimization in wastewater treatment [114,118]. They helped to remove pollutants from textile wastewater treatment by predicting the degradation efficiency of photocatalysts under different reaction situations [118], and they helped with the degradation of chlortoluron in wastewater using a continuous photocatalytic fixed-bed reactor using TiO2. A maximum removal effectiveness of 94% was achieved under optimal conditions. ANN performed somewhat better than SVM when machine learning models were utilized. Combining ANN with a multi-objective genetic algorithm yielded the optimal operating conditions by striking a balance between high degradation efficiency and low energy consumption [119]. The key objective of this study was to use graphene oxide-doped titanium dioxide (GO-TiO2) for the photocatalytic degradation of levofloxacin (LVX). The two modeling approaches that were employed were RSM and ANN. While RSM adjusted the process parameters and achieved approximately 80% degradation efficiency (R2 = 0.88), the ANN model showed superior predicted accuracy with R2 = 0.97. In comparison to RSM, these data show how effectively ANN predicts photocatalytic degradation performance [120]. ML was used to predict the photocatalytic effectiveness of g-C3N4/CdS/MoS2 nanocomposites, reducing the requirement for resource-intensive studies. Following the evaluation of four algorithms (RF, DT, SVM, and NN), NN had the greatest accuracy (R2 = 0.70, R2 ≈ 0.84, RMSE ≈ 4.2). Both models anticipated methylene blue (MB) degradation under 180 min of sunshine to be between 83 and 84%, which was quite similar to the experimental figure of 86%. The results demonstrate that by effectively capturing complex nonlinear photocatalytic action, RF and NN offer reliable prediction power [121]. The dual-functional PeN@Fe3O4 coupled with Cd2+ effectively degraded the antibiotic sulfamethoxazole. The ANN model used to forecast the removal of Cd2+ performed exceptionally well (R2 = 0.99975, MAE = 0.10906, MSE = 0.04399), suggesting great prediction accuracy and dependability. These results show PeN@Fe3O4 to be a sustainable and efficient technique for both organic pollutant degradation and heavy metal removal [122]. According to the study, rGO–SnS2 nanocomposites were synthesized and shown to improve photocatalytic degradation of atrazine (ATZ) and 2,4-D in the presence of natural sunshine, removing up to 91% and 87% of the compounds, respectively. SVM, ANN, and Gaussian Process (GP) predictive modeling showed that ANN performed better than the other models (R2 = 0.99, error = 0.002), offering a dependable tool for photocatalytic wastewater treatment optimization and scalability [123].

5.4. Diverse Architectures of Artificial Neural Networks (ANNs)

The neural networks that are most commonly used in wastewater treatment procedures are feed-forward and recurrent neural networks, and radial-based function [118].

5.4.1. Feed-Forward Neural Networks (FFNNs)

Feed-forward neural networks (FFNNs) are particularly effective at modeling complex, nonlinear relationships between multiple operational parameters and treatment efficiency in photocatalytic processes. By leveraging FFNNs, researchers can enhance predictive accuracy and optimize treatment conditions to improve pollutant degradation performance. FFNNs are a class of neural networks in which information flows in only one direction, from the input layer, through one or more hidden layers, to the output layer, without forming any cycles or feedback loops. This unidirectional propagation means that the network does not retain memory of past inputs, and its weights remain static once trained. Each neuron in an FFNN process weights inputs and passes them through an activation function, which can be linear, step-based, or nonlinear (such as sigmoid, ReLU, or tanh), depending on the modeling needs. FFNNs can be structured as single-layer networks (e.g., perceptrons) or as multi-layered architectures, such as multi-layer perceptrons (MLPs) or radial basis function networks (RBFNs). Their high controllability and robustness make FFNNs well-suited for handling noisy and complex datasets often encountered in environmental and wastewater treatment modeling [124,125]. The application of FFNNs in photocatalysis is one of the many sectors in which they have been thoroughly investigated. Studies on parametrizing radiative characteristics have shown that FFNNs could match complicated properties of mixtures with excellent accuracy [126]. Figure 9 shows the feed-forward neural network with various inputs (Xn) with weight (Wn) in the input layer, the number of the hidden layer (Hn), and the output layer (y) in the forward direction. Feed-forward neural networks (FFNNs) have been used to model complicated systems and forecast results based on input variables in a variety of scientific domains, including photocatalysis. The breakdown of water contaminants, including Niflumic acid (NFA), by photocatalysis has been modeled using FFNNs. In order to do this, neural networks are used instead of kinetic equations to forecast the rates of degradation depending on factors like substrate and catalyst concentrations [127]. To predict the photodegradation of phenolic compounds (PHCs) using black TiO2 under visible light, the feed-forward neural network (FFNN/ANN) was evaluated in conjunction with RF and ERT models. The FFNN performed worse than the ERT model, producing comparatively higher errors and lower R2 values, despite demonstrating an acceptable capacity for prediction. When it came to modeling the degradation of PHCs, the ERT model performed better than the FFNN, producing predictions that were more accurate and closely matched the experimental mean (73.35% vs. 72.79%) [128]. In this study, the photocatalytic degradation efficiency of boron-doped ZnO nanoparticles produced by a mechanochemical method was modeled and predicted using a single-layer feed-forward neural network (FFNN). A high coefficient of determination (R2 = 0.9810), which shows good agreement between experimental and anticipated findings, was attained by the ANN model, demonstrating its exceptional predictive capacity. In comparison to undoped ZnO, the improved photocatalyst, 1 weight percent B-ZnO calcined at 700 °C, obtained 99.94% methyl orange degradation under UVA light. FFNNs can guide the optimization of photocatalytic systems for wastewater treatment, as these data demonstrate [129].
Single-Layer Perceptron (SLP)
The Single-Layer Perceptron (SLP) is a foundational artificial intelligence model inspired by the way biological neurons process information. It produces outputs as a smooth, nonlinear function of the weighted sum of its inputs. Due to its simplicity and learning capabilities, the SLP has been applied across various fields for tasks involving statistical regression and binary classification [130]. In essence, an SLP employs linear logistic regression to perform binary classification tasks (e.g., 0 or 1 outcomes), making it one of the earliest models in the development of artificial neural networks. Despite its simplicity, it serves as a fundamental building block in neural network design, and ongoing research continues to enhance its training algorithms and broaden its applicability [131]. As illustrated in Figure 10, the single-layer feed-forward neural network (SLFFNN) consists of xₙ input neurons derived from experimental photocatalysis datasets. Each input is assigned a corresponding weight wₙ, which influences the computation process. The weighted inputs are passed through a nonlinear activation function f(x) to generate the final output y, representing the predicted photocatalytic efficiency and validating experimental results. Equation (8) represents this activation function, which governs the network’s response and output generation.
y = f(x)
y = i = 0 n X n W n + b
In Equation (9), the bias inputs are denoted by b, while the weights for the (Xn) connections are denoted by (Wn). The function f(x) exhibits a nonlinear excitation function behavior. The output of the model is expressed as in Equation (10) [132].
y = X1W1 + X2W2 + X3W3……XnWn + b
Multi-Layer Perceptron (MLP)
An artificial neural network with one or more hidden layers that can solve complicated issues using pattern recognition and function regression is called a multi-layer perceptron (MLP) [133,134]. The number of neurons in hidden layers and initial weights were two factors that affected the performance of MLPs. These factors could be improved using methods like hyperparameter optimization models using genetic algorithms and backpropagation [120]. Figure 11 illustrates the MLP neural network with multiple layers. Neural network theory has developed recently, showing that every multi-dimensional function can be accurately predicted with high accuracy using multi-layer feed-forward neural networks that include one hidden layer of neurons. In addition, a multi-layer identical feed backward model for ANNs was presented, along with simulation results and learning and recall techniques [135]. Many researchers have successfully used an MLPNN for a variety of purposes. Alsaffar et al.’s study, which used a multi-layer perceptron neural network to predict 1,2-dihydroxybenzene degradation in the setting of photocatalysis, revealed that the volume of the oxidant had a major impact on the degradation process [136]. The output of the neurons in the MLP is typically computed using Equation (11) as follows:
Y x ( n ) = i = o n f ( W n · Y n ) + b
where Yx(n) is the output of Xn input neurons in the nth layer. The Wn is the weight of input, yn number of hidden layers, b is the bias, and f is the activation function, which can vary based on the network design [118]. The study examined the use of a multi-layer perceptron neural network (MLPNN) trained with Bayesian regularization for the predictive modeling of photocatalytic phenol degradation from crude oil effluent. To train the MLPNN, 26 datasets created using the Box–Behnken experimental design were employed. The input variables were irradiation time, starting phenol concentration, photocatalyst dose, and solution pH, while the output layer included phenol degradation [137]. Lenzi and coworkers reported that reactive blue dye 5G can be degraded by photocatalysis using Fe/TiO2, Fe/ZnO, and Fe/TiO2–ZnO. The metallic charge, calcination temperature, and time discoloration were the input data for the MLPPNN model, while the discoloration magnitude was the output value. The model’s output was outstanding, demonstrating highly precise data catalysts such as TiO2/Fe [138].

5.4.2. Radial Basis Function (RBF)

The input layer, hidden layer, and output layer that make up an RBF network’s structure have immediate resemblances with those of MLPs, but RBFs usually have only one hidden layer and convert the input space into a higher-dimensional space with the help of a Gaussian function [139]. Radial basis functions (RBFs) have been widely applied in several domains, demonstrating their effectiveness in tasks including particle coagulation evolution, neural network training, and differential equation solution [140]. Through the use of RBFs’ distinct features, scientists could be able to create fresh ideas for photocatalysis procedures, taking advantage of the flexibility and computing power that RBF approaches provide in a variety of fields [141,142]. The Gaussian function (activation function) is indicated by the following Equation (12):
O j ( X )   =   exp _ | | X j _ C j | | j
where Cj and ∞j are the center width and the peak width, respectively [143]. The input nodes in the first layer send unweighted inputs to each node in the hidden layer, and each hidden node has an RBF as the transfer function. The outputs of these nodes are then weighted and added together to create the final output, and the output nodes that calculate the weighted sum of the outputs from the hidden nodes are in Equation (13).
Y I   = I = 1 n W j i O j ( x )
where wji represents the weights of the connection between the hidden layer, i, and output layer, j, and Oj(x) is obtained from above [144]. RBF architecture is shown in Figure 12, which contains an input layer that is processed through a single hidden layer with a Gaussian as an activation function and gives output. The input layer, hidden layer, and output layer are the three primary layers that make up the network. The input layer, which is displayed on the left, is made up of nodes with the labels I1, I2, I3, and In. Each represents a feature or variable from the input data. Without carrying out any calculations, these nodes are used to send raw data into the network. The network may learn intricate patterns and representations from the input data due to the hidden layer. The output layer, which has nodes with labels, receives the signals after they have been processed. The task at hand determines how many nodes this layer contains [145].
Dashti and coworkers demonstrated the photodegradation of pesticides by ZnO-based photocatalysts for water treatment by different AI models. The input parameters included light source, dopant mass ratio, pesticide concentration, solution pH, catalyst dose, and irradiation duration, while considering physicochemical characteristics like molecular weight and water solubility. Compared to other models, RBF had the highest modeling accuracy, with an average absolute relative deviation (AARD) of 4.80% and the highest determination coefficient R2 = 0.978 [11].

5.4.3. Recurrent Neural Networks (RNNs)

RNNs contain a feedback loop that returns data to the hidden layer, unlike feed-forward neural networks (FFNNs), which have a one-way data flow (from input to output through hidden layers). This loop produces a time lag effect, which helps the RNNs in remembering previous time steps. RNNs are a type of deep learning architecture that is designed to handle sequential or time-series data. Unlike feed-forward networks, RNNs have internal memory that allows them to retain information from previous inputs, capturing time-dependent relationships in the data [146]. This property makes RNNs ideal for modeling dynamic processes like pollutant degradation, where photocatalysis effectiveness can fluctuate over time due to changing environmental conditions, catalyst behaviors, or contaminant concentration. RNNs improve prediction accuracy in complicated, time-dependent degradation systems by taking into account both current and historical input sets. RNNs are widely used in a variety of sectors, one of which is photocatalysis. RNNs are used in the wastewater treatment context to predict how effectively photocatalysts will degrade in terms of removing contaminants from textile waste [118]. RNNs were able to keep up context over time by keeping track of information about past inputs in a hidden state. All things considered, RNNs are essential for process optimization, result prediction, and efficiency enhancement in a wide range of applications, such as spectroscopic analysis and photocatalysis [147]. Furthermore, RNNs were effective in predicting the electromagnetic spectrum evolution of pulses in nonlinear periodically poled waveguides, showing excellent agreement with previous numerical models and providing flexibility in the analysis of optical pulse propagation [148]. The study shows that biochar made from tea waste is a low-cost, efficient adsorbent for the simultaneous removal of aromatic compounds, dyes, and agrochemicals from wastewater. Overall elimination efficiency for combined pollutants was 82.66% under ideal conditions (5 mg mL−1 dose, pH 2, 60 min). When RNN and CatBoost machine learning models were used to forecast removal performance, RNNs demonstrated higher accuracy, with R2 = 0.960 [149]. An RNN’s structure, comprising an input layer, hidden layers, and an output layer, is depicted in Figure 13. RNNs, in contrast to simple neural networks, feature feedback connections that help them store information from earlier stages. The RNN receives an input that updates its hidden state ht based on the previous hidden state ht- and the current input. Mathematically, this can be represented in Equation (14).
ht = σ(Whht − 1 + Wxxt + b)
where ht is the hidden state, and xt is the input at time step t. The Wh and Wx are weight matrices, b is a bias term, and σ\sigma σ is an activation function. The output of each layer can be calculated by Equation (15).
yt = g(wyht + c)
where yt is the output at time step t, wy is a weight matrix for the output layer, is the output bias, ht is the hidden state and g is often softmax for classification tasks [150]. Long short-term memory (LSTM) networks are a complex variation of ordinary RNNs that were created to address their shortcomings, especially the vanishing and ballooning gradient issues in lengthy sequences. The memory cell and gating mechanisms (input gate, forget gate, and output gate) that LSTMs have enable them to selectively store, update, or discard data over time steps [137]. Because of their ability to better represent long-term dependencies than conventional RNNs, LSTMs are a preferred option for time-series prediction tasks in photocatalysis and other fields [151,152].

5.5. Tree-Based Models

The efficiency of combining decision trees, XGBoost, random forests, and gradient boosting in machine learning for classification and prediction problems has been thoroughly investigated. These algorithms are particularly known for their versatility and robustness across a wide range of data domains, including photocatalysis [153]. The input for these models is used for predicting the effect. While random forests and gradient boosting improve performance through collective approaches, decision trees make up the basis of the model. These models help identify key variables influencing degradation, such as light irradiation time and catalyst type, which are crucial for enhancing photocatalytic efficiency [154]. Rhodamine-B photocatalytic degradation efficiency employing TiO2 catalysts is predicted using a machine learning model. The efficacy of XGBoost and other models, such as random forest and gradient boosting decision tree, was confirmed by validation against a variety of composite catalysts [135,155]. Decision trees are straightforward yet effective models for issues involving regression and classification. Although they are simple to understand, they may overfit, particularly when dealing with complicated data [156]. Combining the predictions of several trees, random forests, and a combination of decision trees reduces overfitting and enhances durability and generalization. Gradient boosting creates models one after the other, fixing the errors of the models that came before it. This approach enhances the model’s precision and transparency. XGBoost is a robust gradient-boosting solution that is renowned for its effectiveness and speed. It can handle big datasets well because of a complex algorithm, which makes it appropriate for data with high dimensions, like those seen in photocatalysis [157,158,159]. Apart from conventional ensemble techniques, Extreme Gradient Boosting (XGB) has been acknowledged as a scalable and extremely effective gradient boosting solution, widely used in a variety of prediction tasks [160]. In Figure 14, the effectiveness of pollutant removal from wastewater may be predicted using tree-based models, including decision trees, random forests, XGBoost, and gradient boosting models. Every model removes the bias in prediction before it occurs due to efficiency in its design. Parameters including pH, temperature, catalyst dose, pollutant concentration, and irradiation time are frequently included as input variables for these models. The output variable is the pollutant’s expected removal efficiency, which may be expressed as a percentage removal or residual concentration. Through the examination of the connections between these input variables and the output variable, these models can offer important information about the ideal operating parameters for effective pollutant removal in wastewater treatment [153,161]. The degrading efficiency of ketoconazole (KTC) was predicted using a variety of machine learning models, such as SVM, ANN, and tree-based techniques. With R2 values of 0.992–0.998 and low RMSE and MAE scores, GBR outperformed the others, demonstrating its higher predictive accuracy. Reaction time was shown to be the most significant element, and GBR’s outstanding performance is ascribed to its capacity to capture intricate nonlinear interactions between parameters, including catalyst dosage, pH, and reaction time [162].

5.6. AI Model Development and Benchmarking in Photocatalytic Treatment

The effective use of AI in wastewater treatment is largely dependent on careful model design, which includes the development of features, data selection, model architecture, and assessment techniques. A comprehensive dataset has been compiled, incorporating experimental data points from literature sources, along with extensive datasets obtained from experiments and published studies, to provide data for AI models as input for prediction and optimization of parameters [53,135]. The dataset needs to be preprocessed and cleaned before any AI model is trained. To guarantee data quality, preprocessing procedures are essential and include resolving missing values, encoding categorical variables, normalizing numerical characteristics, and eliminating outliers. To improve statistical reliability, the preprocessed dataset is then divided into training, validation, and testing subsets, usually in a 70:15:15 [163] ratio, or put through k-fold cross-validation. Using hyperparameter optimization methods like Grid Search or Random Search, models are refined after being trained on the training set. In order to choose a suitable AI model, important hyperparameters like the spread factor and the maximum number of neurons had to be systematically adjusted. These adjustments were essential for improving the predicted accuracy of the model [11]. In order to optimize photocatalyst discovery and utilization, selecting software for AI-driven photocatalysis requires integrating machine-learning models with decision-making frameworks. Techniques for software selection ensure that the tools chosen meet the specific needs of the research. Python-based program, Origin Lab, Neuro Selection, Java Pro, and R statistical tools are among the most often used programs based on model prediction. The most popular software and Python libraries for creating AI models that optimize for experimental factors influencing the photocatalysis mechanism are displayed in Table 2 and Table 3 [164,165]. The process for using AI in photocatalysis is shown in Figure 15. Data collection, including database information, experimental investigations, and book reviews, is the first step in the process. A software design is created, and an appropriate AI model is chosen based on this data. In order to guarantee forecast accuracy and dependability, the model parameters are subsequently refined and contrasted with experimental parameters in an ongoing feedback loop.
When AI datasets are trained and analyzed with models that predict efficiency and are reasonably priced, experiments are avoided. These metrics provide information about the model’s durability and accuracy. A benchmarking table, which lists the datasets used, model types, input features, and performance metrics attained under uniform settings, is frequently provided in high-quality studies for a clear comparison [166]. A significant drawback of current AI-based photocatalytic wastewater treatment research is its omission of external validation, which is crucial to guaranteeing the model’s performance in practical settings. To address this, researchers should employ transfer learning strategies, conduct a sensitivity analysis to assess the model’s generalization ability, and incorporate external testing using separate datasets. Moreover, explainable artificial intelligence (XAI) techniques such as SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) can be used to determine which input features have the most impact on the predictions, hence improving the transparency and interpretability of AI models [167]. SHAP works well for elucidating AI models in scientific fields, fostering more transparency, understanding, and trust. The model’s output is decomposed into each input variable’s additive contribution. Each feature’s contribution to the prediction, relative to a baseline (average) value, is computed by SHAP. For instance, SHAP explains the proportion of a model’s predicted 80% dye degradation that can be attributed to factors like time, dye concentration, and catalyst amount [163,168]. The efficacy of the models was evaluated by contrasting their predicted values and fit with the experimental data. The outcome metrics for the training and prediction sets were the root mean square error (RMSE), sum of squares error (SSE), sum of absolute error (SAE), mean squared error (MSE), and coefficient of correlation (R2) [47,169]. Ahmed and coworkers described the use of an experimental dataset from the degradation of methylene blue (MB) in wastewater and applied various AI models to predict maximum degradation efficiency. The study utilized the Scikit-learn library in Python to build the models and evaluated their predictive performance using metrics such as R2, MSE, RMSE, MAE, and CV R2 [158]. More than a thousand tests were conducted to investigate the effectiveness of photocatalytic water purification, resulting in a substantial dataset. ANN demonstrated the highest prediction accuracy among the machine learning models used (R2 = 0.970, MAE = 2.70, MSE = 5.88). According to the SHAP study, the most important variables were the type of pollutant, its concentration, and the amount of catalyst used; the best catalyst was CuO/TiO2. Strong CuO–TiO2 interactions were validated by molecular dynamics simulations, confirming experimental results and pointing to a solid framework for sustained photocatalysis optimization [47].
Oviedo and coworkers reported algorithms such as neural network algorithms and Xtreme Gradient Boosting to create prediction models for photocatalytic deterioration. Using Spearman correlation, the link between the variables influencing RhB degradation was examined, providing information on catalyst and dye concentrations [170]. Sohrabi and coworkers reported gaining insight into the parameters influencing photocatalytic efficiency and, to enhance the design of photocatalysts, the study uses sensitivity analysis and machine learning. The prediction of deterioration efficiency was examined using a number of machine learning models, such as Polynomial Regression, support vector regression (SVR), XGBoost, random forest, gradient boosting, and artificial neural networks (ANNs). The ANN model outperformed the others, with a mean squared error (MSE) of 5.88, a mean absolute error (MAE) of 2.70, and a coefficient of determination (R2) of 0.970 [47].
R 2 = 1 ( y i ŷ i   ) ( y i ȳ )
M A E = 1 n | y i ŷ i |
R M S E = [ 1 n × ( y ŷ ) 2 ]
M S E = 1 n × ( y ŷ ) 2
C V   R 2 = 1 k × R 2 i

5.7. Hybrid AI Models

To improve the efficacy and efficiency of pollutant degradation, hybrid AI models are being included in photocatalysis for water treatment more and more. These models handle the complexity of water contaminants and treatment parameters by combining a variety of computational methodologies to optimize the photocatalytic processes [50,171,172]. Although supervised learning models like SVM, ANN, and tree-based algorithms are the main focus of this research, hybrid approaches are also becoming more popular due to their capacity to capture detailed nonlinear interactions. Among these, frameworks for the cascaded adaptive neuro-fuzzy inference system (ANFIS) are effective in environmental modeling. When dealing with nonlinear and multivariable datasets, ANFIS outperformed single-stage ANFIS in terms of prediction accuracy. The shown resilience of cascaded ANFIS in environmental systems underscores its potential as a future research avenue for combining hybrid AI with photocatalysis, even though its applications in photocatalytic wastewater treatment are limited [173]. Similar to this, hybrid deep learning algorithms that combine long short-term memory (LSTM) and artificial neural networks (ANNs) have been used to predict photocatalytic outcomes with remarkable accuracy (R2 > 0.99, RMSE < 0.03), indicating their potential to improve wastewater purification technologies and increase the efficiency of Se(IV) reduction [174]. In order to improve simulation robustness, improve capture degradation mechanisms, and optimize process parameters, the study builds on this by proposing a hybrid modeling approach for photocatalysis in advanced water treatment that integrates quantitative-structure activity/property relationships (QSAR/QSPR). The efficacy of photocatalytic systems is eventually increased by this integration, which also improves the predictive performance of photocatalytic models and offers mechanistic interpretability [175].

6. Innovative Catalysts for Effective Wastewater Purification

6.1. Titanium Dioxide (TiO2)

Photocatalysts such as TiO2 can facilitate photoreactions by enhancing the absorption of light by the reacting species. TiO2 is preferred because of its low prices, stability, and efficiency; various polymorphs, such as rutile, brookite, and anatase, have distinct characteristics. TiO2’s main drawback is its wide band gap, which limits its photocatalytic activity to ultraviolet light, which makes up a very small portion of the solar spectrum. The modifications of TiO2, such as changing the band gap and crystal size, can increase photocatalytic efficiency [86,176]. Environmental applications such as air filtration and solar energy conversion value TiO2 for its nontoxicity, affordability, and efficiency. Although anatase had a large band gap that limited light absorption, it was the favored polymorph due to its greater photocatalytic activity and durability. TiO2 could be made to absorb visible light more efficiently in a variety of applications by doping it with metals and nonmetals to modify the band gap [86]. Table 4 shows the Titanium dioxide (TiO2) used as a catalyst to degrade different pollutants using AI models.

6.2. Zinc Oxide (ZnO)

AI improves reaction results and synthesis conditions to greatly increase the efficiency of ZnO photocatalysis processes. AI demonstrates encouraging progress in improving the photocatalytic effectiveness of zinc oxide (ZnO) photocatalysts by adjusting their band gap, especially in visible light [187]. The improvement is important because ZnO’s large band gap naturally reduces its ability to absorb UV light, which restricts the material’s application in photocatalysis [188]. AI models, particularly ANNs and GA, have been pivotal in predicting optimal conditions for ZnO NP synthesis and photocatalytic processes [189]. Table 5 shows the Zinc oxide catalysts that degrade different pollutants using an AI model.

6.3. Cadmium Sulfide (CdS)

AI is increasingly being integrated into photocatalysis for wastewater treatment, particularly using CdS-based materials. Cadmium sulfide (CdS) photocatalytic activity is highly dependent on its bandgap energy in a number of settings. Different crystalline phases of CdS have been seen; the bandgap of cubic CdS is 2.24 eV, whereas that of hexagonal CdS is 2.17 eV. Because of its higher energy carrier migration and lower mixing rates, the cubic phase exhibits stronger photocatalytic performance and is hence more useful for hydrogen evolution reactions when subjected to visible light [198]. Furthermore, improved photocatalytic degradation of pollutants is linked to the creation of heterogeneous structures with reduced band gaps, suggesting that lower bandgap values can promote higher light absorption and catalytic activity. In general, changes in structure that control bandgap energy were essential for optimizing CdS photocatalysts in a variety of applications [199]. Research on CdS nanocomposites, such as chitosan/polyaniline/CdS, employed ANNs to predict decolorization efficiency. This indicates that AI can effectively model and optimize photocatalytic reactions involving Cd [200]. Table 6 shows the cadmium sulfides used as catalysts to degrade different pollutants using the AI model

6.4. Tungsten Trioxide (WO3)

AI is increasingly being integrated into the field of photocatalysis; in particular, tungsten trioxide (WO3) is an increasingly common substance for photocatalysis because of its advantageous qualities, such as a band gap of 2.5 to 2.7 eV, high stability, and excellent electrochemical properties. Its uses include pollutant degradation, CO2 reduction, and water splitting, making it a diverse option for sustainable energy solutions [205]. Doping with hydrogen and noble metals (silver) improves solar energy usage and broadens light absorption into the near-infrared spectrum. When coupled with other materials like hydroxyapatite (HAp), WO3 has shown outstanding photocatalytic activity, increasing the breakdown efficiency of contaminants like MB to 88.689% [206,207]. Table 7 shows the Tungsten trioxides (WO3) used as catalysts to degrade different pollutants using the AI model.

6.5. Cesium Dioxide

The integration of AI in CeO2 photocatalysis is revolutionizing the field by enhancing defect engineering, optimizing reaction conditions, and improving predictive capabilities. AI techniques, particularly ML, are being employed to address the challenges associated with photocatalytic processes [83]. ML algorithms have been utilized to control defect structures in CeO2 nanostructures, crucial for their catalytic properties [210]. Table 8 shows the Cesium dioxide as a catalyst that degrades different pollutants using an AI model.

6.6. Zirconium Oxide (ZrO2)

This is a significant milestone, as it combines artificial intelligence with zirconium oxide photocatalysis for highly efficient and optimized water treatment using intelligent systems and advanced materials. Recent studies highlight the development of zirconium-based photocatalysts, such as zirconium oxide–carbon composites and zirconium-doped chromium IV oxide, which demonstrate effective degradation of organic compounds under various light conditions. Table 9 shows the Zirconium oxide as a catalyst that degrades different pollutants using AI models.

6.7. Limitations and Challenges of Data Sparsity and Overfitting in AI-Driven Photocatalysis: Mitigation Strategies

Even if artificial intelligence has the potential to revolutionize photocatalytic wastewater treatment, several inherent limitations must be carefully considered to ensure the scalability, interpretability, and reliability of AI-driven models. The expense, effort, and complexity of synthesizing and characterizing photocatalytic materials limit the availability of complete, high-quality experimental datasets. Consequently, data sparsity remains a major challenge. Predictive accuracy may suffer, and model training may be affected by this lack of data [216]. Model overfitting is a serious issue, especially when using deep learning techniques with small datasets. This can lead to poor generalization to new data since the model may collect noise rather than key patterns. The limited generalizability of AI models across various photocatalysts is another significant drawback. This is because models that have been trained on small or chemically homogeneous datasets frequently perform unreliably when applied to structurally or functionally varied systems [217]. These problems highlight the necessity of strong mitigation measures, such as regularization methods, data augmentation, transfer learning, cross-validation, and the addition of mechanistic descriptors that capture basic physicochemical characteristics. To move AI from a helpful computational tool to a trustworthy prediction framework that can hasten the logical design of next-generation photocatalysts for sustainable wastewater treatment, these constraints must be solved [218]. AI applications in photocatalysis face several challenges, including data sparsity, overfitting, limited generalizability, poor interpretability, lack of reproducibility, weak experimental integration, and dataset bias. The inability to interpret models is a significant issue, especially with complicated deep learning frameworks that frequently act as “black boxes.” This transparency undermines confidence in model-driven decision-making by making it more difficult for researchers to extract significant chemical or mechanistic insights from AI forecasts. Additionally, because much research lacks standardization in feature selection, dataset curation, and evaluation measures, reproducibility is still a major problem. These variations limit the creation of generally recognized benchmarks and make it challenging to compare models across various research teams. The poor integration of AI models with actual experimental procedures is another drawback [98,219]. The practical usefulness of many AI studies is limited because they are mostly theoretical or computational and have received little validation through laboratory experimentation. Additionally, if the training datasets have preferences towards particular catalyst families or reaction conditions, computational bias may be introduced, which would ultimately decrease the fairness and applicability of the model across a variety of systems. Standardized datasets, transparent model development, interdisciplinary cooperation, and a closer connection between AI predictions and experimental validation are all necessary to overcome these more general constraints [220,221]. Along with these challenges, it is important to highlight that overfitting and data sparsity can undermine the predictive accuracy of AI-based photocatalytic models. Transfer learning, which enables models trained on larger, related datasets to be adapted for specialized systems, offers a robust solution to these issues. This approach has been shown to significantly boost performance in materials science applications [222]. Concurrently, rigorous cross-validation methods (such as 10-fold cross-validation) [141] help prevent models from identifying spurious correlations and have proven effective in validating robustness in studies of photocatalytic degradation. When combined with regularization and kinetic feature selection, these strategies ensure improved generalizability and predictive reliability. As a result, such targeted mitigation methods are critical for reducing bias and achieving reproducible outcomes in real-world applications [223].

7. Conclusions

This review offers a comprehensive overview of current methods, materials, and model performances while thoroughly exploring how AI is transforming the field of photocatalytic wastewater treatment. Researchers have significantly enhanced their ability to understand, predict, and optimize photocatalytic degradation processes by using supervised machine learning techniques, including SVM, ANN, and tree-based algorithms. When trained on key operational parameters such as the type of photocatalyst, presence of dopants, light conditions, and types of contaminants, these AI models have shown exceptional effectiveness in capturing complex, nonlinear interactions that traditional methods often miss. AI has played a vital role in improving the performance of materials like TiO2, ZnO, CdS, ZrO2, WO3, and CeO2, along with their doped versions, by guiding experimental design and parameter selection. These materials have consistently demonstrated increased activity. Additionally, by integrating multiple studies into a cohesive synthesis, this review addresses a critical gap in the literature by highlighting both promising results and limitations related to model evaluation and data standardization. Nevertheless, there are still significant research gaps. Reliable model validation requires external datasets. Integration of AI with digital representations can facilitate scalable optimization and real-time monitoring. To increase trust and openness, explainable AI is required. When combined, these developments will position AI as a major facilitator of sustainable and intelligent photocatalytic wastewater treatment. Moving forward, prioritizing open data sharing and code accessibility is essential for ensuring transparency, reproducibility, and accelerated scientific progress in AI-driven photocatalytic research. Establishing benchmarking procedures, publishing reliable code, and providing datasets will enable the scientific community to validate, replicate, and continually improve models, thereby increasing confidence in reported results.

8. Future Perspectives

The analysis’s conclusions offer important information that may help determine the focus of future research, direct the creation of successful AI-driven solutions, and support more sustainable water management techniques. Future research should consider the following:
  • As the current model algorithms are only designed for particular stages of the wastewater treatment process, more organized and comprehensive algorithms involving the prediction of pollutant levels, the enhancement of operating parameters, the monitoring of maintenance processes, and the reuse of recyclable polluting substances should be developed.
  • Developing combination algorithms and combined optimization approaches that can better monitor and control wastewater treatment systems.
  • Using artificial intelligence, which is currently understudied, to design novel, useful materials for wastewater treatment.
  • Strong cross-disciplinary collaboration will be necessary for future developments in AI-driven photocatalysis to connect computational predictions with experimental validation successfully. For the results of models to be chemically interpretable, explainable AI must be implemented.
  • At the same time, basic research needs to be prioritized to support both deeper mechanistic insights and real-world applications. More replicable and optimized photocatalytic systems will be made possible by striking a balance between theoretical knowledge and innovation. Ultimately, this integrated strategy has the potential to revolutionize sustainable chemical synthesis, wastewater treatment, and energy storage.

Author Contributions

A.R.: Writing—original draft. M.A.I.: Conceptualization, Resources, Supervision. M.T.H.: Data curation and Formal Analysis. A.M.: Writing—review and editing, Software, Validation. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

The researchers sought informed consent from all participants before recruitment for data collection. The explicit consent for publication was also obtained from participants.

Data Availability Statement

Data will be made available on request.

Acknowledgments

The authors thank the Pakistan Science Foundation for awarding research grant PSF/CRP/Consr-676.

Conflicts of Interest

The authors declare that they have no competing interests.

References

  1. Bhattacharjee, J.; Roy, S.; Shaikh, A.A. Artificial Intelligence and Machine Learning for the Optimization of Photocatalytic Performance. Energy 2025, 360, 100027. [Google Scholar] [CrossRef]
  2. Hicham, N.; Nassera, H.; Karim, S. Strategic framework for leveraging artificial intelligence in future marketing decision-making. J. Intell. Manag. Decis. 2023, 2, 139–150. [Google Scholar] [CrossRef]
  3. Nishant, R.; Kennedy, M.; Corbett, J. Artificial intelligence for sustainability: Challenges, opportunities, and a research agenda. Int. J. Inf. Manag. 2020, 53, 102104. [Google Scholar] [CrossRef]
  4. Shang, Y.; Zhou, S.; Zhuang, D.; Żywiołek, J.; Dincer, H. The impact of artificial intelligence application on enterprise environmental performance: Evidence from microenterprises. Gondwana Res. 2024, 131, 181–195. [Google Scholar] [CrossRef]
  5. Alprol, A.E.; Mansour, A.T.; Ibrahim, M.E.E.-D.; Ashour, M. Artificial Intelligence Technologies Revolutionizing Wastewater Treatment: Current Trends and Future Prospective. Water 2024, 16, 314. [Google Scholar] [CrossRef]
  6. Xu, W.-L.; Wang, Y.-J.; Wang, Y.-T.; Li, J.-G.; Zeng, Y.-N.; Guo, H.-W.; Liu, H.; Dong, K.-L.; Zhang, L.-Y. Application and innovation of artificial intelligence models in wastewater treatment. J. Contam. Hydrol. 2024, 267, 104426. [Google Scholar] [CrossRef]
  7. Huang, C.; Sun, H.; Liu, Y.; Yuan, H. Trace the evolution path of pharmaceutical wastewater treatment technology based on a patent perspective. Water Sci. Technol. 2024, 90, 1985–2001. [Google Scholar] [CrossRef]
  8. Baskar, G.; Omer, S.N.; Saravanan, P.; Rajeshkannan, R.; Saravanan, V.; Rajasimman, M.; Shanmugam, V. Status and future trends in wastewater management strategies using artificial intelligence and machine learning techniques. Chemosphere 2024, 362, 142477. [Google Scholar] [CrossRef]
  9. Schossler, R.T.; Ojo, S.; Jiang, Z.; Hu, J.; Yu, X. A novel interpretable machine learning model approach for the prediction of TiO2 photocatalytic degradation of air contaminants. Sci. Rep. 2024, 14, 13070. [Google Scholar] [CrossRef]
  10. Behera, S.K.; Karthika, S.; Mahanty, B.; Meher, S.K.; Zafar, M.; Baskaran, D.; Rajamanickam, R.; Das, R.; Pakshirajan, K.; Bilyaminu, A.M. Application of artificial intelligence tools in wastewater and waste gas treatment systems: Recent advances and prospects. J. Environ. Manag. 2024, 370, 122386. [Google Scholar] [CrossRef]
  11. Dashti, A.; Navidpour, A.H.; Amirkhani, F.; Zhou, J.L.; Altaee, A. Application of machine learning models to improve the prediction of pesticide photodegradation in water by ZnO-based photocatalysts. Chemosphere 2024, 362, 142792. [Google Scholar] [CrossRef]
  12. Mehmet, O.; Yorucu, V. Human Damage to the Global Ecosystem. In From Land Disputes to Sustainable Environmental Development: A Near East Perspective; Springer: Berlin/Heidelberg, Germany, 2024; pp. 151–165. [Google Scholar]
  13. Roy, B.; Bhunia, B.; Bandyopadhyay, T.K.; Khan, S.A.; Nandi, N.B.; Nath, P.C. Water Pollution by Heavy Metals and Their Impact on Human Health. In Handbook of Water Pollution; Inamuddin, Altalhi, T., Alrooqi, A., Eds.; Scrivener Publishing LLC: Beverly, MA, USA; Wiley: Hoboken, NJ, USA, 2024; pp. 333–352. [Google Scholar]
  14. Merchán-Sanmartín, B.; Álava-Zúñiga, B.; Vallejo-Palomeque, F.; Suárez-Zamora, S.; Aguilar-Aguilar, M.; Morante-Carballo, F. Integrated wastewater management for environmental protection and sustainable ecotourism in an Andean paramo community. Chall. Sustain. 2025, 13, 334–353. [Google Scholar] [CrossRef]
  15. El Hammoudani, Y.; Dimane, F.; Haboubi, K.; Benaissa, C.; Benaabidate, L.; Bourjila, A.; Achoukhi, I.; El Boudammoussi, M.; Faiz, H.; Touzani, A. Micropollutants in wastewater treatment plants: A bibliometric-bibliographic study. Desalination Water Treat. 2024, 317, 100190. [Google Scholar] [CrossRef]
  16. Agbasi, J.C.; Ayejoto, D.A.; Egbueri, J.C.; Khan, N.; Abba, S.I.; Ahmad, V.; Abuzinadah, M.F. HERisk and statistical clustering integrated for health risk modelling of PTEs in natural water resources for drinking and sanitary uses. Toxin Rev. 2024, 43, 513–539. [Google Scholar] [CrossRef]
  17. Sharma, K.; Rajan, S.; Nayak, S.K. Water pollution: Primary sources and associated human health hazards with special emphasis on rural areas. In Water Resources Management for Rural Development; Elsevier: Amsterdam, The Netherlands, 2024; pp. 3–14. [Google Scholar]
  18. Vosough, M.; Khayati, G.R.; Sharafi, S. A novel nanocomposite for photocatalytic rhodamine B dye removal from wastewater using visible light. Environ. Res. 2024, 249, 118415. [Google Scholar] [CrossRef]
  19. Hamrayev, H.; Korpayev, S.; Shameli, K. Advances in Synthesis Techniques and Environmental Applications of TiO2 Nanoparticles for Wastewater Treatment: A Review. J. Res. Nanosci. Nanotechnol. 2024, 12, 1–24. [Google Scholar] [CrossRef]
  20. Ogundele, O.; Oyegoke, D.; Anaun, T. Exploring the potential and challenges of electro-chemical processes for sustainable waste water remediation and treatment. Acadlore Trans. Geosci. 2023, 2, 80–93. [Google Scholar] [CrossRef]
  21. Coelho, L.L.; Wilhelm, M.; Hotza, D.; de Fátima Peralta Muniz Moreira, R. Oily wastewater treatment by photocatalytic membranes: A review. Environ. Technol. Rev. 2024, 13, 95–119. [Google Scholar] [CrossRef]
  22. Awad, H.; Mossad, M.; Mahanna, H.; Foad, M.; Alalm, M.G. Comparative assessment of different scenarios for upgrading activated sludge wastewater treatment plants in developing countries. Sci. Total Environ. 2024, 907, 168022. [Google Scholar] [CrossRef]
  23. Kallawar, G.A.; Bhanvase, B.A. A review on existing and emerging approaches for textile wastewater treatments: Challenges and future perspectives. Environ. Sci. Pollut. Res. 2024, 31, 1748–1789. [Google Scholar] [CrossRef]
  24. Akinyemi, B.; Ogundele, O.; Afolabi, A. Advancements in sustainable membrane technologies for enhanced remediation and wastewater treatment: A comprehensive review. Acadlore Trans. Geosci. 2023, 2, 196–207. [Google Scholar] [CrossRef]
  25. Yuan, L.; Yan, P.; Wang, P.; Li, L.; Xiao, X.; Xie, Y. Constructing stable type-II NaLiTi3O7/La2S3 heterojunctions for efficient photocatalytic charge separation and hydrogen production. Int. J. Hydrogen Energy 2024, 64, 958–964. [Google Scholar] [CrossRef]
  26. Safira, A.R.; Fattah-alhosseini, A.; Kaseem, M. Surface growth of novel MOFs on AZ31 Mg alloy coated via plasma electrolytic oxidation for enhanced corrosion protection and photocatalytic performance. J. Magnes. Alloys 2024, 12, 2413–2432. [Google Scholar] [CrossRef]
  27. Su, R.; Zhu, Y.; Gao, B.; Li, Q. Progress on mechanism and efficacy of heterogeneous photocatalysis coupled oxidant activation as an advanced oxidation process for water decontamination. Water Res. 2024, 251, 121119. [Google Scholar] [CrossRef]
  28. Chong, M.N.; Jin, B.; Chow, C.W.; Saint, C. Recent developments in photocatalytic water treatment technology: A review. Water Res. 2010, 44, 2997–3027. [Google Scholar] [CrossRef]
  29. Kanoun, M.B.; Ahmed, F.; Awada, C.; Jonin, C.; Brevet, P.-F. Band gap engineering of Au doping and Au–N codoping into anatase TiO2 for enhancing the visible light photocatalytic performance. Int. J. Hydrogen Energy 2024, 51, 907–913. [Google Scholar] [CrossRef]
  30. Liza, T.Z.; Tusher, M.M.H.; Anwar, F.; Monika, M.F.; Amin, K.F.; Asrafuzzaman, F. Effect of Ag-doping on morphology, structure, band gap and photocatalytic activity of bio-mediated TiO2 nanoparticles. Results Mater. 2024, 22, 100559. [Google Scholar] [CrossRef]
  31. Alhajeri, N.S.; Tawfik, A.; Nasr, M.; Osman, A.I. Artificial intelligence-enabled optimization of Fe/Zn@ biochar photocatalyst for 2, 6-dichlorophenol removal from petrochemical wastewater: A techno-economic perspective. Chemosphere 2024, 352, 141476. [Google Scholar] [CrossRef]
  32. Esmaeili, N.; Saraei, F.E.K.; Pirbazari, A.E.; Tabatabai-Yazdi, F.-S.; Khodaee, Z.; Amirinezhad, A.; Esmaeili, A.; Pirbazari, A.E. Estimation of 2,4-dichlorophenol photocatalytic removal using different artificial intelligence approaches. Chem. Prod. Process Model. 2023, 18, 247–263. [Google Scholar] [CrossRef]
  33. Jabbar, Z.H.; Graimed, B.H.; Ammar, S.H.; Sabit, D.A.; Najim, A.A.; Radeef, A.Y.; Taher, A.G. The latest progress in the design and application of semiconductor photocatalysis systems for degradation of environmental pollutants in wastewater: Mechanism insight and theoretical calculations. Mater. Sci. Semicond. Process. 2024, 173, 108153. [Google Scholar] [CrossRef]
  34. Sun, N.; Si, X.; He, L.; Zhang, J.; Sun, Y. Strategies for enhancing the photocatalytic activity of semiconductors. Int. J. Hydrogen Energy 2024, 58, 1249–1265. [Google Scholar] [CrossRef]
  35. Vishwanathan, S.; Laxmi, S.; Nandan, S.; Jayan, S.; Lijo, M.; Das, S. Effect of experimental parameters on photocatalytic degradation efficiency of TiO2 nanoparticles synthesized by electrochemical method towards Rhodamine B dye solution under natural sunlight. Environ. Sci. Pollut. Res. 2023, 30, 8448–8463. [Google Scholar]
  36. Lin, L.; Jiang, W.; Chen, L.; Xu, P.; Wang, H. Treatment of produced water with photocatalysis: Recent advances, affecting factors and future research prospects. Catalysts 2020, 10, 924. [Google Scholar] [CrossRef]
  37. Yamazaki, S.; Takaki, D.; Nishiyama, N.; Yamazaki, Y. Factors affecting photocatalytic activity of TiO2. In Current Developments in Photocatalysis and Photocatalytic Materials; Elsevier: Amsterdam, The Netherlands, 2020; pp. 23–38. [Google Scholar]
  38. Al-Nuaim, M.A.; Alwasiti, A.A.; Shnain, Z.Y. The photocatalytic process in the treatment of polluted water. Chem. Pap. 2023, 77, 677–701. [Google Scholar] [CrossRef]
  39. Lanjwani, M.F.; Tuzen, M.; Khuhawar, M.Y.; Saleh, T.A. Trends in photocatalytic degradation of organic dye pollutants using nanoparticles: A review. Inorg. Chem. Commun. 2024, 159, 111613. [Google Scholar] [CrossRef]
  40. Ahmed, S.; Rasul, M.; Brown, R.; Hashib, M. Influence of parameters on the heterogeneous photocatalytic degradation of pesticides and phenolic contaminants in wastewater: A short review. J. Environ. Manag. 2011, 92, 311–330. [Google Scholar] [CrossRef] [PubMed]
  41. Adnan, M.A.M.; Majnis, M.F.; Adnan, W.N.W.; Abdullah, N.H.; Baharom, A.S.; Julkapli, N.M. Deep Insights into the Integration of Artificial Neural Networks (ANNs) for Predicting the Photocatalytic Activities of Metal-Based Catalysts in Water Pollutant Reduction. J. Environ. Chem. Eng. 2025, 13, 116350. [Google Scholar] [CrossRef]
  42. Jiang, D.; Otitoju, T.A.; Ouyang, Y.; Shoparwe, N.F.; Wang, S.; Zhang, A.; Li, S. A review on metal ions modified TiO2 for photocatalytic degradation of organic pollutants. Catalysts 2021, 11, 1039. [Google Scholar] [CrossRef]
  43. Mohammed, N.; Palaniandy, P.; Shaik, F. Optimization of solar photocatalytic biodegradability of seawater using statistical modelling. J. Indian Chem. Soc. 2021, 98, 100240. [Google Scholar] [CrossRef]
  44. Kumar, A.; Pandey, G. A review on the factors affecting the photocatalytic degradation of hazardous materials. Mater. Sci. Eng. Int. J. 2017, 1, 1–10. [Google Scholar] [CrossRef]
  45. Mohammadzadeh Kakhki, R.; Zirjanizadeh, S.; Mohammadpoor, M. A review of clinoptilolite, its photocatalytic, chemical activity, structure and properties: In time of artificial intelligence. J. Mater. Sci. 2023, 58, 10555–10575. [Google Scholar] [CrossRef]
  46. Wang, S.; Mo, P.; Li, D.; Syed, A. Intelligent Algorithms Enable Photocatalyst Design and Performance Prediction. Catalysts 2024, 14, 217. [Google Scholar] [CrossRef]
  47. Sohrabi, S.; Rahimi, P.; Khedri, M.; Heydari, R.; Mirzaei, M.; Bahrami, A.; Akhlaghian, F.; Taghipoor, M. Evaluation of machine learning and molecular dynamics models for photocatalytic water decontamination. Process Saf. Environ. Prot. 2025, 195, 106780. [Google Scholar]
  48. Ai, C.; Zhou, D.; Wang, Q.; Shao, X.; Lei, Y. Optimization of operating parameters for photocatalytic degradation of tetracycline using In2S3 under natural solar radiation. Sol. Energy 2015, 113, 34–42. [Google Scholar] [CrossRef]
  49. Yan, Q.; Wang, X.; Xiong, Q.; Lu, J.; Liao, B. The influences of technological parameters on the ultraviolet photocatalytic reaction rate and photocatalysis-assisted polishing effect for SiC. J. Cryst. Growth 2020, 531, 125379. [Google Scholar] [CrossRef]
  50. Ali, H.; Yasir, M.; Haq, H.U.; Guler, A.C.; Masar, M.; Khan, M.N.A.; Machovsky, M.; Sedlarik, V.; Kuritka, I. Machine learning approach for photocatalysis: An experimentally validated case study of photocatalytic dye degradation. J. Environ. Manag. 2025, 386, 125683. [Google Scholar] [CrossRef]
  51. Xu, K.; Pan, B.; Lu, H.; Wang, X.; Zhang, X.; Xie, M.; Yu, J. Machine Learning-Assisted ZnO-Doped Photocatalytic Degradation of Rhodamine B: Prediction, Analysis, and Optimization. Environ. Technol. Innov. 2025, 40, 104425. [Google Scholar] [CrossRef]
  52. Fuziki, M.E.K.; Ribas, L.S.; Tusset, A.M.; Brackmann, R.; Dos Santos, O.A.; Lenzi, G.G. Pharmaceutical compounds photolysis: pH influence. Heliyon 2023, 9, e13678. [Google Scholar] [CrossRef]
  53. Gheytanzadeh, M.; Baghban, A.; Habibzadeh, S.; Jabbour, K.; Esmaeili, A.; Mohaddespour, A.; Abida, O. An insight into tetracycline photocatalytic degradation by MOFs using the artificial intelligence technique. Sci. Rep. 2022, 12, 6615. [Google Scholar] [CrossRef]
  54. Marfur, N.A.; Jaafar, N.F.; Anuar, M.H.; Zulkeffli, N. Effect of pH on the photocatalytic degradation of 2, 4-dichlorophenol via noble metal doped ZnO photocatalyst. AIP Conf. Proc. 2021, 2610, 040015. [Google Scholar]
  55. Gilani, S.A.B.; Naseeb, F.; Kiran, A.; Ihsan, M.U.; Iqbal, J.; Javed, H.M.A.; Bhatti, H.N.; Karami, A.M.; Hussain, S.; ShabirMahr, M. pH dependent synthesis of ceria nanoparticles for efficient sunlight-driven photocatalysis of methyl orange containing wastewater. Opt. Mater. 2024, 148, 114871. [Google Scholar] [CrossRef]
  56. Mbuyazi, T.B.; Ajibade, P.A. Photocatalytic degradation of organic dyes by magnetite nanoparticles prepared by co-precipitation. Int. J. Mol. Sci. 2024, 25, 7876. [Google Scholar] [CrossRef]
  57. Sirota, V.V.; Savotchenko, S.E.; Strokova, V.V.; Vashchilin, V.S.; Podgornyi, D.S.; Limarenko, M.V.; Kovaleva, M.G. Effect of irradiation intensity on the rate of photocatalysis of TiO2 coatings obtained by detonation spraying. Int. J. Appl. Ceram. Technol. 2024, 21, 3335–3345. [Google Scholar] [CrossRef]
  58. Ramos-Huerta, L.A.; Laureys, L.; Llanos, A.G.; Valadés, P.J.; Ruiz, R.S.; Castillo, C.O. Assessing the effect of light intensity and light wavelength spectra on the photoreduction of formic acid using a graphene oxide material. Int. J. Chem. React. Eng. 2020, 18, 20200008. [Google Scholar] [CrossRef]
  59. Pirgholi-Givi, G.; Farjami-Shayesteh, S.; Azizian-Kalandaragh, Y. The influence of irradiation intensity and stirring rate on the photocatalytic activity of titanium dioxide nanostructures prepared by the microwave-assisted method for photodegradation of MB from water. Phys. B Condens. Matter 2020, 578, 411886. [Google Scholar] [CrossRef]
  60. Khataee, A. Photocatalytic removal of CI Basic Red 46 on immobilized TiO2 nanoparticles: Artificial neural network modelling. Environ. Technol. 2009, 30, 1155–1168. [Google Scholar] [CrossRef]
  61. Chen, Y.-W.; Hsu, Y.-H. Effects of reaction temperature on the photocatalytic activity of TiO2 with Pd and Cu cocatalysts. Catalysts 2021, 11, 966. [Google Scholar] [CrossRef]
  62. Cho, Y.; Yamaguchi, A.; Sinaga, A.S.; Yang, Y.; Miyauchi, M. Photocatalysis under thermally shifted bandgap. Appl. Catal. A Gen. 2022, 643, 118772. [Google Scholar] [CrossRef]
  63. Nourizade, M.; Rahmani, M.; Javadi, A. Simulation of a Photocatalytic Reactor Using Finite Volume and Discrete Ordinate Method: A Parametric Study. Amirkabir J. Mech. Eng. 2021, 53, 573–588. [Google Scholar]
  64. Sorathiya, K.; Mishra, B.; Kalarikkal, A.; Reddy, K.P.; Gopinath, C.S.; Khushalani, D. Enhancement in rate of photocatalysis upon catalyst recycling. Sci. Rep. 2016, 6, 35075. [Google Scholar] [CrossRef]
  65. Markovskaya, D.; Kozlova, E. Formal Kinetic Description of Photocatalytic Hydrogen Evolution from Ethanol Aqueous Solutions in the Presence of Sodium Hydroxide. Kinet. Catal. 2018, 59, 727–734. [Google Scholar] [CrossRef]
  66. Wang, C.; Jeon, J.; Seo, E.; Park, J. Ion-concentration-polarization-assisted photocatalytic reactor for highly efficient water purification. Lab Chip 2022, 22, 2962–2970. [Google Scholar] [CrossRef]
  67. Sieland, F.; Duong, N.A.-T.; Schneider, J.; Bahnemann, D.W. Influence of inorganic additives on the photocatalytic removal of nitric oxide and on the charge carrier dynamics of TiO2 powders. J. Photochem. Photobiol. A Chem. 2018, 366, 142–151. [Google Scholar] [CrossRef]
  68. Wang, Y.; Jiang, L.; Feng, C. Effect of additives on photocatalysis of Cr (VI)-methyl orange. Procedia Environ. Sci. 2013, 18, 625–631. [Google Scholar] [CrossRef]
  69. Abreu, E.; Fidelis, M.Z.; Fuziki, M.; Malikoski, R.; Mastsubara, M.; Imada, R.; de Tuesta, J.D.; Gomes, H.; Anziliero, M.; Baldykowski, B. Degradation of emerging contaminants: Effect of thermal treatment on nb2o5 as photocatalyst. J. Photochem. Photobiol. A Chem. 2021, 419, 113484. [Google Scholar] [CrossRef]
  70. Krishna, V.; Bai, W.; Han, Z.; Yano, A.; Thakur, A.; Georgieva, A.; Tolley, K.; Navarro, J.; Koopman, B.; Moudgil, B. Contaminant-activated visible light photocatalysis. Sci. Rep. 2018, 8, 1894. [Google Scholar] [CrossRef]
  71. Rodríguez-González, V.; Obregón, S.; Patrón-Soberano, O.A.; Terashima, C.; Fujishima, A. An approach to the photocatalytic mechanism in the TiO2-nanomaterials microorganism interface for the control of infectious processes. Appl. Catal. B Environ. 2020, 270, 118853. [Google Scholar] [CrossRef]
  72. Lukic, S.; Menze, J.; Weide, P.; Busser, G.W.; Winterer, M.; Muhler, M. Decoupling the Effects of High Crystallinity and Surface Area on the Photocatalytic Overall Water Splitting over β-Ga2O3 Nanoparticles by Chemical Vapor Synthesis. ChemSusChem 2017, 10, 4190–4197. [Google Scholar] [CrossRef]
  73. Kumari, N.; Gaurav, K.; Dash, R.; Bhattacharyya, A. Doped mixed phase transition metal oxides for photocatalysis. In Handbook of Emerging Materials for Sustainable Energy; Elsevier: Amsterdam, The Netherlands, 2024; pp. 333–346. [Google Scholar]
  74. Liu, Z.; Zhuang, Y.; Dong, L.; Mu, H.; Li, D.; Zhang, F.; Xu, H.; Xie, H. Enhancement mechanism of photocatalytic hydrogen production activity of CeO2/CdS by morphology regulation. ACS Appl. Energy Mater. 2023, 6, 7722–7736. [Google Scholar] [CrossRef]
  75. Ganguli, A.K.; Kunde, G.B.; Raza, W.; Kumar, S.; Yadav, P. Assessment of performance of photocatalytic nanostructured materials with varied morphology based on reaction conditions. Molecules 2022, 27, 7778. [Google Scholar] [CrossRef]
  76. Ge, L.; Ke, Y.; Li, X. Machine learning integrated photocatalysis: Progress and challenges. Chem. Commun. 2023, 59, 5795–5806. [Google Scholar] [CrossRef]
  77. Tabatabai-Yazdi, F.-S.; Pirbazari, A.E.; Saraei, F.E.K.; Gilani, N. Construction of graphene based photocatalysts for photocatalytic degradation of organic pollutant and modeling using artificial intelligence techniques. Phys. B Condens. Matter 2021, 608, 412869. [Google Scholar] [CrossRef]
  78. Xiao, F.; Xiao, T.; Zhao, L.; He, X. Enhanced solar-driven photoelectrochemical water splitting of H/N co-doped TiO2: Role of defect states in a band gap reduction and promotion of charge transfer. Renew. Energy 2024, 230, 120778. [Google Scholar] [CrossRef]
  79. Fang, W.; Yan, J.; Wei, Z.; Liu, J.; Guo, W.; Jiang, Z.; Shangguan, W. Account of doping photocatalyst for water splitting. Chin. J. Catal. 2024, 60, 1–24. [Google Scholar] [CrossRef]
  80. She, S.; Chen, L.; Liao, K.; Fu, Y.; Wang, J.; Wu, X. Doping engineering in S–scheme composite for Regulating the selectivity of photocatalytic CO2 reduction. J. Colloid Interface Sci. 2024, 663, 947–960. [Google Scholar] [CrossRef] [PubMed]
  81. Sen, P.; Bhattacharya, P.; Mukherjee, G.; Ganguly, J.; Marik, B.; Thapliyal, D.; Verma, S.; Verros, G.D.; Chauhan, M.S.; Arya, R.K. Advancements in doping strategies for enhanced photocatalysts and adsorbents in environmental remediation. Technologies 2023, 11, 144. [Google Scholar] [CrossRef]
  82. Gentili, P.L. Photochromic and luminescent materials for the development of Chemical Artificial Intelligence. Dye. Pigment. 2022, 205, 110547. [Google Scholar] [CrossRef]
  83. Xu, J.; Su, A.; Huang, P.; Yu, W.; Du, K.; Fan, Z.; Sun, B.; Zhong, Z.; Jin, C.; Su, W. PhotoCat: An Artificial Intelligence-Driven Synthesis Planning Platform for Photocatalysis. ChemRxiv 2023. [Google Scholar] [CrossRef]
  84. Wei, C.; Song, Z.; Liu, Y.; Zhang, B.; Song, S.; Qin, L.; Zhao, Z. Enhancing photocatalytic performance of Cu6Fe2SnS8 by N doping using magnetic grinding method. Mater. Sci. Semicond. Process. 2024, 176, 108269. [Google Scholar] [CrossRef]
  85. AlMohamadi, H.; Awad, S.A.; Sharma, A.K.; Fayzullaev, N.; Távara-Aponte, A.; Chiguala-Contreras, L.; Amari, A.; Rodriguez-Benites, C.; Tahoon, M.A.; Esmaeili, H. Photocatalytic Activity of Metal-and Non-Metal-Anchored ZnO and TiO2 Nanocatalysts for Advanced Photocatalysis: Comparative Study. Catalysts 2024, 14, 420. [Google Scholar] [CrossRef]
  86. Zhang, Y.; Xu, X. Machine learning band gaps of doped-TiO2 photocatalysts from structural and morphological parameters. ACS Omega 2020, 5, 15344–15352. [Google Scholar] [CrossRef]
  87. Lamouadene, H.; Kassaoui, M.E.; El Yadari, M.; El Kenz, A.; Benyoussef, A. Exploring modeling techniques for predicting band gaps of Doped-ZnO: A Machine learning approach. Chem. Phys. 2025, 591, 112603. [Google Scholar] [CrossRef]
  88. Hafsa, H.; Nasrallah, N.; Zeghbib, S.; Kebir, M.; Tahraoui, H.; Assadi, A.A.; Khezami, L.; Alghamdi, A.; Dahdouh, N.; Lekmine, S. Enhanced Photocatalytic Degradation of Pharmaceutical Pollutants Using Copper-Doped TiO2: Optimization, Machine Learning Integration, and Ecological Safety Assessment. Arab. J. Sci. Eng. 2025, 50, 1–25. [Google Scholar] [CrossRef]
  89. Bakır, R.; Orak, C.; Horoz, S. Enhancing photocatalytic degradation of hazardous pollutants with green-synthesized catalysts: A machine learning approach. J. Environ. Manag. 2025, 385, 125695. [Google Scholar] [CrossRef]
  90. Kakhki, R.M.; Mohammadpoor, M.; Faridi, R.; Bahadori, M. The development of an artificial neural network–genetic algorithm model (ANN-GA) for the adsorption and photocatalysis of methylene blue on a novel sulfur–nitrogen co-doped Fe2O3 nanostructure surface. RSC Adv. 2020, 10, 5951–5960. [Google Scholar] [CrossRef]
  91. Ngulube, K.F.; Abdelhaleem, A.; Fujii, M.; Nasr, M. Synergism of artificial intelligence and techno-economic for sustainable treatment of methylene blue dye-containing wastewater by photocatalysis. Sustainability 2024, 16, 529. [Google Scholar] [CrossRef]
  92. Hamdy, A.; Mostafa, M.; Nasr, M. Regression analysis and artificial intelligence for removal of methylene blue from aqueous solutions using nanoscale zero-valent iron. Int. J. Environ. Sci. Technol. 2019, 16, 357–372. [Google Scholar] [CrossRef]
  93. Igwegbe, C.A.; Mohmmadi, L.; Ahmadi, S.; Rahdar, A.; Khadkhodaiy, D.; Dehghani, R.; Rahdar, S. Modeling of adsorption of methylene blue dye on Ho-CaWO4 nanoparticles using response surface methodology (RSM) and artificial neural network (ANN) techniques. MethodsX 2019, 6, 1779–1797. [Google Scholar] [CrossRef] [PubMed]
  94. Khiam, G.K.; Karri, R.R.; Mubarak, N.M.; Khalid, M.; Walvekar, R.; Abdullah, E.C.; Rahman, M.E. Modelling and optimization for methylene blue adsorption using graphene oxide/chitosan composites via artificial neural network-particle swarm optimization. Mater. Today Chem. 2022, 24, 100946. [Google Scholar] [CrossRef]
  95. Ferk Savec, V.; Mlinarec, K. Experimental work in science education from green chemistry perspectives: A systematic literature review using PRISMA. Sustainability 2021, 13, 12977. [Google Scholar] [CrossRef]
  96. Sohrabi, C.; Franchi, T.; Mathew, G.; Kerwan, A.; Nicola, M.; Griffin, M.; Agha, M.; Agha, R. PRISMA 2020 statement: What’s new and the importance of reporting guidelines. Int. J. Surg. 2021, 88, 105918. [Google Scholar] [CrossRef] [PubMed]
  97. Dabodiya, T.S.; Kumar, J.; Murugan, A.V. Contemplation of Photocatalysis Through Machine Learning. In Machine Learning for Advanced Functional Materials; Springer: Berlin/Heidelberg, Germany, 2023; pp. 221–232. [Google Scholar]
  98. Mustafa, M.; Epelle, E.I.; Macfarlane, A.; Cusack, M.; Burns, A.; Yaseen, M. Innovative approaches to greywater micropollutant removal: AI-driven solutions and future outlook. RSC Adv. 2025, 15, 12125–12151. [Google Scholar] [CrossRef] [PubMed]
  99. Díez, A.Á.; Rois, R.P.; Landín, S.M.; Montenegro, J.M.F. Reinforcement Learning Based Strategies for Decision Support on Water Treatment Plants. In Proceedings of the International Conference on Water Energy Food and Sustainability, Leiria, Portugal, 10–12 May 2023; pp. 649–659. [Google Scholar]
  100. Li, X.; Su, J.; Wang, H.; Boczkaj, G.; Mahlknecht, J.; Singh, S.V.; Wang, C. Bibliometric analysis of artificial intelligence in wastewater treatment: Current status, research progress, and future prospects. J. Environ. Chem. Eng. 2024, 12, 113152. [Google Scholar] [CrossRef]
  101. Palma, D.; Antela, K.U.; Prevot, A.B.; Cervera, M.L.; Morales-Rubio, A.; Sáez-Hernández, R. Artificial neural networks applied to photo-Fenton process: An innovative approach to wastewater treatment. Water Sci. Eng. 2025, 18, 324–334. [Google Scholar] [CrossRef]
  102. Yazdi, A.A.; Pirbazari, A.E.; Saraei, F.E.K.; Esmaeili, A.; Pirbazari, A.E.; Kohnehsari, A.A.; Derakhshesh, A. Design of 2D/2D β-Ni(OH)2/ZnO heterostructures via photocatalytic deposition of nickel for sonophotocatalytic degradation of tetracycline and modeling with three supervised machine learning algorithms. Chemosphere 2024, 352, 141328. [Google Scholar] [CrossRef]
  103. Wang, Z.; Zhu, D. An accurate detection method for surface defects of complex components based on support vector machine and spreading algorithm. Measurement 2019, 147, 106886. [Google Scholar] [CrossRef]
  104. Sheikhmohammadi, A.; Khakzad, P.; Rasolevandi, T.; Azarpira, H. Leveraging artificial intelligence models (GBR, SVR, and GA) for efficient chromium reduction via UV/trichlorophenol/sulfite reaction. Results Eng. 2025, 26, 104599. [Google Scholar] [CrossRef]
  105. Subramanian, Y.; Gajendiran, J.; Veena, R.; Azad, A.K.; Sabarish, V.B.; Muhammed Ali, S.; Kumar, A.; Gubendiran, R.K. Structural, photoabsorption and photocatalytic characteristics of BiFeO3-WO3 nanocomposites: An attempt to validate the experimental data through SVM-based Artificial Intelligence (AI). J. Electron. Mater. 2023, 52, 2421–2431. [Google Scholar] [CrossRef]
  106. Acosta-Angulo, B.; Lara-Ramos, J.; Niño-Vargas, A.; Diaz-Angulo, J.; Benavides-Guerrero, J.; Bhattacharya, A.; Cloutier, S.; Machuca-Martínez, F. Unveiling the potential of machine learning in cost-effective degradation of pharmaceutically active compounds: A stirred photo-reactor study. Chemosphere 2024, 358, 142222. [Google Scholar] [CrossRef]
  107. Patel, J.; Gaur, R.; Shahabuddin, S.; Padia, N.; Vakharia, V.; Suhas, P.; Tyagi, I. Predictive Modeling and Analysis of Photocatalytic Degradation Performance of Biochar-ZnO Nanocomposites on Different Agrochemicals. Int. J. Environ. Res. 2025, 19, 66. [Google Scholar] [CrossRef]
  108. Li, H. Support vector machine. In Machine Learning Methods; Springer: Berlin/Heidelberg, Germany, 2023; pp. 127–177. [Google Scholar]
  109. Okoye, P.C.; Azi, S.O.; Owolabi, T.O.; Adeyemi, O.W.; Souiyah, M.; Latif, M.B.; Olusayo, O. Modeling Energy Gap of Doped Tin (II) Sulfide Metal Semiconductor Nanocatalyst Using Genetic Algorithm-Based Support Vector Regression. J. Nanomater. 2022, 2022, 8211023. [Google Scholar] [CrossRef]
  110. Oyehan, T.; Liadi, M.; Alade, I. Modeling the efficiency of TiO2 photocatalytic degradation of MTBE in contaminated water: A support vector regression approach. SN Appl. Sci. 2019, 1, 1–10. [Google Scholar] [CrossRef]
  111. Mahmoodi, N.M.; Abdi, J.; Taghizadeh, M.; Taghizadeh, A.; Hayati, B.; Shekarchi, A.A.; Vossoughi, M. Activated carbon/metal-organic framework nanocomposite: Preparation and photocatalytic dye degradation mathematical modeling from wastewater by least squares support vector machine. J. Environ. Manag. 2019, 233, 660–672. [Google Scholar]
  112. Vaez, M.; Omidkhah, M.; Alijani, S.; Zarringhalam Moghaddam, A.; Sadrameli, M.; Gholipour Zanjani, N. Evaluation of photocatalytic activity of immobilized titania nanoparticles by support vector machine and artificial neural network. Can. J. Chem. Eng. 2015, 93, 1009–1016. [Google Scholar] [CrossRef]
  113. Azmil, A.S.; Majnis, M.F.; Adnan, M.A.M.; Ismail, S. Application of Artificial Neural Network for Accurate Prediction of Photocatalytic Dye Degradation. In Proceedings of the 2024 5th International Conference on Artificial Intelligence and Data Sciences (AiDAS), Bangkok, Thailand, 3–4 September 2024; pp. 1–6. [Google Scholar]
  114. Pravina, R.; Uthayakumar, H.; Sivasamy, A. Hybrid approach based on response surface methodology and artificial neural networks coupled with genetic algorithm (RSM-GA-ANN) for the Prediction and optimization for the Photodegradation of dye using nano ZnO anchored glass fiber under solar light irradiation. J. Taiwan Inst. Chem. Eng. 2023, 153, 105248. [Google Scholar]
  115. Moslehi, M.H.; Eslami, M.; Ghadirian, M.; Nateq, K.; Ramavandi, B.; Nasseh, N. Photocatalytic decomposition of metronidazole by zinc hexaferrite coated with bismuth oxyiodide magnetic nanocomposite: Advanced modelling and optimization with artificial neural network. Chemosphere 2024, 356, 141770. [Google Scholar] [CrossRef]
  116. Lianmawii, L.; Singh, N.M. Effect of additives on the photocatalytic degradation of malachite green using NiS:Tb3+ nanoparticle and their photoluminescence properties. J. Mol. Struct. 2025, 1320, 139748. [Google Scholar]
  117. Heydari, B.; Sharghi, E.A.; Rafiee, S.; Mohtasebi, S.S. Use of artificial neural network and adaptive neuro-fuzzy inference system for prediction of biogas production from spearmint essential oil wastewater treatment in up-flow anaerobic sludge blanket reactor. Fuel 2021, 306, 121734. [Google Scholar]
  118. Das, S.; Moon, S.; Kaur, R.; Sharma, G.; Kumar, P.; Lavrenčič Štangar, U. Artificial neural network modeling of photocatalytic degradation of pollutants: A review of photocatalyst, optimum parameters and model topology. Catal. Rev. 2024, 67, 544–578. [Google Scholar] [CrossRef]
  119. Hout, S.; Hamdi, L.; Sebti, A.; Laoufi, A. Experimental investigation and bio-inspired optimization of fixed bed photocatalytic reactor system for chlortoluron removal from water. Int. J. Environ. Sci. Technol. 2025, 1–18. [Google Scholar] [CrossRef]
  120. Nair, N.G.; Gandhi, V.G.; Modi, S.; Shukla, A.; Shah, K.J. Response Surface Methodology–Artificial Neural Network (RSM-ANN) Approach to Optimise Photocatalytic Degradation of Levofloxacin Using Graphene Oxide-Doped Titanium Dioxide (GO-TiO2). Water 2025, 17, 2362. [Google Scholar] [CrossRef]
  121. Kumari, P.; Devi, C.; Kumar, M.; Sharma, S.K.; Singh, R.P.; Yadav, K.; Yogesh, G.K. Leveraging machine learning for predicting the photocatalytic performance of a gC3N4/CdS/MoS2-based heterostructure nanocomposite. New J. Chem. 2025, 49, 10287–10308. [Google Scholar] [CrossRef]
  122. Akinola, A.O.; Prabakaran, E.; Govender, K.; Pillay, K. Magnetically-derived pecan nut shells for the adsorptive removal of cadmium: Artificial neural network modelling and photodegradation of sulfamethoxazole using the spent sorbent. J. Environ. Chem. Eng. 2025, 13, 118057. [Google Scholar] [CrossRef]
  123. Patel, J.; Parmar, M.; Shahabuddin, S.; Tyagi, I.; Gaur, R. Designing a Z-scheme rGO–SnS2 synergistic photocatalyst for photocatalytic mineralization of atrazine and 2, 4-dichlorophenoxyacetic acid and applying machine learning for predictive modelling of photocatalytic performance. Nanoscale Adv. 2025, 7, 3485–3507. [Google Scholar] [CrossRef]
  124. Ayodele, B.V.; Alsaffar, M.A.; Mustapa, S.I.; Cheng, C.K.; Witoon, T. Modeling the effect of process parameters on the photocatalytic degradation of organic pollutants using artificial neural networks. Process Saf. Environ. Prot. 2021, 145, 120–132. [Google Scholar] [CrossRef]
  125. Das, L.; Maity, U.; Basu, J.K. The photocatalytic degradation of carbamazepine and prediction by artificial neural networks. Process Saf. Environ. Prot. 2014, 92, 888–895. [Google Scholar] [CrossRef]
  126. Sun, H.; Yan, K.; Yao, C.; Zhang, X.; Gao, Y.; Chen, Z. Feed forward neural network parametrization of the mean radiative properties of the mixture. J. Quant. Spectrosc. Radiat. Transf. 2023, 310, 108740. [Google Scholar] [CrossRef]
  127. Kassahun, S.K.; Kiflie, Z.; Kim, H.; Baye, A.F. Process optimization and kinetics analysis for photocatalytic degradation of emerging contaminant using N-doped TiO2-SiO2 nanoparticle: Artificial Neural Network and Surface Response Methodology approach. Environ. Technol. Innov. 2021, 23, 101761. [Google Scholar] [CrossRef]
  128. Hanafiah, M.M.; Nawaz, R.; Ikram, A.; Ishaq, Y.; Alothman, A.A.; Mohammad, S.; Anjum, M.; Arshad, U.; Baki, Z.A. TiO2-mediated visible-driven photocatalytic degradation of phenolic compounds: Predictive modeling and optimization via machine learning techniques. Chem. Eng. Commun. 2025, 212, 1–20. [Google Scholar] [CrossRef]
  129. Nedelkovski, V.; Radovanović, M.; Medić, D.; Stanković, S.; Hulka, I.; Tanikić, D.; Antonijević, M. Enhancing Wastewater Treatment Through Python ANN-Guided Optimization of Photocatalysis with Boron-Doped ZnO Synthesized via Mechanochemical Route. Processes 2025, 13, 2240. [Google Scholar] [CrossRef]
  130. Raudys, Š. On the universality of the single-layer perceptron model. In Proceedings of the Neural Networks and Soft Computing: Proceedings of the Sixth International Conference on Neural Networks and Soft Computing, Zakopane, Poland, 11–15 June 2002; Springer: Berlin/Heidelberg, Germany, 2003; pp. 79–86. [Google Scholar]
  131. Toennies, K.D. 7 multi-layer perceptron for image classification. In An Introduction to Image Classification: From Designed Models to End-to-End Learning; Springer: Berlin/Heidelberg, Germany, 2024; pp. 139–167. [Google Scholar]
  132. Goel, A.; Goel, A.K.; Kumar, A. Performance analysis of multiple input single layer neural network hardware chip. Multimed. Tools Appl. 2023, 82, 28213–28234. [Google Scholar] [CrossRef]
  133. da Costa Tavares, O.C.; Abidin, A.Z. Artificial Neural Network Multi-Layer Perceptron for Diagnosis of Diabetes Mellitus. JIKO 2024, 7, 19–23. [Google Scholar] [CrossRef]
  134. Essiet, I.O. Neural classification of good and bad food using a feed-forward multi-layer perceptron with supervised learning. J. Emerg. Trends Eng. Appl. Sci. 2014, 5, 61–65. [Google Scholar]
  135. Li, K.; Du, H.; Liu, L.; Yang, H.; Fang, J.; Li, D. Research progress of machine learning in the field of photocatalysis applications. J. Ind. Eng. Chem. 2025, in press. [Google Scholar] [CrossRef]
  136. Alsaffar, M.A.; Ayodele, B.V.; Ghany, M.A.A.; Mustapa, S.I. Modeling the photocatalytic degradation of 1, 2-Dihydroxybenzene using Multilayer Perceptron Neural Networks. In Proceedings of the IOP Conference Series: Materials Science and Engineering, Assiut, Egypt, 11–12 February 2020; p. 012057. [Google Scholar]
  137. Al Haiqi, O.; Nour, A.H.; Ayodele, B.V.; Bargaa, R. Bayesian regularization-trained multi-layer perceptron neural network predictive modelling of phenol degradation using ZnO/Fe2O3 photocatalyst. J. Phys. Conf. Ser. 2019, 1529, 052058. [Google Scholar] [CrossRef]
  138. Lenzi, G.; Evangelista, R.; Duarte, E.; Colpini, L.; Fornari, A.; Neto, R.M.; Jorge, L.; Santos, O. Photocatalytic degradation of textile reactive dye using artificial neural network modeling approach. Desalination Water Treat. 2016, 57, 14132–14144. [Google Scholar] [CrossRef]
  139. Chow, V.; Phan, R.C.-W.; Le Ngo, A.C.; Krishnasamy, G.; Chai, S.-P. Data-driven photocatalytic degradation activity prediction with Gaussian process. Process Saf. Environ. Prot. 2022, 161, 848–859. [Google Scholar] [CrossRef]
  140. Arora, G.; Bala, K.; Emadifar, H.; Khademi, M. A review of radial basis function with applications explored. J. Egypt. Math. Soc. 2023, 31, 6. [Google Scholar] [CrossRef]
  141. Ng, K.H.; Gan, Y.; Cheng, C.K.; Liu, K.-H.; Liong, S.-T. Integration of machine learning-based prediction for enhanced Model’s generalization: Application in photocatalytic polishing of palm oil mill effluent (POME). Environ. Pollut. 2020, 267, 115500. [Google Scholar] [CrossRef]
  142. da Costa, M.F.; Araújo, R.d.S.; Silva, A.R.; Pereira, L.; Silva, G.M. Predictive artificial neural networks as applied tools in the remediation of dyes by adsorption—A review. Appl. Sci. 2025, 15, 2310. [Google Scholar] [CrossRef]
  143. Sargolzaei, J.; Hedayati Moghaddam, A.; Nouri, A.; Shayegan, J. Modeling the removal of phenol dyes using a photocatalytic reactor with SnO2/Fe3O4 nanoparticles by intelligent system. J. Dispers. Sci. Technol. 2015, 36, 540–548. [Google Scholar] [CrossRef]
  144. Ni, Y.; Xia, Z.; Kokot, S. A kinetic spectrophotometric method for simultaneous determination of phenol and its three derivatives with the aid of artificial neural network. J. Hazard. Mater. 2011, 192, 722–729. [Google Scholar] [CrossRef]
  145. Noman, E.A.; Al-Gheethi, A.A.; Alzaeemi, S.A.; Mohamed, R.M.S.R.; Gaik, T.K. Photocatalysis of low-density polyethylene using FKMW-ZnO NPs: Optimization and predication model using a radial basis function neural network ensemble system. Clean Technol. Environ. Policy 2024, 26, 2203–2218. [Google Scholar] [CrossRef]
  146. Aslam, M.; Lee, J.-M.; Kim, H.-S.; Lee, S.-J.; Hong, S. Deep learning models for long-term solar radiation forecasting considering microgrid installation: A comparative study. Energies 2019, 13, 147. [Google Scholar] [CrossRef]
  147. Pascanu, R.; Gulcehre, C.; Cho, K.; Bengio, Y. How to construct deep recurrent neural networks. arXiv 2013, arXiv:1312.6026. [Google Scholar]
  148. Lauria, S.; Saleh, M.F. Conditional recurrent neural networks for broad applications in nonlinear optics. Opt. Express 2024, 32, 5582–5591. [Google Scholar] [CrossRef] [PubMed]
  149. Jha, S.; Gaur, R.; Shahabuddin, S.; Vakharia, V.; Mohsin, M.E.A. Integration of RNN and CatBoost models in a tea-waste biochar filtration system for toxic organic pollutant removal efficiency prediction. RSC Adv. 2025, 15, 27260–27278. [Google Scholar] [CrossRef] [PubMed]
  150. Alonso, N.I. The Mathematics of Recurrent Neural Networks. 27 October 2024. Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5001243 (accessed on 8 September 2025).
  151. Jaffari, Z.H.; Abbas, A.; Lam, S.-M.; Park, S.; Chon, K.; Kim, E.-S.; Cho, K.H. Machine learning approaches to predict the photocatalytic performance of bismuth ferrite-based materials in the removal of malachite green. J. Hazard. Mater. 2023, 442, 130031. [Google Scholar] [CrossRef]
  152. Kumar, P.; Verma, S.; Kaur, R.; Papac, J.; Kušić, H.; Štangar, U.L. Enhanced photo-degradation of N-methyl-2-pyrrolidone (NMP): Influence of matrix components, kinetic study and artificial neural network modelling. J. Hazard. Mater. 2022, 434, 128807. [Google Scholar] [CrossRef]
  153. Song, C.; Shi, Y.; Li, M.; He, Y.; Xiong, X.; Deng, H.; Xia, D. Prediction of g-C3N4-based photocatalysts in tetracycline degradation based on machine learning. Chemosphere 2024, 362, 142632. [Google Scholar] [CrossRef]
  154. Navidpour, A.H.; Hosseinzadeh, A.; Huang, Z.; Li, D.; Zhou, J.L. Application of machine learning algorithms in predicting the photocatalytic degradation of perfluorooctanoic acid. Catal. Rev. 2024, 66, 687–712. [Google Scholar] [CrossRef]
  155. Hou, X.; Lu, H.; Wang, X.; Yu, Z.; Chen, C.; Xu, K.; Wu, H.; He, Y.; Pan, B. Predicting Photocatalytic Degradation Efficiency of Rhodamine: A Machine Learning-Based Model for Composite Catalyst Screening. J. Water Process Eng. 2025, 72, 107512. [Google Scholar]
  156. Dong, M.; Yao, L.; Wang, X.; Benatallah, B.; Zhang, S.; Sheng, Q.Z. Gradient boosted neural decision forest. IEEE Trans. Serv. Comput. 2021, 16, 330–342. [Google Scholar] [CrossRef]
  157. Li, J.; Liu, X.; Wang, H.; Sun, Y.; Dong, F. Prediction and interpretation of photocatalytic NO removal on g-C3N4-based catalysts using machine learning. Chin. Chem. Lett. 2024, 35, 108596. [Google Scholar] [CrossRef]
  158. Ahmed, Y.; Dutta, K.R.; Nepu, S.N.; Prima, M.; AlMohamadi, H.; Akhtar, P. Optimizing photocatalytic dye degradation: A machine learning and metaheuristic approach for predicting methylene blue in contaminated water. Results Eng. 2025, 25, 103538. [Google Scholar] [CrossRef]
  159. Javed, M.F.; Shahab, M.Z.; Asif, U.; Najeh, T.; Aslam, F.; Ali, M.; Khan, I. Evaluation of machine learning models for predicting TiO2 photocatalytic degradation of air contaminants. Sci. Rep. 2024, 14, 13688. [Google Scholar] [CrossRef]
  160. Chen, T.; Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [Google Scholar]
  161. Abdi, J.; Hadipoor, M.; Hadavimoghaddam, F.; Hemmati-Sarapardeh, A. Estimation of tetracycline antibiotic photodegradation from wastewater by heterogeneous metal-organic frameworks photocatalysts. Chemosphere 2022, 287, 132135. [Google Scholar] [CrossRef]
  162. Sehrawat, P.; Kansal, Y.; Singhal, N.; Kansal, S.K. Implementation of machine learning models to predict the photocatalytic KTC drug degradation efficiency over Zn0.5Cd0.5S/MoS2 composite. J. Water Process Eng. 2025, 75, 108078. [Google Scholar] [CrossRef]
  163. Makumbura, R.K.; Mampitiya, L.; Rathnayake, N.; Meddage, D.; Henna, S.; Dang, T.L.; Hoshino, Y.; Rathnayake, U. Advancing water quality assessment and prediction using machine learning models, coupled with explainable artificial intelligence (XAI) techniques like shapley additive explanations (SHAP) for interpreting the black-box nature. Results Eng. 2024, 23, 102831. [Google Scholar] [CrossRef]
  164. Jaison, A.; Mohan, A.; Lee, Y.-C. Machine learning-enhanced photocatalysis for environmental sustainability: Integration and applications. Mater. Sci. Eng. R Rep. 2024, 161, 100880. [Google Scholar] [CrossRef]
  165. Mahapatra, D.M.; Kumar, A.; Kumar, R.; Gupta, N.K.; Ethiraj, B.; Singh, L. Artificial intelligence interventions in 2D MXenes-based photocatalytic applications. Coord. Chem. Rev. 2025, 529, 216460. [Google Scholar] [CrossRef]
  166. Park, J.; Ahn, J.; Kim, J.; Yoon, Y.; Park, J. Prediction and interpretation of water quality recovery after a disturbance in a water treatment system using artificial intelligence. Water 2022, 14, 2423. [Google Scholar] [CrossRef]
  167. Wang, D.; Thunéll, S.; Lindberg, U.; Jiang, L.; Trygg, J.; Tysklind, M. Towards better process management in wastewater treatment plants: Process analytics based on SHAP values for tree-based machine learning methods. J. Environ. Manag. 2022, 301, 113941. [Google Scholar] [CrossRef] [PubMed]
  168. Alizamir, M.; Wang, M.; Adnan Ikram, R.M.; Kim, S.; Ahmed, K.O.; Heddam, S. Developing an efficient explainable artificial intelligence approach for accurate reverse osmosis desalination plant performance prediction: Application of SHAP analysis. Eng. Appl. Comput. Fluid Mech. 2024, 18, 2422060. [Google Scholar] [CrossRef]
  169. Nesfchi, M.M.; Pirbazari, A.E.; Saraei, F.E.K.; Rojaee, F.; Mahdavi, F.; Fa’al Rastegar, S.A. Fabrication of plasmonic nanoparticles/cobalt doped TiO2 nanosheets for degradation of tetracycline and modeling the process by artificial intelligence techniques. Mater. Sci. Semicond. Process. 2021, 122, 105465. [Google Scholar] [CrossRef]
  170. Oviedo, L.R.; Druzian, D.M.; Dalla Nora, L.D.; da Silva, W.L. Study of machine learning on the photocatalytic activity of a novel nanozeolite for the application in the Rhodamine B dye degradation. Catal. Today 2025, 443, 114986. [Google Scholar] [CrossRef]
  171. Khataee, A.; Kasiri, M. Artificial neural networks modeling of contaminated water treatment processes by homogeneous and heterogeneous nanocatalysis. J. Mol. Catal. A Chem. 2010, 331, 86–100. [Google Scholar] [CrossRef]
  172. Zaresefat, M.; Derakhshani, R. Revolutionizing groundwater management with hybrid AI models: A practical review. Water 2023, 15, 1750. [Google Scholar] [CrossRef]
  173. Hoshino, Y.; Rathnayake, N.; Dang, T.L.; Rathnayake, U. Cascaded-ANFIS and its successful real-world applications. In Fuzzy Logic Controllers and Applications; IntechOpen Limited: London, UK, 2024. [Google Scholar]
  174. Liang, Y.; Yin, Y.; Deng, Q.; Jiao, S.; Liang, X.; Huo, C.; Luo, Y. Efficient and easily recyclable photocatalytic reduction of Se (IV) from wastewater using stable TiO2/BiOBr/cloth: Mechanism insight and machine learning modeling. Sep. Purif. Technol. 2025, 352, 128021. [Google Scholar] [CrossRef]
  175. Tomic, A.; Jerkovic, M.; Kovacic, M.; Kovac, E.B.; Kušić, H.; Peternel, I.; Karamanis, P.; Rasulev, B.; Bozic, A.L. Robust simulation of advanced water treatment employing hybrid modeling approach. In Proceedings of the 2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), Male, Maldives, 16–18 November 2022; pp. 1–5. [Google Scholar]
  176. Fidalgo, A.; Letichevsky, S.; Santos, B.F. Assessment of TiO2 band gap from structural parameters using artificial neural networks. J. Photochem. Photobiol. A Chem. 2021, 405, 112870. [Google Scholar] [CrossRef]
  177. Jarollahi, S.; Nabiyouni, G.; Sorinezami, Z.; Shabani, A. Synthesis and characterization of Fe3O4/TiO2/Ag magnetic nanocomposite with enhanced photocatalytic activity for methylene blue degradation and modeling by an artificial neural network (ANN). J. Nanostructures 2023, 13, 359–372. [Google Scholar]
  178. Chandrika, K.; Prabhu, T.N.; Kiran, R.S.; Krishna, R.H. Applications of artificial neural network and Box-Behnken Design for modelling malachite green dye degradation from textile effluents using TiO2 photocatalyst. Environ. Eng. Res. 2022, 27, 200553. [Google Scholar]
  179. Bhagwat, U.O.; Anandan, S.; Goel, S.; Al Souwaileh, A.; Wu, J.J.; Thirunavukarasu, V.; Anandan, S.; Ashokkumar, M. Bi-TiO2 nanomaterials in treating toxic water dye pollutants with Machine learning models. Opt. Mater. 2025, 167, 117231. [Google Scholar] [CrossRef]
  180. Asadollahfardi, G.; Afsharnasab, M.; Rasoulifard, M.H.; Tayebi Jebeli, M. Predicting of acid red 14 removals from synthetic wastewater in the advanced oxidation process using artificial neural networks and fuzzy regression. Rend. Lincei. Sci. Fis. E Nat. 2022, 33, 115–126. [Google Scholar] [CrossRef]
  181. Esmaeili, A.; Heydari Shalmani, S.; Ebrahimian Pirbazari, A.; Esmaeili Khalil Saraei, F.; Tabatabai-Yazdi, F.-S.; Ebrahimian Pirbazari, A.; Derakhshesh, A. Pharmaceutical wastewater treatment using TiO2 nanosheets deposited by cobalt co-catalyst as hybrid photocatalysts: Combined experimental study and artificial intelligence modeling. Chem. Prod. Process Model. 2023, 18, 611–631. [Google Scholar] [CrossRef]
  182. Caglar Gencosman, B.; Eker Sanli, G. Prediction of polycyclic aromatic hydrocarbons (PAHs) removal from wastewater treatment sludge using machine learning methods. Water Air Soil Pollut. 2021, 232, 87. [Google Scholar] [CrossRef]
  183. Ijadpanah-Saravi, H.; Safari, M.; Noruzi-Masir, B.; Darban, A.K.; Bakhshi, P. Intelligent tools to model photocatalytic degradation of beta-naphtol by titanium dioxide nanoparticles. J. Chemom. 2017, 31, e2907. [Google Scholar] [CrossRef]
  184. Sethi, S.; Dhir, A.; Arora, V. Intervention of artificial intelligence to predict the degradation and mineralization of amoxicillin through photocatalytic route using nickel phosphide-titanium dioxide catalyst. React. Kinet. Mech. Catal. 2023, 136, 549–565. [Google Scholar] [CrossRef]
  185. Kohzadi, S.; Bundschuh, M.; Rezaee, R.; Marzban, N.; Vahabzadeh, Z.; Johari, S.A.; Shahmoradi, B.; Amini, N.; Maleki, A. Integrating machine learning with experimental investigation for optimizing photocatalytic degradation of Rhodamine B using neodymium-doped titanium dioxide: A comprehensive approach with toxicity assessment. Environ. Sci. Pollut. Res. 2024, 31, 55301–55316. [Google Scholar] [CrossRef]
  186. Sebti, A.; Souahi, F.; Mohellebi, F.; Igoud, S. Experimental study and artificial neural network modeling of tartrazine removal by photocatalytic process under solar light. Water Sci. Technol. 2017, 76, 311–322. [Google Scholar] [CrossRef]
  187. Zhou, J.; Wu, Z.; Jin, C.; Zhang, J.X. Machine learning assisted dual-functional nanophotonic sensor for organic pollutant detection and degradation in water. Npj Clean Water 2024, 7, 3. [Google Scholar] [CrossRef]
  188. Saeed, M.H.; Kosar, N.; Hassan, S.-u.; Nadeem, S.; Mohammed, M.A.; Abd Ghani, M.K.; Abdulkareem, K.H. Determination of bandgap of period 3, 4, and 5 transition metal dopants on zinc oxide using an artificial neural network based approach. Chemom. Intell. Lab. Syst. 2023, 242, 104983. [Google Scholar] [CrossRef]
  189. Martínez-Vargas, B.L.; González Rodríguez, L.M.; Pacheco-Álvarez, M.; Peralta-Hernández, J.M.; Picos, A. Use of artificial intelligence models for the reduction of nanoparticle size in the synthesis of ZnO. J. Chem. Technol. Biotechnol. 2023, 98, 1868–1877. [Google Scholar] [CrossRef]
  190. Moradi, M.; Moradkhani, M.; Hosseini, S.; Olazar, M. Intelligent modeling of photocatalytically reactive yellow 84 azo dye removal from aqueous solutions by ZnO-light expanded clay aggregate nanoparticles. Int. J. Environ. Sci. Technol. 2023, 20, 3009–3022. [Google Scholar] [CrossRef]
  191. Tanasa, D.E.; Piuleac, C.G.; Curteanu, S.; Popovici, E. Photodegradation process of Eosin Y using ZnO/SnO2 nanocomposites as photocatalysts: Experimental study and neural network modeling. J. Mater. Sci. 2013, 48, 8029–8040. [Google Scholar] [CrossRef]
  192. Hosseini, S.A.; Akbari, M. ZnO/Mg-Al layered double hydroxides as a photocatalytic bleaching of methylene orange—A black box modeling by artificial neural network. Bull. Chem. React. Eng. Catal. 2016, 11, 299–315. [Google Scholar] [CrossRef]
  193. Kahkha, M.R.R.; Piri, J. Comparison of Artificial Neural Network and Neutral-Fuzzy Inference System for photocatalytic removal of reactive red dye. Tech. J. Eng. Appl. Sci 2016, 6, 39–44. [Google Scholar]
  194. Reddy, B.; Maurya, A.; Narayana, P.; Pasha, S.K.; Reddy, M.; Hatshan, M.R.; Darwish, N.M.; Kori, S.; Cho, K.-K.; Reddy, N. Knowledge extraction of sonophotocatalytic treatment for acid blue 113 dye removal by artificial neural networks. Environ. Res. 2022, 204, 112359. [Google Scholar] [CrossRef] [PubMed]
  195. Orero, B.; Otieno, B.; Ntuli, F.; Lekgoba, T.; Ochieng, A. UV-photodegradation of R6G dye in three-phase fluidized bed reactor: Modeling and optimization using adaptive neuro-fuzzy inference system and artificial neural network. J. Water Process Eng. 2023, 56, 104453. [Google Scholar] [CrossRef]
  196. Abdollahi, Y.; Zakaria, A.; Abbasiyannejad, M.; Masoumi, H.R.F.; Moghaddam, M.G.; Matori, K.A.; Jahangirian, H.; Keshavarzi, A. Artificial neural network modeling of p-cresol photodegradation. Chem. Cent. J. 2013, 7, 96. [Google Scholar] [CrossRef]
  197. Esmaeili, A.; Kiadeh, S.P.H.; Pirbazari, A.E.; Saraei, F.E.K.; Pirbazari, A.E.; Derakhshesh, A.; Tabatabai-Yazdi, F.-S. CdS nanocrystallites sensitized ZnO nanosheets for visible light induced sonophotocatalytic/photocatalytic degradation of tetracycline: From experimental results to a generalized model based on machine learning methods. Chemosphere 2023, 332, 138852. [Google Scholar] [CrossRef]
  198. Qin, N.; Li, L.; Zheng, H.; Cui, Q. CdS with tunable crystalline phase structures: Controllable preparation and enhanced photocatalytic properties. Res. Chem. Intermed. 2023, 49, 5505–5516. [Google Scholar] [CrossRef]
  199. Sheng, C.K.; Aziz, N.A.B.; Alrababah, Y.M. Annealing temperature-dependent CdS phase tunability in improving photocatalytic efficiency towards aquatic dye decomposition. Results Mater. 2023, 19, 100445. [Google Scholar] [CrossRef]
  200. Rasoulifard, M.; Dorraji, M.S.; Amani-Ghadim, A.; Keshavarz-Babaeinezhad, N. Visible-light photocatalytic activity of chitosan/polyaniline/CdS nanocomposite: Kinetic studies and artificial neural network modeling. Appl. Catal. A Gen. 2016, 514, 60–70. [Google Scholar] [CrossRef]
  201. AttariKhasraghi, N.; Zare, K.; Mehrizad, A.; Modirshahla, N.; Behnajady, M.A. Zeolite 4A supported CdS/g-C3N4 type-II heterojunction: A novel visible-light-active ternary nanocomposite for potential photocatalytic degradation of cefoperazone. J. Mol. Liq. 2021, 342, 117479. [Google Scholar] [CrossRef]
  202. Tajmiri, S.; Azimi, E.; Hosseini, M.R.; Azimi, Y. Evolving multilayer perceptron, and factorial design for modelling and optimization of dye decomposition by bio-synthetized nano CdS-diatomite composite. Environ. Res. 2020, 182, 108997. [Google Scholar] [CrossRef]
  203. Firouzi, F.; Pirbazari, A.E.; Saraei, F.E.K.; Tabatabai-Yazdi, F.-S.; Esmaeili, A.; Khodaee, Z. Simultaneous adsorption-photocatalytic degradation of tetracycline by CdS/TiO2 nanosheets/graphene nanocomposites: Experimental study and modeling. J. Environ. Chem. Eng. 2021, 9, 106795. [Google Scholar] [CrossRef]
  204. Ataei, A.; Mehrizad, A.; Zare, K. Photocatalytic degradation of cefazoline antibiotic using zeolite-supported CdS/CaFe2O4 Z-scheme photocatalyst: Optimization and modeling of process by RSM and ANN. J. Mol. Liq. 2021, 328, 115476. [Google Scholar] [CrossRef]
  205. Gu, X.; Lin, S.; Qi, K.; Yan, Y.; Li, R.; Popkov, V.; Almjasheva, O. Application of tungsten oxide and its composites in photocatalysis. Sep. Purif. Technol. 2024, 345, 127299. [Google Scholar] [CrossRef]
  206. Mizar, K.; Mulyati, S.; Arahman, N. Synthesis of Tungsten Trioxide/Hydroxyapatite (WO3/HAp) Photocatalyst For Methylene Blue Degradation. Elkawnie J. Islam. Sci. Technol. 2023, 9, 99–110. [Google Scholar] [CrossRef]
  207. Li, J.; Luo, N.; Wang, Y.; Li, H.; Zhang, T.; Tang, X.; Hu, Z. Construction of photocatalyst by modification of argentum noble metal and hydrogen doping into WO3 nanoparticles: Enhancing the solar energy utilization. Fuel 2023, 352, 128966. [Google Scholar] [CrossRef]
  208. Abubakar, H.L.; Tijani, J.O.; Abdulkareem, A.S.; Egbosiuba, T.C.; Abdullahi, M.; Mustapha, S.; Ajiboye, E.A. Effective removal of malachite green from local dyeing wastewater using zinc-tungstate based materials. Heliyon 2023, 9, e19167. [Google Scholar] [CrossRef] [PubMed]
  209. Sheikhmohammadi, A.; Alamgholiloo, H.; Golaki, M.; Khakzad, P.; Asgari, E.; Rahimlu, F. Cefixime removal via WO3/Co-ZIF nanocomposite using machine learning methods. Sci. Rep. 2024, 14, 13840. [Google Scholar] [CrossRef] [PubMed]
  210. Kumar, U.; Arunachalam, A.; Feit, C.; Berriel, S.N.; Basu, K.; Banerjee, P.; Seal, S. Real-time artificial intelligence enhanced defect engineering in CeO2 nanostructures. J. Vac. Sci. Technol. A 2023, 41, 062409. [Google Scholar] [CrossRef]
  211. Fulzele, N.N.; Bhanvase, B.A.; Pandharipande, S.L. Sonochemically prepared rGO/Ag3PO4/CeO2 nanocomposite photocatalyst for effective visible light photocatalytic degradation of methylene dye and its prediction with ANN modeling. Mater. Chem. Phys. 2022, 292, 126809. [Google Scholar] [CrossRef]
  212. Hasanzadeh, M.; Farahani, M.D.; Far, H.S.; Lebouachera, S.E.I. Modeling of textile dye removal from aqueous solution with a Zr-MOF framework: Design of experiments and artificial neural network approaches. Emergent Mater. 2024, 7, 2583–2593. [Google Scholar] [CrossRef]
  213. da Silva, M.D.C.R.; Druzian, D.M.; Brum, L.F.W.; dos Santos, C.; Pavoski, G.; Espinosa, D.C.R.; Ruiz, Y.P.M.; Galembeck, A.; da Silva, W.L. Green synthesis of ZrO2/PdO-NPs for photodegradation of anionic dyes: Photocatalytic activity and machine learning modelling. J. Mol. Liq. 2024, 410, 125581. [Google Scholar] [CrossRef]
  214. Nademi, M.; Moradi, G.; Mansouri, M. A comprehensive study on the photocatalytic activity of CuO-doped ZrO2–ZnO nanocomposites under visible light. Inorg. Nano-Met. Chem. 2022, 52, 1383–1395. [Google Scholar] [CrossRef]
  215. Sethi, S.; Dhir, A.; Arora, V. Photocatalysis based hydrogen production and antibiotic degradation prediction using neural networks. React. Kinet. Mech. Catal. 2023, 136, 3283–3297. [Google Scholar] [CrossRef]
  216. Capodaglio, A.G.; Callegari, A. Use, potential, needs, and limits of AI in wastewater treatment applications. Water 2025, 17, 170. [Google Scholar] [CrossRef]
  217. Mai, H.; Le, T.C.; Chen, D.; Winkler, D.A.; Caruso, R.A. Machine learning for electrocatalyst and photocatalyst design and discovery. Chem. Rev. 2022, 122, 13478–13515. [Google Scholar] [CrossRef] [PubMed]
  218. Ganthavee, V.; Fernando, M.M.; Trzcinski, A.P. Monte carlo simulation, artificial intelligence and machine learning-based modelling and optimization of three-dimensional electrochemical treatment of Xenobiotic Dye wastewater. Environ. Process. 2024, 11, 41. [Google Scholar] [CrossRef]
  219. Muhammad, R.; Mahboob, M.; Mustafa, K.; Khan, M.; Musaddiq, S.; Mahboob, R.M.S. Artificial Intelligence in Waste Management/Wastewater Treatment. In Omics for Environmental Engineering and Microbiology Systems; CRC Press: Boca Raton, FL, USA, 2022; pp. 493–507. [Google Scholar]
  220. Qiu, X. The application of artificial intelligence–artificial neural networks–in wastewater treatment. Proc. E3S Web Conf. 2023, 393, 03003. [Google Scholar] [CrossRef]
  221. Lowe, M.; Qin, R.; Mao, X. A review on machine learning, artificial intelligence, and smart technology in water treatment and monitoring. Water 2022, 14, 1384. [Google Scholar] [CrossRef]
  222. Hutchinson, M.; Antono, E.; Gibbons, B.; Paradiso, S.; Ling, J.; Meredig, B. Overcoming data scarcity with transfer learning. arXiv 2017, arXiv:1711.05099. [Google Scholar] [CrossRef]
  223. Jiang, Z.; Hu, J.; Tong, M.; Samia, A.C.; Zhang, H.; Yu, X. A novel machine learning model to predict the photo-degradation performance of different photocatalysts on a variety of water contaminants. Catalysts 2021, 11, 1107. [Google Scholar] [CrossRef]
Figure 1. Schematic illustration of the photocatalytic degradation mechanism under sunlight irradiation. When exposed to sunlight, electrons (e) in the valence band (VB) of the photocatalyst are excited to the conduction band (CB), leaving behind positively charged holes (h+). These charge carriers generate reactive oxygen species (ROS), such as superoxide radicals (•O2) and hydroxyl radicals (•OH), which actively degrade various water pollutants, including heavy metals, dyes, organic compounds, and bacteria, into harmless byproducts like water (H2O) and carbon dioxide (CO2).
Figure 1. Schematic illustration of the photocatalytic degradation mechanism under sunlight irradiation. When exposed to sunlight, electrons (e) in the valence band (VB) of the photocatalyst are excited to the conduction band (CB), leaving behind positively charged holes (h+). These charge carriers generate reactive oxygen species (ROS), such as superoxide radicals (•O2) and hydroxyl radicals (•OH), which actively degrade various water pollutants, including heavy metals, dyes, organic compounds, and bacteria, into harmless byproducts like water (H2O) and carbon dioxide (CO2).
Ai 06 00258 g001
Figure 2. Illustration of the key pathways involved in photocatalytic degradation. (A) Superoxide radical-mediated mechanism: Pollutants interact with superoxide radicals (•O2), forming intermediate species that subsequently decompose into non-toxic byproducts. (B) Hydroxyl radical-mediated mechanism: Pollutants react with hydroxyl radicals (•OH), generating intermediates that are further oxidized into less harmful or inert substances. These radical species play a crucial role in the oxidative breakdown of organic contaminants during the photocatalytic process.
Figure 2. Illustration of the key pathways involved in photocatalytic degradation. (A) Superoxide radical-mediated mechanism: Pollutants interact with superoxide radicals (•O2), forming intermediate species that subsequently decompose into non-toxic byproducts. (B) Hydroxyl radical-mediated mechanism: Pollutants react with hydroxyl radicals (•OH), generating intermediates that are further oxidized into less harmful or inert substances. These radical species play a crucial role in the oxidative breakdown of organic contaminants during the photocatalytic process.
Ai 06 00258 g002
Figure 3. Schematic representation of the factors influencing AI model performance in predicting photocatalytic degradation efficiency. The input layer consists of multiple key parameters, including temperature, light intensity and wavelength, pH, chemical additives, photocatalyst properties, contaminant type, reactant concentration, and catalyst dosage. These variables are processed through interconnected hidden layers of the AI model, where weighted neurons learn complex, nonlinear relationships. The model ultimately generates a predicted output representing the photocatalytic degradation efficiency. This approach enables the identification of optimal operating conditions to maximize performance in wastewater treatment applications.
Figure 3. Schematic representation of the factors influencing AI model performance in predicting photocatalytic degradation efficiency. The input layer consists of multiple key parameters, including temperature, light intensity and wavelength, pH, chemical additives, photocatalyst properties, contaminant type, reactant concentration, and catalyst dosage. These variables are processed through interconnected hidden layers of the AI model, where weighted neurons learn complex, nonlinear relationships. The model ultimately generates a predicted output representing the photocatalytic degradation efficiency. This approach enables the identification of optimal operating conditions to maximize performance in wastewater treatment applications.
Ai 06 00258 g003
Figure 4. A visual representation of the efficiency of different dopants for methylene blue degradation, redrawn in Origin using data extracted from various research articles [90,91,92,93,94].
Figure 4. A visual representation of the efficiency of different dopants for methylene blue degradation, redrawn in Origin using data extracted from various research articles [90,91,92,93,94].
Ai 06 00258 g004
Figure 5. PRISMA 2020 diagram of the study selection.
Figure 5. PRISMA 2020 diagram of the study selection.
Ai 06 00258 g005
Figure 6. Shows the classification of AI techniques applied to pollutant removal in wastewater treatment. These techniques are categorized into three main types: supervised learning, unsupervised learning, and reinforcement learning. Among them, supervised learning is the most commonly used, particularly for optimizing photocatalytic processes and aiding in catalyst design.
Figure 6. Shows the classification of AI techniques applied to pollutant removal in wastewater treatment. These techniques are categorized into three main types: supervised learning, unsupervised learning, and reinforcement learning. Among them, supervised learning is the most commonly used, particularly for optimizing photocatalytic processes and aiding in catalyst design.
Ai 06 00258 g006
Figure 7. SVM (support vector machine) model for classification. The red and green data points indicate two distinct classes: Class 1 and Class 2. Part (A) shows a scenario in which the classes are linearly separable. A straight hyperplane is created to maximize the margin between the nearest data points in each class (known as support vectors), resulting in the most efficient and accurate classification. Part (B) deals with cases in which the classes cannot be separated by a straight line. Here, the SVM employs a kernel function to transform the input data into a higher-dimensional space (e.g., from 2D to 3D), allowing the formation of a nonlinear hyperplane that effectively divides the classes and improves classification performance.
Figure 7. SVM (support vector machine) model for classification. The red and green data points indicate two distinct classes: Class 1 and Class 2. Part (A) shows a scenario in which the classes are linearly separable. A straight hyperplane is created to maximize the margin between the nearest data points in each class (known as support vectors), resulting in the most efficient and accurate classification. Part (B) deals with cases in which the classes cannot be separated by a straight line. Here, the SVM employs a kernel function to transform the input data into a higher-dimensional space (e.g., from 2D to 3D), allowing the formation of a nonlinear hyperplane that effectively divides the classes and improves classification performance.
Ai 06 00258 g007
Figure 8. A schematic illustration of an artificial neural network (ANN) used to forecast pollutant degradation efficiency. The model accepts many input variables (Xn), such as catalyst concentration, pollutant concentration, and reaction time, which are gathered from experiments. These inputs are routed through several interconnected hidden layers (h1, h2, h3, and h4), in which the network learns complex patterns and relationships by adjusting weights and biases to reduce prediction error. The final output node (Y) produces the expected deterioration efficiency, represented as a percentage, providing information about the system’s performance.
Figure 8. A schematic illustration of an artificial neural network (ANN) used to forecast pollutant degradation efficiency. The model accepts many input variables (Xn), such as catalyst concentration, pollutant concentration, and reaction time, which are gathered from experiments. These inputs are routed through several interconnected hidden layers (h1, h2, h3, and h4), in which the network learns complex patterns and relationships by adjusting weights and biases to reduce prediction error. The final output node (Y) produces the expected deterioration efficiency, represented as a percentage, providing information about the system’s performance.
Ai 06 00258 g008
Figure 9. The feed-forward neural network (FFNN) model. Part (A) describes the basic design, in which input variables (Xn) are passed through a hidden layer (Hn) to produce an output (y). Part (B) provides a more detailed depiction, highlighting how inputs are combined with weighted sums and processed by activation functions in the hidden layer. The model additionally includes bias terms (b) to alter learning, eventually generating the final predicted output.
Figure 9. The feed-forward neural network (FFNN) model. Part (A) describes the basic design, in which input variables (Xn) are passed through a hidden layer (Hn) to produce an output (y). Part (B) provides a more detailed depiction, highlighting how inputs are combined with weighted sums and processed by activation functions in the hidden layer. The model additionally includes bias terms (b) to alter learning, eventually generating the final predicted output.
Ai 06 00258 g009
Figure 10. The structure of a simple neural network model for predicting pollutant degradation. The input layer represents experimental variables such as dye concentration, catalyst dose, time, and other relevant characteristics. The output layer is fully connected to each input node through weighted connections (colored arrows), which determine each input’s influence on the output. Based on the relationships identified during model training, the output layer produces the predicted degradation efficiency.
Figure 10. The structure of a simple neural network model for predicting pollutant degradation. The input layer represents experimental variables such as dye concentration, catalyst dose, time, and other relevant characteristics. The output layer is fully connected to each input node through weighted connections (colored arrows), which determine each input’s influence on the output. Based on the relationships identified during model training, the output layer produces the predicted degradation efficiency.
Ai 06 00258 g010
Figure 11. Multi-layer neural network model. The structure includes an input layer x1, x2, …, xn. They are handled by the use of linked hidden layers. To extract significant patterns from the data, each hidden layer applies nonlinear activations and weighted transformations. The predicted value, yn, which is the result of the last output layer, shows how well the model captures intricate relationships in the input data. This structure has the capacity to represent high-dimensional and nonlinear interactions.
Figure 11. Multi-layer neural network model. The structure includes an input layer x1, x2, …, xn. They are handled by the use of linked hidden layers. To extract significant patterns from the data, each hidden layer applies nonlinear activations and weighted transformations. The predicted value, yn, which is the result of the last output layer, shows how well the model captures intricate relationships in the input data. This structure has the capacity to represent high-dimensional and nonlinear interactions.
Ai 06 00258 g011
Figure 12. Radial basis function (RBF) neural network model. The network receives multiple inputs and utilizes various activation functions within the hidden layer to generate the final model output. An input layer, a hidden layer with activation functions, and an output layer make up this simple feed-forward neural network architecture. The model may learn intricate associations in the data because every neuron in a layer is fully connected to the neurons in the layer below.
Figure 12. Radial basis function (RBF) neural network model. The network receives multiple inputs and utilizes various activation functions within the hidden layer to generate the final model output. An input layer, a hidden layer with activation functions, and an output layer make up this simple feed-forward neural network architecture. The model may learn intricate associations in the data because every neuron in a layer is fully connected to the neurons in the layer below.
Ai 06 00258 g012
Figure 13. An RNN architecture used for predictive modeling is shown schematically. The network consists of an input layer X1, X2, …, Xn that receives information, one or more hidden layers that use activation functions and weighted connections to execute nonlinear transformations, and an output layer that generates the final prediction, y. Throughout the training process, the arrows show which way data flows, and learning occurs through interconnected neurons.
Figure 13. An RNN architecture used for predictive modeling is shown schematically. The network consists of an input layer X1, X2, …, Xn that receives information, one or more hidden layers that use activation functions and weighted connections to execute nonlinear transformations, and an output layer that generates the final prediction, y. Throughout the training process, the arrows show which way data flows, and learning occurs through interconnected neurons.
Ai 06 00258 g013
Figure 14. Machine learning algorithms for predicting pollutant degradation are gradually evaluated and optimized. The ordered model development process, which started with a single decision tree and produced suboptimal performance, is depicted in the figure. Ensemble techniques were introduced to improve prediction accuracy: random forest, which uses bagging for robustness; XGBoost (Extreme Gradient Boosting), which uses regularization and weighted data handling; and gradient boosting, which iteratively improves predictions by minimizing residual errors. By moving from simple to complex methods for predicting the best catalytic performance, this flow demonstrates the reasoning behind model selection.
Figure 14. Machine learning algorithms for predicting pollutant degradation are gradually evaluated and optimized. The ordered model development process, which started with a single decision tree and produced suboptimal performance, is depicted in the figure. Ensemble techniques were introduced to improve prediction accuracy: random forest, which uses bagging for robustness; XGBoost (Extreme Gradient Boosting), which uses regularization and weighted data handling; and gradient boosting, which iteratively improves predictions by minimizing residual errors. By moving from simple to complex methods for predicting the best catalytic performance, this flow demonstrates the reasoning behind model selection.
Ai 06 00258 g014
Figure 15. All the inclusive processes for designing and optimizing experiments with AI. The procedure starts with gathering information from databases, experimental work, and literature reviews. Next, a suitable AI model is chosen, and software is designed to incorporate both experimental data and model-defined parameters. For ongoing development and increased prediction accuracy, this system facilitates a dynamic feedback loop.
Figure 15. All the inclusive processes for designing and optimizing experiments with AI. The procedure starts with gathering information from databases, experimental work, and literature reviews. Next, a suitable AI model is chosen, and software is designed to incorporate both experimental data and model-defined parameters. For ongoing development and increased prediction accuracy, this system facilitates a dynamic feedback loop.
Ai 06 00258 g015
Table 1. Different dopants are used in methylene blue degradation by artificial intelligence photocatalysis to predict its efficiency.
Table 1. Different dopants are used in methylene blue degradation by artificial intelligence photocatalysis to predict its efficiency.
Sr#DopantAI ModelDegradation EfficiencyTimeReference
1Sulfur–nitrogen codoped
Fe2O3 nanostructure
ANN95%5 min[90]
2ZnO/MgOANN99%174 min[91]
3Nanoscale zero-valent iron (nZVI)ANN100%30 min[92]
4Ho-CaWO4 nanoparticlesANN71.17%15.16 min[93]
5Graphene oxide/chitosan (GO/CS)ANN90.34%125 min[94]
Table 2. Specialized AI/ML platforms for materials science.
Table 2. Specialized AI/ML platforms for materials science.
Platform/ToolTypeKey FeaturesApplication AreasRef (Accessed on 8 September 2025)
Materials ProjectDatabase and ML ToolsMaterials database based on DFT with machine learning methods for predicting propertiesBattery materials, thermodynamic stability, and crystal structureshttps://next-gen.materialsproject.org/ml
AFLOWFramework and DatabaseData production for material attributes that is automatedAnalysis of mechanical properties, symmetry, and high-throughput screeninghttps://aflowlib.org/
CitrinationAI/ML PlatformMaterials discovery powered by machine learning (Citrine Informatics)Material selection, property prediction, and process optimizationhttps://citrine.io/
NOMADRepository and ToolkitML-ready data and analysis tools for materialsAnalysis of electronic structures and dataset benchmarkinghttps://nomad-lab.eu/nomad-lab/
MatminerPython LibraryTools for materials data feature extraction and machine learningFeature development and data mininghttps://pypi.org/project/matminer/
AtomateWorkflow AutomationHandles procedures for high quantities of materialsElectronic framework and synthesis path modelinghttps://atomate.org/
ASEPython LibrarySetting up and analyzing an atomic modelSimulations using DFT/MD and modeling of the manufacturing processhttps://pypi.org/project/ase/
MODNetML Model FrameworkProperty prediction using materials descriptorsSupervised learning from structured datahttps://github.com/ZHKKKe/MODNet
DeepChemML LibraryDeep learning in chemistry and materials scienceQuantum chemistry and molecule/material property predictionhttps://deepchem.io/
Open Catalyst ProjectDataset + ModelML models for catalyst discoveryReaction energy prediction and catalyst screeninghttps://opencatalystproject.org/
MEGNetGraph Neural NetworkGNN models for material property predictionsPrediction from atomic connectivity graphshttps://opencatalystproject.org/
QMOF DatabaseDataset + ModelsData about MOFs from quantum chemistryGas storage and electronic and thermal propertieshttps://github.com/Andrew-S-Rosen/QMOF
SISSOCompressed Sensing ML ToolIdentifying descriptors using sparsifying agentsPredicting material efficiency with regression modelinghttps://github.com/rouyang2017/SISSO
SchNetPackDeep Learning ModelLearning fundamental interactions from start to finishDynamics of molecules and property forecastinghttps://schnetpack.readthedocs.io/en/latest/
TPOTAutoML ToolOptimizing ML pipelines with genetic programmingPredicting the behavior of materials and creating auto modelshttps://epistasislab.github.io/tpot/latest/
Polymer GenomeML PlatformML for predicting polymer propertiesElectrical power, thermal energy, and mechanical characteristicshttps://www.polymergenome.org/
BigSMILESPolymer RepresentationPolymer uniform representation for machine learning inputModeling the structure and properties of polymershttps://olsenlabmit.github.io/BigSMILES/docs/line_notation.html
Table 3. General-purpose AI/ML frameworks in materials science.
Table 3. General-purpose AI/ML frameworks in materials science.
Framework/ToolTypeKey FeaturesUse in Materials ScienceRef (Accessed on 8 September 2025)
Scikit-learnML Library (Python)Traditional machine learning algorithms (e.g., SVM, RF, PCA)Quick prototyping, grouping, regression, and classificationhttps://scikit-learn.org/stable/
TensorFlowDeep Learning FrameworkBuilding neural networks and machine learning from scratchVirtual models, GNNs, and deep neural networks for predicting propertieshttps://www.tensorflow.org/
KerasHigh-level DL APINeural network protocol that is simple to use (TensorFlow as backend)CNNs/RNNs for structure–property estimates and spectral informationhttps://keras.io/
PyTorchDeep Learning FrameworkA flexible deep learning system based on graphsGNNs and deep learning for simulated and structured recognitionhttps://pytorch.org/
XGBoostGradient Boosting FrameworkEffective gradient boosting for classification and regressionQuick and precise material property predictionhttps://xgboost.ai/
LightGBMGradient Boosting FrameworkAcceleration and memory efficiency optimizationPredicting properties with high-dimensional informationhttps://lightgbm.readthedocs.io/en/stable/
Auto-sklearnAutoML LibraryHyperparameter-tuning and robotic machine learningQuick creation of forecasting modelshttps://pypi.org/project/auto-sklearn/
DGLGNN FrameworkPerforming deep learning using graphs (supports PyTorch/TensorFlow)Crystal framework and interatomic interactions modelinghttps://www.dgl.ai/
PyCaretML LibraryML model assessment and training made simplerRapid implementation of models and assessmenthttps://pycaret.org/
Table 4. Titanium dioxide (TiO2) used as a catalyst to degrade different pollutants using AI models.
Table 4. Titanium dioxide (TiO2) used as a catalyst to degrade different pollutants using AI models.
Sr#Pollutant DegradedStructure of PollutantCatalystAI Method UsedLight SourceFactor EffectsRef.
1Methylene BlueAi 06 00258 i001Fe3O4TiO2
Ag magnetic nanocomposite
ANNUV
lamp
Initial dye concentration, pH, and temperature[177]
2Malachite green dyeAi 06 00258 i002TiO2ANN, BBDUV lightCatalyst dosage, time, and initial dye concentration[178]
3Selenium Se (VI)_TiO2BiOBr fabricANN, LSTMVisible lightMachine learning models, recyclability, light, and catalyst stability[174]
4Congo redAi 06 00258 i003Bi–TiO2 nanomaterialsRF, GBDT, XG BoostVisible lightInitial dye concentration, pH, and temperature[179]
5Acid red 14 (AR14)Ai 06 00258 i004TiO2RBF, ANFISUV lightIrradiation time, flow rate, and catalyst concentration[180]
6Tetracycline (TC)Ai 06 00258 i005Cobalt atoms as a co-catalyst on TiO2 nanosheetsANN, ANFISUV,
visible light
Co catalyst dose, time of irradiation[181]
7Polycyclic aromatic hydrocarbons (PAHs)_Rutile TiO2ANNUV-C lightUV wavelength, temperature, and catalyst concentration[182]
8Beta-naphtholAi 06 00258 i006(TiO2)
NPs
ANN-PSO and ANFIS-PSOUV
light
Aeration rate, acidity, catalyst content, and impurity concentration[183]
9Amoxicillin (AMX)Ai 06 00258 i007Ni2P–TiO2 (NPT)ANNUV irradiationpH, catalyst dose, and irradiation time[184]
10Rhodamine B (RhB)Ai 06 00258 i008Nd-TiO2ANNUV
light, solar light
Doping concentration, light source, presence of humic acid, and CaCl2[185]
11TartrazineAi 06 00258 i009TiO2ANNSolar lightpH, TiO2 concentration, initial pollutant concentration, and solar radiation intensity[186]
122,4-dichlorophenol (2,4-DCP)Ai 06 00258 i010(Fe3O4/TiO2/Ag), TiO2SGB, ANN, ANFIS, GA-ANFIS, PSO-ANFISUV,
visible light
pH, temperature, light intensity, pollutant nature, and type of catalyst[32]
13Cetirizine hydrochlorideAi 06 00258 i011(Cu–TiO2) nanoparticlesSVM with IGWOUV,
visible light
Copper loading, solution pH, catalyst dosage, and initial pollutant concentration[88]
Table 5. Zinc oxide catalysts that degrade different pollutants using an AI model.
Table 5. Zinc oxide catalysts that degrade different pollutants using an AI model.
Sr#Pollutant DegradedStructure of PollutantCatalystAI Method UsedLight SourceFactor EffectRef.
1Methylene blue (MB)Ai 06 00258 i012ZnO/MgOANNUV lightCatalyst dose, initial dye concentration level, and photodegradation time[91]
2Yellow 84 dyeAi 06 00258 i013(ZnO) NPs(GPR), RBF, ANF, MLPUV lightCatalyst dose, initial dye concentration level, and photodegradation time[190]
3Low-density polyethylene (LDPE)_FKMW-ZnO NPsRBFNNES_Pollutant concentrations, catalyst concentrations, time, and pH[145]
4Eosin YAi 06 00258 i014ZnO/SnO2 nanocompositesFFNNUV lightCrystallite size, surface area, absorption edge, TOC values, time of reaction, and catalyst concentration[191]
5Methylene OrangeAi 06 00258 i015ZnO-MgAl layered double hydroxidesANNUV lightTemperature, irradiation time, catalyst amount, and dye concentration[192]
6Red dyeAi 06 00258 i016ZnOANN,
ANFIS
UV lightpH, amount of ZnO, and initial dye concentration[193]
7Acid blue 113 (AB113) dyeAi 06 00258 i017ZnOANNUltrasound irradiationReaction time, pH, ZnO dosage, ultrasonic power, and persulphate dosage[194]
8Rhodamine 6G dyeAi 06 00258 i018TiO2-ZnO/BAC compositeANFIS, ANNUV lightCoupling of material, support of material, and light intensity[195]
9p-cresolAi 06 00258 i019ZnOANNUV irradiationIrradiation time, pH, photocatalyst amount, and concentration of pollutant[196]
10Metronidazole (MNZ)Ai 06 00258 i020ZnFe12O19/BiOI nanocompositeANNUV irradiationContaminant concentration, pH, nanocomposite dosage, and retention time[115]
11Pesticide photodegradation_ZnOCSA-LSSVM, RBF, PSO-ANFIS, MLP-ANNUV, VIS lightIrradiation time, pH, light source, dopant mass proportion, catalyst dose, and starting pesticide concentration[11]
12TetracyclineAi 06 00258 i021CdS/ZnO nanosheetsANN and GBRTVIS lightTemperature, pH, and light intensity[197]
13PhenolAi 06 00258 i022ZnOFe2O3ANN, MLPNNSolar irradiationInitial pollutant concentration, photocatalyst dosage, photocatalysis irradiation time, and solution pH[137]
Table 6. Cadmium sulfides used as catalysts to degrade different pollutants using the AI model.
Table 6. Cadmium sulfides used as catalysts to degrade different pollutants using the AI model.
Sr#Pollutant DegradedStructure of PollutantCatalystAI Method UsedLight SourceFactor EffectReference
1CefoperazoneAi 06 00258 i023CdSg-C3N4ANNVisible lightpH, irradiation period, and catalyst dose[201]
2Methylene blueAi 06 00258 i024Nano CdS diatomiteANNUV lightComposite weight, pH level, dye concentration, and light intensity[202]
3Reactive Blue 19 (RB19)Ai 06 00258 i025CS/PAni/CdS nanocompositeANNVisible lightLight intensity and nanocomposite dosage[200]
4Tetracycline (TC)Ai 06 00258 i026CdS/ZnO nanosheetsANN and GBRTUV and ultrasonic lightCatalyst surface area and light source[197]
5Tetracycline (TC)Ai 06 00258 i027CdS/TiO2 nanosheets/graphene nanocompositesANN, ANFISVisible lightCdS molar ratio, surface area, and
light intensity
[203]
6Cefazoline (CFZ)Ai 06 00258 i028CdS-ZnFe2O4 nanocompositesANNVisible lightpH, time, catalyst concentration, and pollutant concentration[204]
Table 7. Tungsten trioxides (WO3) used as catalysts to degrade different pollutants using the AI model.
Table 7. Tungsten trioxides (WO3) used as catalysts to degrade different pollutants using the AI model.
Sr#Pollutant DegradedStructure of PollutantCatalystAI Method UsedLight SourceFactor EffectReference
1Malachite greenAi 06 00258 i029ZnWO4ANNUvpH, contact duration, nano adsorbent dosage, initial MG concentration, and temperature[208]
2CefiximeAi 06 00258 i030WO3/Co-ZIF nanocompositeANN,
SVR
UVpH level,
reaction time, and catalyst amount
[209]
3Methylene blue (MB)Ai 06 00258 i031BiFeO3-WO3 nanocompositeAI(SVM)SunlightLight intensity, dye concentration, and
temperature
[105]
4Methylene blue (MB)Ai 06 00258 i032CuWO4@TiO2HGB modelUVLight intensity, dye concentration, and
temperature
[158]
Table 8. Cesium dioxide as a catalyst that degrades different pollutants using an AI model.
Table 8. Cesium dioxide as a catalyst that degrades different pollutants using an AI model.
Sr#Pollutant DegradedStructure of PollutantCatalystAI Method UsedLight SourceFactor EffectReference
1Acid Orange 7 (AO7) dyeAi 06 00258 i033CeO2ANNUV lightReaction time and pH[88]
2Methylene blue (MB) dyeAi 06 00258 i034rGO/Ag3PO4/CeO2 nanocompositeANNVisible lightInitial dye concentration, pH, reaction time, and temperature[211]
3Cefazoline (CFZ)Ai 06 00258 i035CdS-CaFe2O4-CPANNVisible lightpH of the solution[204]
Table 9. Zirconium oxide as a catalyst that degrades different pollutants using AI models.
Table 9. Zirconium oxide as a catalyst that degrades different pollutants using AI models.
Sr#Pollutant DegradedStructure of PollutantCatalystAI Method UsedLight SourceFactor EffectReference
1Organic dyes *_Zr-MOFANN-pH, contact time, MOF content, and dye concentration[212]
2Congo redAi 06 00258 i036ZrO2/PdO-NPsRF, XGB,
GBR
VisiblepH, CR concentration, catalyst concentration, and irradiation time[213]
3CarbamazepineAi 06 00258 i037TiO2/ZrO2 nano compositeANNUV radiationInitial concentration of pollutant, pH of the solution, catalyst concentration, and time of UV irradiation[125]
4Basic red 46Ai 06 00258 i038CuO-doped ZrO2–ZnO (ZZC) nanocompositesANNLED visible irradiationInitial concentration of pollutant, pH, time, and catalyst loading[214]
5Amoxicillin (AMX)Ai 06 00258 i039ZrO2ANNUV lightpH, catalyst dose, and time[215]
* Wastewater containing multiple dyes was used.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Rehman, A.; Iqbal, M.A.; Haider, M.T.; Majeed, A. Artificial Intelligence-Guided Supervised Learning Models for Photocatalysis in Wastewater Treatment. AI 2025, 6, 258. https://doi.org/10.3390/ai6100258

AMA Style

Rehman A, Iqbal MA, Haider MT, Majeed A. Artificial Intelligence-Guided Supervised Learning Models for Photocatalysis in Wastewater Treatment. AI. 2025; 6(10):258. https://doi.org/10.3390/ai6100258

Chicago/Turabian Style

Rehman, Asma, Muhammad Adnan Iqbal, Mohammad Tauseef Haider, and Adnan Majeed. 2025. "Artificial Intelligence-Guided Supervised Learning Models for Photocatalysis in Wastewater Treatment" AI 6, no. 10: 258. https://doi.org/10.3390/ai6100258

APA Style

Rehman, A., Iqbal, M. A., Haider, M. T., & Majeed, A. (2025). Artificial Intelligence-Guided Supervised Learning Models for Photocatalysis in Wastewater Treatment. AI, 6(10), 258. https://doi.org/10.3390/ai6100258

Article Metrics

Back to TopTop