Modeling and optimization by particle swarm embedded neural network for adsorption of zinc (II) by palm kernel shell based activated carbon from aqueous environment

Application and innovation of artificial intelligence models in wastewater treatment

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

Enhanced adsorption of Bismark Brown R dye by chitosan conjugated magnetic pectin loaded filter mud: A comprehensive study on modeling and mechanisms

Herein, a polymer-based bioadsorbent was prepared by cross-linking chitosan to filter mud and magnetic pectin (Ch-mPC@FM) for the removal of Bismark Brown R dye (BB-R) from wastewater. Morphological characterization analysis indicated that Ch-mPC@FM had a higher surface area and better pore structure than its components. The Artificial Neuron Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were employed to evaluate the simulation and prediction of the adsorption process based on input variables like temperature, pH, dosage, initial BB-R dye concentration, and contact time. ANFIS and ANN demonstrated significant modeling and predictive accuracy, with R2 > 0.93 and R2 > 0.96, and root mean square error < 0.023 and <0.020, respectively. The Langmuir isotherm and the pseudo-second-order kinetic models provided the best fits to the equilibrium and kinetic data. The thermodynamic assessment showed spontaneous and endothermic adsorption with average entropy and enthalpy changes of 119.32 kJ mol-1 K and 403.47 kJ mol-1, respectively. The study of BB-R dye adsorption on Ch-mPC@FM revealed multiple mechanisms, including electrostatic, complexation, pore filling, cation-π interaction, hydrogen bonding, and π-π interactions. The approximate production cost of US$ 5.809 Kg-1 and excellent adsorption capability render Ch-mPC@FM an inexpensive, pragmatic, and ecologically safe bioadsorbent for BB-R dye removal from wastewater.

Thermo-chemical behaviour of Dunaliella salina biomass and valorising their biochar for naphthalene removal from aqueous rural environment

Thermo-chemical behavior of a microalgal biomass; Dunaliella salina was investigated through thermo-gravimetric analyses. Fully-grown D. salina biomass were subjected for biochar conversion using pyrolytic treatment at three distinct heating rates such as 2.5, 5, and 15 °C min-1. The kinetic appraisals were explained by using model-free kinetics viz., Kissinger-Akahira-Sanose, Flynn-Waal-Ozawa and Starink iso-conversional correlations with concomitant evaluation of activation energies (Ea). The Ea value is 194.2 kJ mol-1 at 90% conversion in FWO model, which is higher as compared to other two models. Moisture, volatile substances, and other biochemical components of the biomass were volatilized between 400 and 1000 K in two separate thermo-chemical breakdown regimes. Microscopic and surface characterization analyses were carried out to elucidate the elemental and morphological characteristics of the biomass and biochar. Further, the proficiency of the prepared biochar was tested for removing naphthalene from the watery media. The novelty of the present study lies in extending the applicability of biochar prepared from D. salina for the removal of a model polyaromatic hydrocarbon, naphthalene.

Role of modeling and artificial intelligence in process parameter optimization of biochar: A review

Enhancement of crop yield, conservation and quality upgradation of soil, and efficient water management are the main objectives of sustainable agriculture and mitigating climate change's impact on agriculture. In recent days, biochar, obtained via thermochemical alteration of biomass is becoming a powerful agent for soil and water quality improvement, carbon sequestration, greenhouse gas emission reduction, and heavy metal adsorption. The present study predominantly focuses on various process parameters related to biochar preparation through pyrolysis, their impact on biochar production as well as physicochemical characteristics, and the optimization of such process parameters. Different designs of the experiment (DOE) and optimization techniques including traditional and non-traditional optimizations are discussed in the current review, along with their applicability and shortcomings. Since the biochar preparation process is tedious and energy-consuming, the present review will help to understand the importance of optimization in preparing biochar, thereby leading to a better way to prepare biochar.

Black carbon derived PET plastic bottle waste and rice straw for sorption of Acid Red 27 dye: Machine learning approaches, kinetics, isotherm and thermodynamic studies

This study focuses on the probable use of PET waste black carbon (PETWBC) and rice straw black carbon (RSBC) as an adsorbent for Acid Red 27 (AR 27) adsorption. The prepared adsorbent is characterized by FE-SEM and FT-IR. Batch adsorption experiments were conducted with the influencing of different operational conditions namely time of contact (1-180 min), AR 27 concentration (5-70 mg/L), adsorbent dose (0.5-20 g/L), pH (2-10), and temperature (25-60°C). High coefficient value [PETWBC (R2 = 0.94), and RSBC (R2 = 0.97)] of process optimization model suggesting that this model was significant, where pH and adsorbent dose expressively stimulus removal efficiency including 99.88, and 99.89% for PETWBC, and RSBC at pH (2). Furthermore, the machine learning approaches (ANN and BB-RSM) revealed a good association between the tested and projected value. Pseudo-second-order was the well-suited kinetics, where Freundlich isotherm could explain better equilibrium adsorption data. Thermodynamic study shows AR 27 adsorption is favourable, endothermic, and spontaneous. Environmental friendliness properties are confirmed by desorption studies and satisfactory results also attain from real wastewater experiments. Finally, this study indicates that PETWBC and RSBC could be potential candidates for the adsorption of AR 27 from wastewater.

Optimization of laccase enzyme extraction from spent mushroom waste of Pleurotus florida through ANN-PSO modeling: An ecofriendly and economical approach

The cardinal focus of this study is to optimize the best reaction conditions for maximizing laccase activity from spent mushroom waste (SMW) of Pleurotus florida. Optimization process parameters were studied by the modeling techniques, artificial neural networking (ANN) embedded in particle swarm optimization (PSO), and response surface model (RSM). The best topology of ANN-PSO architecture was obtained on 4-10-1. The R², IOA, MSE, and MAE values of the ANN model were obtained as 0.98785, 0.9939, 0.0023, and 0.0251 while, that of the RSM model were obtained as 0.74290, 0.9210, 0.0244, and 0.1110 respectively. The higher values of R², IOA, and lower values of MSE and MAE of the ANN-PSO model depict that ANN-PSO outperformed compared to RSM and also verified the effectiveness of the ANN-PSO model. The ANN-PSO model performance demonstrates the robustness of the technique in optimizing laccase activity in SMW of P. florida. The optimization results revealed that pH 4.5, time 3 h, solid: solution ratio 1:5, and ABTS concentration of 1 mM was optimal for achieving maximum laccase activity at temperature 30 °C. The enzymatic activity of crude laccase enzyme was obtained as 1.185 U ml^-1 without loss of enzyme activity. Additionally, crude laccase enzyme was 1.74 fold partially purified, and 83.54% of the enzyme was yielded. Out of all the independent process variables, ABTS and pH had an influence on laccase activity. Therefore, we anticipate that the findings of this investigation will reduce the ambiguity in maximizing laccase activity and ease the screening process. This study also highlights the comparative cost evaluation of crude laccase enzyme extracted from P. florida and commercial enzymes. There is a great potential for the utilization of the laccase enzyme extracted from SMW and using it for the degradation of recalcitrant micropollutants. Thus, SMW promises a cost-effective and sustainable approach leading towards circular economy.

Water and wastewater quality prediction: current trends and challenges in the implementation of artificial neural network

Traditional freshwater supplies have been over-abstracted in the current global problem of water scarcity. Through the analysis of complex experimental and real-time data, to improve the activity of water and wastewater treatment (WWT) systems, an artificial neural network (ANN), a computational model inspired by the human brain, and its variants were created. This review paper focuses on recent trends and advances in modeling and simulating different water and wastewater systems using ANN. This study uses ANN in watershed management, impurity removal from wastewater, and wastewater treatment plants. According to the literature review, ANN can predict nonlinear, linear, and complex systems with high accuracy and well control. Finally, the limitations and future scope of ANNs were discussed. ANN proved itself in the prediction of various water and WWT processes. Still, implementation has practical challenges, which include a lack of data availability, poorly built models, timely updates in developed models, and low repeatability. The use of a proper toolbox, faster computing power, and proper domain knowledge makes the practical implementation of ANN successful. As a result, ANN can build a solid foundation for attracting and motivating investigators to work in this region in the forthcoming.

Machine learning analysis and prediction of N2, N2O, and O2 adsorption on activated carbon and carbon molecular sieve

This research focuses on predicting the adsorbed amount of N₂, O₂, and N₂O on carbon molecular sieve and activated carbon using the artificial neural network (ANN) approach. Experimental isotherm data (data set 1242) on adsorbent type, gas type, temperature, and pressure of the process adsorption were used as input datasets for network investigation utilizing the Sips and dual-site Langmuir isotherm models. The network's output has been used to assess the quantity of gas adsorbed. The Gaussian algorithm was applied as a single 98-neuron hidden layer from a radial based functions (RBF) approach, and the Bayesian regularization (BR) algorithm was used as a two-layer network deep learning from a multi-layer perceptron (MLP) approach utilizing 20 neurons. The MLP and RBF networks would have the best mean square error (MSE) after 98 and 100 epochs, respectively, validating efficiencies of 0.00008 and 0.00033, while the square of the coefficient of correlations (R²) was 0.9996 and 0.9993, respectively. The ANN weight matrix generated can accurately predict the adsorption process behavior of different carbon-based adsorbents under various process conditions for air separation and N₂O adsorption. The results of this study have the potential to assist a wide range of process industries.

Optimization and modeling of ammonia nitrogen removal from anaerobically digested liquid dairy manure using vacuum thermal stripping process

During anaerobic digestion (AD) of liquid dairy manure, organic nitrogen converts to ammonia nitrogen (NH₃-N) and subsequently escalates the NH₃-N concentrations in manure. Among different available NH₃-N removal processes treating anaerobically digested liquid dairy manure (ADLDM), vacuum thermal stripping is reported to be an effective technique. However, none of the studies have performed multi-parameter optimization, which is of utmost significance in maximizing process efficiency. In this study, critical operational parameters for vacuum thermal stripping of NH₃-N from ADLDM were optimized and modeled for the first time via integrating grey relational analysis (GRA)-based Taguchi design, response surface methodology (RSM), and RSM-artificial neural network (ANN). The initial experimental trials conducted using the GRA coupled with Taguchi L₁₆ orthogonal array revealed the order of influence of the process parameters on NH₃-N removal as vacuum pressure (kPa) > temperature (°C) > treatment time (min) > mixing speed (rpm) > pH. The values of the first three most influential operating parameters were then further optimized and modeled using RSM and RSM-ANN models. Under the optimized conditions (temperature: 69.6 °C, vacuum pressure: 43.5 kPa, and treatment time: 87.65 min), the NH₃-N removal efficiency of 93.58 ± 0.59 % was experimentally observed and was in line with the RSM and RSM-ANN models' predicted values. While the RSM-ANN model showed a better prediction potential than did the RSM model when compared statistically. Moreover, the nutrient contents (nitrogen, N and sulfur, S) of the recovered NH₃-N as ammonium sulfate ((NH₄)₂SO₄) were in reasonable agreement with the market-available (NH₄)₂SO₄ fertilizer. The results presented in this study provide important insights into improving the treatment process performance and will help design and operate future pilot- and full-scale vacuum thermal stripping processes in dairy farms.

Enhanced remediation of lead (II) and cadmium (II) ions from aqueous media using porous magnetic nanocomposites - A comprehensive review on applications and mechanism

Lead and Cadmium, identified as toxic heavy metals, cause significant imbalance in the eco-system due to their tendency to bioaccumulate. Remediation of heavy metals by conventional adsorptive materials suffer demerits related to low efficiency or removal. Among the variety of adsorbent materials used in the adsorption process, metal oxides- and graphene oxide magnetic nanocomposites have gained a considerable attention. The use of nanomaterials may help to reduce this contamination, but after use, they are difficult to remove from water. An added magnetic property to nanomaterials facilitates their retrieval after use. The magnetic properties of these hybrid magnetic nanocomposites, coupled with unique characteristics of organic and inorganic elements, have found extensive application in water treatment technology. Detailed discussion on functionalisation of magnetic nanocomposites and the enhanced performance are presented. Magnetic graphene oxide-covalently functionalized-tryptophan was reported to have the highest adsorption capacity of 766.1 mg/g for remediation of lead (II) ions and graphene oxide exhibited the highest adsorption capacity of 530 mg/g for Cd (II) ions. The adsorption mechanisms for heavy metal ions on the surface of novel adsorbents, particularly lead and cadmium, using magnetic nanocomposites have been explained with reference to the isotherm models studied. The future scope of research in this area of research is proposed.

Efficient, parallelized global optimization of groundwater pumping in a regional aquifer with land subsidence constraints

The design of groundwater exploitation schedules with constraints on pumping-induced land subsidence is a computationally intensive task. Physical process-based groundwater flow and land subsidence simulations are high-dimensional, nonlinear, dynamic and computationally demanding, as they require solving large systems of partial differential equations (PDEs). This work is the first application of a parallelized surrogate-based global optimization algorithm to mitigate land subsidence issues by controlling the pumping schedule of multiple groundwater wellfields over space and time. The application was demonstrated in a 6500 km² region in China, involving a large-scale coupled groundwater flow-land subsidence model that is computationally expensive in terms of computational resources, including runtime and CPU memory for one single evaluation. In addition, the optimization problem contains 50 decision variables and up to 13 constraints, which adds to the computational effort, thus an efficient optimization is required. The results show that parallel DYSOC (dynamic search with surrogate-based constrained optimization) can achieve an approximately 100% parallel efficiency when upscaling computing resources. Compared with two other widely used optimization algorithms, DYSOC is 2-6 times faster, achieving computational cost savings of at least 50%. The findings demonstrate that the integration of surrogate constraints and dynamic search process can aid in the exploration and exploitation of the search space and accelerate the search for optimal solutions to complicated problems.

Adsorption isotherm models: A comprehensive and systematic review (2010-2020)

Among numerous methods developed in purification and separation industries, the adsorption process has received considerable attention due to its inexpensive, facile, and eco-friendly nature. The importance of the adsorption process causes extraordinary endeavors for modeling the adsorption isotherms during the years; thus, myriads of research have been conducted and many reviews have been published. In this paper, we have attempted to gather the most widely used adsorption isotherms and their related definitions, along with examples of correlated work of the recent decade. In the present review, 37 adsorption isotherms with about 400 references have been collected from the research published in the period of 2010-2020. The adsorption isotherms utilized are alphabetically organized for ease of access. The parameters of each isotherm, as well as the applicable definitions, are presented in the table, in addition to being discussed in the text. Another table is provided for the practical use of researchers, featuring the usage of the related isotherms in peer-reviewed studies.

Predictive capability evaluation and optimization of Pb(II) removal by reduced graphene oxide-based inverse spinel nickel ferrite nanocomposite

Pb(II) is a heavy metal that is a prominent contaminant in water contamination. Among the different pollution removal strategies, adsorption was determined to be the most effective. The adsorbent and its type determine the adsorption process's efficiency. As part of this effort, a magnetic reduced graphene oxide-based inverse spinel nickel ferrite (rGNF) nanocomposite for Pb(II) removal is synthesized, and the optimal values of the independent process variables (like initial concentration, pH, residence time, temperature, and adsorbent dosage) to achieve maximum removal efficiency are investigated using conventional response surface methodology (RSM) and artificial neural networks (ANN). The results indicate that the initial concentration, adsorbent dose, residence time, pH, and process temperature are set to 15 mg/L, 0.55 g/L, 100 min, 5, and 30 °C, respectively, the maximum removal efficiency (99.8%) can be obtained. Using the interactive effects of process variables findings, the adsorption surface mechanism was examined in relation to process factors. A data-driven quadratic equation is derived based on the ANOVA, and its predictions are compared with ANN predictions to evaluate the predictive capabilities of both approaches. The R² values of RSM and ANN predictions are 0.979 and 0.991 respectively and confirm the superiority of the ANN approach.

A Review of the Modeling of Adsorption of Organic and Inorganic Pollutants from Water Using Artificial Neural Networks

The application of artificial neural networks on adsorption modeling has significantly increased during the last decades. These artificial intelligence models have been utilized to correlate and predict kinetics, isotherms, and breakthrough curves of a wide spectrum of adsorbents and adsorbates in the context of water purification. Artificial neural networks allow to overcome some drawbacks of traditional adsorption models especially in terms of providing better predictions at different operating conditions. However, these surrogate models have been applied mainly in adsorption systems with only one pollutant thus indicating the importance of extending their application for the prediction and simulation of adsorption systems with several adsorbates (i.e., multicomponent adsorption). This review analyzes and describes the data modeling of adsorption of organic and inorganic pollutants from water with artificial neural networks. The main developments and contributions on this topic have been discussed considering the results of a detailed search and interpretation of more than 250 papers published on Web of Science ® database. Therefore, a general overview of the training methods, input and output data, and numerical performance of artificial neural networks and related models utilized for adsorption data simulation is provided in this document. Some remarks for the reliable application and implementation of artificial neural networks on the adsorption modeling are also discussed. Overall, the studies on adsorption modeling with artificial neural networks have focused mainly on the analysis of batch processes (87%) in comparison to dynamic systems (13%) like packed bed columns. Multicomponent adsorption has not been extensively analyzed with artificial neural network models where this literature review indicated that 87% of references published on this topic covered adsorption systems with only one adsorbate. Results reported in several studies indicated that this artificial intelligence tool has a significant potential to develop reliable models for multicomponent adsorption systems where antagonistic, synergistic, and noninteraction adsorption behaviors can occur simultaneously. The development of reliable artificial neural networks for the modeling of multicomponent adsorption in batch and dynamic systems is fundamental to improve the process engineering in water treatment and purification.

Data-Driven Machine Learning Intelligent Tools for Predicting Chromium Removal in an Adsorption System

This study investigates chromium removal onto modified maghemite nanoparticles in batch experiments based on a central composite design. The effect of modified maghemite nanoparticles on the adsorptive removal of chromium was quantitatively elucidated by fitting the experimental data using artificial neural network (ANN) and adaptive neuro-fuzzy interference system (ANFIS) modeling approaches. The ANN and ANFIS models, relating the inputs, i.e., pH, adsorbent dose, and initial chromium concentration to the output, i.e., chromium removal efficiency (RE), were developed by comparing the predicted value with that of the experimental values. The RE of chromium ranged from 49.58% to 92.72% under the influence of varying pH (i.e., 2.6–9.4) and adsorbent dose, i.e., 0.8 g/L to 9.2 g/L. The developed ANN model fits the experimental data exceptionally well with correlation coefficients of 1.000 and 0.997 for training and testing, respectively. In addition, the Pearson’s Chi-square measure (χ2) of 0.0004 and 0.0673 for the ANN and ANFIS models, respectively, indicated the superiority of ANN over ANFIS. However, a small discrepancy in the predictability of the ANFIS model was observed owing to the fuzzy rule-based complexity and overtraining of data. Thus, the developed models can be used for the online prediction of RE onto synthesized maghemite nanoparticles with different sets of input parameters and it can also predict the operational errors in the system.

Modeling defluoridation of real-life groundwater by a green adsorbent aluminum/olivine composite: Isotherm, kinetics, thermodynamics and novel framework based on artificial neural network and support vector machine

The kinetic, isotherm, and thermodynamics of adsorptive removal of fluoride from the real-life groundwater was evaluated to assess the applicability of a green adsorbent, aluminum/olivine composite (AOC). The isotherm and kinetics were demonstrated by the Freundlich and Elovich model indicating significant surface heterogeneity of AOC in favouring the fluoride sorption. The fluoride removal efficiency of AOC was achieved as 87.5% after 240 min of contact time. The diffusion kinetic model exhibited that both the intra-particle and film diffusion together control the rate-limiting step of fluoride adsorption. A negative value of ΔG⁰ (-19.919 kJ/mol) at 303 K confirmed the spontaneous adsorption reaction of fluoride, and its endothermic nature was supported by the negative value of ΔH⁰ (39.504 kJ/mol). A novel framework for a predictive model by artificial neural network (ANN), and support vector machine (SVM) considering the real and synthetic fluoride-containing water was developed to assess the efficiency of adsorbent under different scenarios. ANN model was observed to be statistically significant (RMSE: 1.0955 and R²: 0.9982) and the proposed method may be instrumental in a similar area for benchmarking the synthetic and real-life samples. The low desorption potential of the spent adsorbent exhibited safe disposal of sludge and the secondary-pollutant-free treated water by the efficient and green adsorbent AOC enhanced the field-scale applicability of the green technology.

Optimization and Modeling of Ammonia Nitrogen Removal from High Strength Synthetic Wastewater Using Vacuum Thermal Stripping

Waste streams with high ammonia nitrogen (NH3-N) concentrations are very commonly produced due to human intervention and often end up in waterbodies with effluent discharge. The removal of NH3-N from wastewater is therefore of utmost importance to alleviate water quality issues including eutrophication and fouling. In the present study, vacuum thermal stripping of NH3-N from high strength synthetic wastewater was conducted using a rotary evaporator and the process was optimized and modeled using response surface methodology (RSM) and RSM–artificial neural network (ANN) approaches. RSM was first employed to evaluate the process performance using three independent variables, namely pH, temperature (°C) and stripping time (min), and the optimal conditions for NH3-N removal (response) were determined. Later, the obtained data from the designed experiments of RSM were used to train the ANN for predicting the responses. NH3-N removal was found to be 97.84 ± 1.86% under the optimal conditions (pH: 9.6, temperature: 65.5 °C, and stripping time: 59.6 min) and was in good agreement with the values predicted by RSM and RSM–ANN models. A statistical comparison between the models revealed the better predictability of RSM–ANN than that of the RSM. To the best of our knowledge, this is the first attempt comparing the RSM and RSM–ANN in vacuum thermal stripping of NH3-N from wastewater. The findings of this study can therefore be useful in designing and carrying out the vacuum thermal stripping process for efficient removal of NH3-N from wastewater under different operating conditions.

Optimization for the conditions to prepare sewage sludge derived adsorbent and ciprofloxacin adsorption

In the present study, sewage sludge (SS) was used to synthesize activated carbon (AC) which was further utilized as adsorbent for the removal of ciprofloxacin (CPX) from synthetic wastewater. The adsorbent was prepared by chemical activation method using ZnCl₂ as activating agent. Design of experiments (DOE) approach was explored to determine the optimum operating conditions for the synthesis of AC and CPX removal from the wastewater. The optimum conditions for AC synthesis (i.e., carbonization temperature = ~500°C, activation time = 30 min, and impregnation ratio = 2.26) were decided based on results for three response parameters, that is, adsorbent yield, methylene blue removal, and iodine number. The synthesized adsorbent showed ~93% CPX removal (initial CPX concentration = 100 mg/L) at the following optimum conditions: adsorbent dose = 1.31 g/L, pH = 7 and reaction time = 12 h. Langmuir isotherm model was best fit to the equilibrium adsorption data (maximum adsorption capacity of SS derived AC = 102 mg/g) whereas pseudo-second order model showed the best fit to adsorption kinetic data (adsorption capacity = 77.5 mg/g). An effort was also made to reduce fresh water requirement for adsorbent synthesis by recycling the wastewater produced during chemical activation of SS. PRACTITIONER POINTS: Experiment design approach was used for optimization of adsorbent preparation conditions and CPX removal conditions by waste derived adsorbent. Sewage sludge derived adsorbent had BET surface area of 564 m² /g which is comparable to commercial activated carbon. 93% CPX adsorption with the sewage sludge derived adsorbent at optimum conditions. Langmuir model better suited the CPX adsorption data. Wastewater recycling and ZnO recovery from wastewater produced during adsorbent synthesis were performed.

Artificial neural networks modeling for lead removal from aqueous solutions using iron oxide nanocomposites from bio-waste mass

Heavy metal ions in aqueous solutions are taken into account as one of the most harmful environmental issues that ominously affect human health. Pb(II) is a common pollutant among heavy metals found in industrial wastewater, and various methods were developed to remove the Pb(II). The adsorption method was more efficient, cheap, and eco-friendly to remove the Pb(II) from aqueous solutions. The removal efficiency depends on the process parameters (initial concentration, the adsorbent dosage of T-Fe3O4 nanocomposites, residence time, and adsorbent pH). The relationship between the process parameters and output is non-linear and complex. The purpose of the present study is to develop an artificial neural networks (ANN) model to estimate and analyze the relationship between Pb(II) removal and adsorption process parameters. The model was trained with the backpropagation algorithm. The model was validated with the unseen datasets. The correlation coefficient adj.R² values for total datasets is 0.991. The relationship between the parameters and Pb(II) removal was analyzed by sensitivity analysis and creating a virtual adsorption process. The study determined that the ANN modeling was a reliable tool for predicting and optimizing adsorption process parameters for maximum lead removal from aqueous solutions.

Process modeling, characterization, optimization, and mechanisms of fluoride adsorption using magnetic agro-based adsorbent

In this study, fluoride removal from polluted potable water using magnetic carbon-based adsorbents derived from agricultural biomass was thoroughly investigated. An experimental matrix is designed considering the interactive effects of independent process variables (pH, adsorbent dose, contact time, and initial fluoride concentration) on the removal efficiency. Isotherms and kinetics studies, as well as anions interactions, were also investigated to understand the adsorption mechanisms further. The model parameters of isotherms and kinetics are estimated using nonlinear differential evolution optimization (DEO). Approaches like adaptive neuro-fuzzy inference system (ANFIS) and response surface methodology (RSM) are implemented to predict the fluoride removal and identify the optimal process values. The optimum removal efficiency of GAC-Fe3O4 (89.34%) was found to be higher than that of PAC-Fe3O4 (85.14%). Kinetics experiments indicated that they follow the intraparticle diffusion model, and adsorption isotherms indicated that they follow Langmuir and Freundlich models. Both PAC-Fe3O4 and GAC-Fe3O4 adsorbents have shown an adsorption capacity of 1.20 and 2.74 mg/g, respectively. The model predictions from ANFIS have a strong correlation with experimental results and superior to RSM predictions. The shape of the contours depicts the nonlinearity of the interactive effects and the mechanisms in the adsorption process.

A Promising Solution for Food Waste: Preparing Activated Carbons for Phenol Removal from Water Streams

Phenol and its derivatives are highly toxic chemicals and are widely used in various industrial applications. Therefore, the industrial wastewater streams must be treated to lower the concentration of phenol before discharge. At the same time, food waste has been a major environmental problem globally and the scientific community is eagerly seeking effective management solutions. The objective of this study was to understand the potential of utilizing food waste as a renewable and sustainable resource for the production of activated carbons for the removal of phenol from water streams. The food waste was pyrolyzed and physically activated by steam. The pyrolysis and activation conditions were optimized to obtain activated carbons with high surface area. The activated carbon with the highest surface area, 745 m2 g-1, was derived via activation at 950 °C for 1 h. A detailed characterization of the physicochemical and morphological properties of the activated carbons derived from food waste was performed and a comprehensive adsorption study was conducted to investigate the potential of using the activated carbons for phenol removal from water streams. The effects of pH, contact time, and initial concentration of phenol in water were studied and adsorption models were applied to experimental data to interpret the adsorption process. A remarkable phenol adsorption capacity of 568 mg g-1 was achieved. The results indicated that the pseudo-second-order kinetic model was better over the pseudo-second-order kinetic model to describe the kinetics of adsorption. The intraparticle diffusion model showed multiple regions, suggesting that the intraparticle diffusion was not the sole rate-controlling step of adsorption. The Langmuir isotherm model was the best model out of Freundlich, Temkin, and Dubinin-Radushkevich models to describe the phenol adsorption on activated carbons derived from food waste. This study demonstrated that food waste could be utilized to produce activated carbon and it showed promising capacity on phenol removal.

Enhancing arsenic sequestration on ameliorated waste molasses nanoadsorbents using response surface methodology and machine-learning frameworks

The development of a novel nanobiosorbent derived from waste molasses for the adsorptive removal of arsenic (As) has been attempted in this study. Waste molasses were chemically ameliorated through a solvothermal route for the incorporation of iron oxide, thereby producing iron oxide incorporated carbonaceous nanomaterial (IOCN). Synthesis of IOCN was confirmed through transmission electron microscopy (TEM), X-ray diffraction (XRD), Fourier transform infrared spectroscopy (FTIR), and atomic emission spectroscopy (AES) analysis. The surface area and porous behavior of IOCN were elucidated by Brunauer-Emmett-Teller (BET) assessments. The experimental conditions for adsorption were first modeled using response surface methodology (RSM) based on the central composite design (CCD), considering the parameters: adsorbate dosage, adsorbent dosage, pH, and contact time. RSM optimizations were improved upon using a three-layer feed-forward multilayer perceptron (MLP) based Artificial Neural Network (ANN) model. Optimization through ANN model resulted in the increase of the maximal As adsorption efficiency to ~ 96% for IOCN. The IOCN isotherm plots show the best fit for the Sips isotherm, and the reaction kinetics follows the pseudo-second-order model, indicating the chemisorption mechanism for As adsorption. Evidence for direct coordination of As to the surface of adsorbents was further confirmed by FTIR spectroscopic studies before and after As adsorption. The high adsorption efficiencies and the low-cost facile synthesis of the IOCN nanosorbent from agro-industrial waste indicate their potential for commercial applications.

Machine learning approach for prediction of paracetamol adsorption efficiency on chemically modified orange peel

High consumption of paracetamol (PCM) has led to the discharge of a large quantity of its metabolite into the environment and there is an urgent need to remove this harmful contaminant in a sustainable manner. In this work, Artificial Neural Network (ANN) was used as a Machine Learning tool for prediction of PCM adsorption efficiency on chemically modified orange peel (CMOP). Orange peel was chemically modified with orthophosphoric acid and then characterized using Scanning Electron Microscopy (SEM) and Fourier Transform Infrared Spectroscopy (FTIR). Thereafter, batch adsorption of PCM on CMOP were conducted at different operating conditions namely: contact time (0-330 min), temperature (30-50 °C) and initial drug concentration (10 mg/L-50 mg/L) to obtain the residual concentration of PCM in solution. Experimental data was used to compute the adsorption efficiency of PCM on CMOP. To predict the adsorption efficiency, different ANN architectures were examined. A neural network structure with Levenberg Marquardt (LM) training algorithm, 17 hidden neurons, and tangent sigmoid transfer function at both the input and output layers gave the best level of prediction. Comparing with experimental data, the optimal model yielded Mean Square Error (MSE), Root Mean Square Error (RMSE), and Correlation coefficient (R²) of 5.8985 × 10^-04, 0.0243 and 0.9958 respectively. The results obtained showed that ANN is efficient in predicting the adsorption efficiency of PCM on CMOP.

Preparation and Characterisation of Activated Carbon from Palm Mixed Waste Treated with Trona Ore

This study explores the use of a novel activating agent and demonstrates the production and characterisation of activated carbon (AC) from a combine palm waste (CPW) in 3:2:1 proportion by weight of empty fruit bunch, mesocarp fibre and palm kernel shell. The resulting biomass was processed by a microwave-assisted method using trona and compared with material produced by conventional routes. These results demonstrate the potential of trona ore as an activating agent and the effectiveness of using a combined palm waste for a single stream activation process. It also assesses the effectiveness of trona ore in the elimination of alcohol, acids and aldehydes; with a focus on increasing the hydrophilicity of the resultant AC. The optimum results for the conventional production technique at 800 °C yielded a material with S_BET 920 m²/g, V_total 0.840 cm³/g, a mean pore diameter of 2.2 nm and an AC yield 40%. The optimum outcome of the microwave assisted technique for CPW was achieved at 600 W, S_BET is 980 m²/g; V_total 0.865 cm³/g; a mean pore diameter 2.2 nm and an AC yield of 42%. Fourier transform infrared spectrometry analyses showed that palm waste can be combined to produce AC and that trona ore has the capacity to significantly enhance biomass activation.

Adsorption kinetic models: Physical meanings, applications, and solving methods

Adsorption technology has been widely applied in water and wastewater treatment, due to its low cost and high efficiency. The adsorption kinetic models have been used to evaluate the performance of the adsorbent and to investigate the adsorption mass transfer mechanisms. However, the physical meanings and the solving methods of the kinetic models have not been well established. The proper interpretation of the physical meanings and the standard solving methods for the adsorption kinetic models are very important for the applications of the kinetic models. This paper mainly focused on the physical meanings, applications, as well as the solving methods of 16 adsorption kinetic models. Firstly, the mathematical derivations, physical meanings and applications of the adsorption reaction models, the empirical models, the diffusion models, and the models for adsorption onto active sites were analyzed and discussed in detail. Secondly, the model validity evaluation equations were summarized based on literature. Thirdly, a convenient user interface (UI) for solving the kinetic models was developed based on Excel software and provided in supplementary information, which is helpful for readers to simulate the adsorption kinetic process.

Modeling and optimization by particle swarm embedded neural network for adsorption of methylene blue by jicama peroxidase immobilized on buckypaper/polyvinyl alcohol membrane

Jicama peroxidase (JP) immobilized functionalized Buckypaper/Polyvinyl alcohol (BP/PVA) membrane was synthesized and evaluated as a promising nanobiocomposite membrane for methylene blue (MB) dye removal from aqueous solution. The effects of independent process variables, including pH, agitation speed, initial concentration of hydrogen peroxide (H₂O₂), and contact time on dye removal efficiency were investigated systematically. Both Response Surface Methodology (RSM) and Artificial Neural Network coupled with Particle Swarm Optimization (ANN-PSO) approaches were used for predicting the optimum process parameters to achieve maximum MB dye removal efficiency. The best optimal topology for PSO embedded ANN architecture was found to be 4-6-1. This optimized network provided higher R² values for randomized training, testing and validation data sets, which are 0.944, 0.931 and 0.946 respectively, thus confirming the efficacy of the ANN-PSO model. Compared to RSM, results confirmed that the hybrid ANN-PSO shows superior modeling capability for prediction of MB dye removal. The maximum MB dye removal efficiency of 99.5% was achieved at pH-5.77, 179 rpm, ratio of H₂O₂/MB dye of 73.2:1, within 229 min. Thus, this work demonstrated that JP-immobilized BP/PVA membrane is a promising and feasible alternative for treating industrial effluent.

Potential of adsorbents from agricultural wastes as alternative fillers in mixed matrix membrane for gas separation: A review

Mixed matrix membrane (MMM), formed by dispersing fillers in polymer matrix, has attracted researchers’ attention due to its outstanding performance compared to polymeric membrane. However, its widespread use is limited due to high cost of the commercial filler which leads to the studies on alternative low-cost fillers. Recent works have focused on utilizing agricultural wastes as potential fillers in fabricating MMM. A membrane with good permeability and selectivity was able to be prepared at low cost. The objective of this review article is to compile all the available information on the potential agricultural wastes as fillers in fabricating MMM for gas separation application. The gas permeation mechanisms through polymeric and MMM as well as the chemical and physical properties of the agricultural waste fillers were also reviewed. Additionally, the economic study and future direction of MMM development especially in gas separation field were discussed.

Evolving multilayer perceptron, and factorial design for modelling and optimization of dye decomposition by bio-synthetized nano CdS-diatomite composite

Design of experiment and hybrid genetic algorithm optimized multilayer perceptron (GA-MLP) artificial neural network have been employed to model and predict dye decomposition capacity of the biologically synthesized nano CdS diatomite composite. Impact of independent variables such as, light (UV: on-off), solution pH (5-8), composite weight (CW: 0.5-1 mg), initial dye concentration (DC: 10-20 mg/l) and contact time (0-120 min), mainly in two levels, were examined to evaluate dye removal efficiency of the composite. According to the developed response surface based on the factorial design, all independent variables shown positive interactive effect on dye removal (UV > CW > pH > DC), as well as the pH-CW mutual interaction, while both UV-DC and CW-DC had antagonistic effect. The pH-CW interaction was more influential than pH and DC. Incorporation of the intermediate measurements of dye removal between the start and final contact times in GA-MLP approach, had found to improve the accuracy and predictability of the GA-MLP model. Based on the closeness of the R² (0.98), root mean square error (1.03), variance accounted for (98.23%), mean absolute error (0.61) and model predictive error (9.46%) to their desirable levels, proposed GA-MLP model outperformed the factorial design model. Finally, optimal parameter choice for maximum dye removal using factorial design and GA-MLP were found as: UV (on), pH (9), CW (1 g) and DC (10 mg/l) and UV (on), pH (8.85), CW (0.92 g), DC (12.3 mg/l) and T (117 0.6 min), respectively.

Continuous Adsorption Modeling and Fixed Bed Column Studies: Adsorption of Tannery Wastewater Pollutants Using Beach Sand

This study deals with the removal of residual pollutants from tanning wastewater by continuous adsorption mechanism, using local sand as a low-cost adsorbent. The possibility of pretreating a complex tannery effluent heavily loaded with a natural material such as sand is significant. The characterization of the adsorbent before and after continuous adsorption was performed by X-ray diffraction, Fourier transform infrared spectroscopy, and scanning electron microscopy. Column studies were also carried out to evaluate the performance of the adsorbent and the efficiency of column adsorption. The adsorption kinetic rate seems to be strongly influenced by certain parameters such as the particle size of the material used, the withdrawal rate of the influent and the height of the adsorbent bed, and optimized parameters were found to be 63 μm, 15 ml·min−1, and 7 cm, respectively, and the color removal has achieved maximum values which vary between 95 and 100%. The results suggest that sand can be used as an economical adsorbent for the removal of color from the wastewater of the tanning industries.

Palm Kernel Shell as an effective adsorbent for the treatment of heavy metal contaminated water

Heavy metal contamination in water causes severe adverse effects on human health. Millions of tons of kernel shell are produced as waste from oil palm plantation every year. In this study, palm oil kernel shell (PKS), an agricultural waste is utilized as effective adsorbent for the removal of heavy metals, namely; Cr6+, Pb2+, Cd2+ and Zn2+ from water. Different parameters of adsorptions; solution pH, adsorbent dosage, metal ions concentration and contact time were optimized. The PKS was found to be effective in the adsorption of heavy metal ions Cr6+, Pb2+, Cd2+ and Zn2+ from water with percentage removal of 98.92%, 99.01%, 84.23% and 83.45%, respectively. The adsorption capacities for Cr6+, Pb2+, Cd2+ and Zn2+ were found to be 49.65 mg/g, 43.12 mg/g, 49.62 mg/g and 41.72 mg/g respectively. Kinetics of adsorption process were determined for each metal ion using different kinetic models like the pseudo-first order, pseudo-second order and parabolic diffusion models. For each metal ion the pseudo-second order model fitted well with correlation coefficient, R2 = 0.999. Different isotherm models, namely Freundlich and Langmuir were applied for the determination of adsorption interaction between metal ions and PKS. Adsorption capacity was also determined for each of the metal ions. PKS was found to be very effective adsorbent for the treatment of heavy metal contaminated water and short time of two hours is required for maximum adsorption. This is a comprehensive study almost all the parameters of adsorptions were studied in detail. This is a cost effective and greener approach to utilize the agricultural waste without any chemical treatment, making it user friendly adsorbent.

Magnetic palm kernel biochar potential route for phenol removal from wastewater

The pollution of water resources due to the disposal of industrial wastes that have organic material like phenol is causing worldwide concern because of their toxicity towards aquatic life, human beings and the environment. Phenol causes nervous system damage, renal kidney disease, mental retardation, cancer and anaemia. In this study, magnetic palm kernel biochar is used for removal of phenol from wastewater. The effect of parameters such as pH, agitation speed, contact time and magnetic biochar dosage are validated using design of experiments. The statistical analysis reveals that the optimum conditions for the highest removal (93.39%) of phenol are obtained at pH of 8, magnetic biochar dosage of 0.6 g, agitation speed at 180 rpm and time of 60 min with the initial concentration of 10 mg/L. The maximum adsorption capacities of phenol were found to be 10.84 mg/g and Langmuir and Freundlich isotherm models match the experimental data very well and adsorption kinetic obeys a pseudo-second order. Hence, magnetic palm kernel can be a potential candidate for phenol removal from wastewater.

Removal of methylene blue via bioinspired catecholamine/starch superadsorbent and the efficiency prediction by response surface methodology and artificial neural network-particle swarm optimization

This paper demonstrates coupling of the artificial neural network (ANN) technique with the particle swarm optimization (PSO) method and compares the performance of ANN-PSO with response surface methodology (RSM) in prediction of the adsorption of methylene blue (MB) by a novel bio-superadsorbent. To this, a starch-based superadsorbent was synthesized using acrylic acid and acryl amid polymers and then catecholamine functional groups were combined onto the surface with oxidative polymerization of dopamine. The adsorption of MB was considered as a function of pH, dye concentration, and contact time. The best topology of the ANN was found to be 3-7-1, and prediction model of the adsorption capacity was demonstrated as a matrix of explicit equations. ANN-PSO is more accurate than RSM. The results revealed that the root-mean-square error, correlation coefficient, and normalized standard deviation for the ANN-PSO are 22.46, 0.99, and 16.83, respectively, while for RSM are 82.89, 0.98, and 65.41, respectively.

Green Synthesis of Iron Oxide Nanoparticles for Lead Removal from Aqueous Solutions

Pb(II) being carcinogenic and one of the heavy metals which always pose a severe threat to human health. Adsorption is a commonly used method for the removal of heavy metal ions as this process possess high efficiency, easy to handle and cost-effective. Iron oxide based nanomaterial were found to be more attractive for the removal of heavy metals from the aqueous solution because of their size, high surface area, and magnetic. Therefore, in this research study, iron oxide nanoparticles modified with tangerine peel extract (T-Fe3O4) and utilized to carry batch adsorption experiments for the removal of lead from aqueous solutions. It was observed that 99% of Pb(II) adsorption removal was achieved with 0.6 g/L of T-Fe3O4 at an initial concentration of metal at 10 ppm and room temperature of 25°C. The adsorption isotherm was found to be monolayer on the homogeneous surface of the adsorbent. Therefore, the green tangerine peel modified iron oxide nanoparticles can be applied for lead removal from water resources for providing clean and hygienic water for a sustainable and healthier life.

A comprehensive review of applications of magnetic graphene oxide based nanocomposites for sustainable water purification

With the rapid growth of industrialization, water bodies are polluted with heavy metals and toxic pollutants. In pursuit of removal of toxic pollutants from the aqueous environment, researchers have been developed many techniques. Among these techniques, magnetic separation has caught research attention, as this approach has shown excellent performance in the removal of toxic pollutants from aqueous solutions. However, magnetic graphene oxide based nanocomposites (MGO) possess unique physicochemical properties including excellent magnetic characteristics, high specific surface area, surface active sites, high chemical stability, tunable shape and size, and the ease with which they can be modified or functionalized. As results of their multi-functional properties, affordability, and magnetic separation capability, MGO's have been widely used in the removal of heavy metals, radionuclides and organic dyes from the aqueous environment, and are currently attracting much attention. This paper provides insights into preparation strategies and approaches of MGO's utilization for the removal of pollutants for sustainable water purification. It also reviews the preparation of magnetic graphene oxide nanocomposites and primary characterization instruments required for the evaluation of structural, chemical and physical functionalities of synthesized magnetic graphene oxide nanocomposites. Finally, we summarized some research challenges to accelerate the synthesized MGO's as adsorbents for the treatment of water pollutants such as toxic and radioactive metal ions and organic and agricultural pollutants.

Modelling dye removal by adsorption onto water treatment residuals using combined response surface methodology-artificial neural network approach

In this study, response surface methodology (RSM)-artificial neural network (ANN) approach was used to optimise/model disperse dye removal by adsorption using water treatment residuals (WTR). RSM was first applied to evaluate the process using three controllable operating parameters, namely WTR dose, initial pH (pH_initial) and dye concentration, and optimal conditions for colour removal were determined. In the second step, the experimental results of the design data of RSM were used to train the neural network along with a non-controllable parameter, the final pH (pH_final). The trained neural networks were used for predicting the colour removal. A colour removal of 52.6 ± 2.0% obtained experimentally at optimised conditions (pH_initial 3.0, adsorbent dose 30 g/L and dye concentration 75 mg/L) was comparable to 52.0% and 52.2% predicted by RSM and RSM-ANN, respectively. This study thus shows that optimising/predicting the colour removal process using the RSM-ANN approach is possible, and it also indicates that adsorption onto WTR could be used as a primary treatment for removal of colour from dye wastewater.

Biosorptive removal of Zn(II) ions by Pongamia oil cake (Pongamia pinnata) in batch and fixed-bed column studies using response surface methodology and artificial neural network

Design of experiment and artificial neural networks (ANN) have been effectively employed to predict the rate of uptake of Zn(II) ions onto defatted pongamia oil cake. Four independent variables such as, pH (2.0-7.0), initial concentration of Zn(II) ions (50-500 mg/L), temperature (30ºC-50 °C), and dosage of biosorbent (1.0-5.0 g/L) were used for the batch mode while the three independent variables viz. flowrate, initial concentration of Zn(II) ions and bed height were employed for the continuous mode. Second-order polynomial equations were then derived to predict the Zn(II) ion uptake rate. The optimum conditions for batch studies was found to be pH: 4.45, metal ion concentration: 462.48 mg/L, dosage: 2.88 g/L, temperature: 303 K and on the other hand the column studies flow rate: 5.59 mL/min, metal ion concentration: 499.3 mg/L and bed height: 14.82 cm. Under these optimal condition, the adsorption capacity was 80.66 mg/g and 66.29 mg/g for batch and column studies, respectively. The same data was fed to train a feed-forward multilayered perceptron, using MATLAB to develop the ANN based model. The predictive capabilities of the two methodologies were compared, by means of the absolute average deviation (AAD) (4.57%), model predictive error (MPE) (4.15%), root mean square error (RMSE) (3.19), standard error of prediction (SEP) (4.23) and correlation coefficient (R) (0.99) for ANN and for RSM AAD (16.27%), MPE (21,25%), RMSE (13.15%), SEP and R (0.96) by validation data. The findings suggested that compared to the prediction ability of RSM model, the properly trained ANN model has better prediction ability. In batch studies, equilibrium data was used to determine the isotherm constants and first and second order rate constants. In column, bed depth service time (BDST) and Thomas model was used to fit the obtained column data.