Advancing Sustainable Wastewater Treatment Using Enhanced Membrane Oil Flux and Separation Efficiency through Experimental-Based Chemometric Learning

Round 1

Reviewer 1 Report

Comments to Authors

Ensure that the manuscript is free from grammatical errors and is written in concise, clear language.

1.       Kindly break the abstract into more structured sections, such as Background, Methods, Results, and Conclusion, to make it even more reader-friendly.

2.       Mention why efficient oil-water separation is crucial, especially in the context of environmental protection and sustainable development. Connect the research to real-world problems, such as oil spills and contamination.

3.       Provide more detail about the methods used to create the ceramic membrane and the superhydrophobic silica sol-gel solutions.

4.       Highlight how AI and computational learning were applied to enhance oil flux and separation efficiency. Mention the specific role of AI in optimizing process parameters and improving oil-water separation. This will help readers understand the novel aspect of your research.

5.     Kindly rewrite all equations and use multipliers as × instead of .

6.       What are the sources of the equation used in this study?

7.       Where are the training and testing data?

8.       How are the results verified?

9.       When introducing the regression models (MLR, SVR, RLR), briefly explain what each model does and why they were chosen. This can provide context for readers who may not be familiar with these techniques.

10.   Explain what SVR-M2 signifies and why it was superior to other modelling techniques.

11.   While you've mentioned statistical metrics (R2, MSE, R, RMSE), briefly define what these metrics measure and why they are essential in evaluating the simulation results.

12.   How might the successful application of AI in membrane-based oil-water separation impact industries and environmental protection efforts? What are the potential next steps for research or practical applications?

 

13.    The conclusions may be written pointwise for clear understanding.

Comments for author File: Comments.pdf

Need some improvement. 

Author Response

Reviewer 1

1. The text needs to go through a formal revision. English, Equation placement, figures style should be unified (font, size,…) use the image format to adjust the aspect ratio instead to adjusting using the corners of the image.

 

Response: Thank you for the suggestion. The English and style of the journal were checked appropriately.

2-    The transitioning from literature to machine learning is vague. It would be better to add discussions on the importance of utilizing machine learning and any potential previous studies on this. (The authors have stated there was no previous similar studies however, utilization of machine learning in different aspect to show its practicability would be helpful)

 

Response: Thank you for the positive comments. We have added the literature review based on the above comments. We have updated the manuscript.

Actions

It is worth mentioning that ML models, specifically chemometric learning, play a fundamental role in optimizing the efficiency and sustainability of wastewater treatment. ML brings data-driven advantages to the field by analyzing large datasets, enabling real-time monitoring and control, enhancing energy efficiency, and aiding resource recovery. It optimizes treatment parameters, predicts water quality, detects anomalies, and contributes to the circular economy by recovering valuable resources from wastewater. Previous studies have showcased the applicability of ML in wastewater treatment. These studies include predictive modelling for parameters like chemical and biological oxygen demand, anomaly detection to address issues like membrane fouling, optimization of treatment systems and resource recovery, and real-time water quality monitoring. Coupling experimental-based chemometric learning with MLs emphasizes the importance of introducing data-driven insights with experimental observations, thus enhancing the advancement of sustainable wastewater treatment solutions. Ultimately, this multidisciplinary approach promises more efficient, cost-effective, and environmentally friendly wastewater treatment processes. For details related to advanced literature Nandi et. al. [1] took the path of modelling, employing both conventional pore-blocking models and the advanced multi-layer feedforward ANN model to interpret the enigmatic behaviour of flux. Chen et. al. [2] introduced a novel group of super hydrophilic hybrid membranes, designed to master the art of oil and water parting. These membranes whispered the secrets of their separation prowess. Rahimzadeh et. al. [3] harnessed the power of the adaptive neuro-fuzzy inference system (ANFIS), an inspired tool capable of taming complex and nonlinear systems. In addition, Ma et. al. [4] showed a dual pH- and ammonia-vapor-responsive polyimide (PI)-based nanofibrous membrane. Zhu et. al. [5] composed a super hydrophilic triumph, fashioning a zwitterionic poly(vinylidene fluoride) (PVDF) membrane through a two-part alchemical process. This membrane bore witness to the transformative power of in situ cross-linking reactions and subsequent sulfonation reactions. Zhang et. al. [6] proposed structures that held the promise of high-efficiency oil-water separation, a biological marvel brought to life in the laboratory. However, Ismail et. al. [7] provided an illuminating panorama of recent approaches and materials that have graced the world of oily wastewater treatment. Their insights painted a canvas of hydrophilic membranes as guardians of purity. Similarly, Usman et. al. [8] explored impressive models, such as SVR and Gaussian process regression (GPR), armouring themselves with the Response Surface Method (RSM). Kang et. al. [6] and Li et. al. [9] worked on oil-water separation.

 

References

[1]      B. K. Nandi, A. Moparthi, R. Uppaluri, and M. K. Purkait, “Treatment of oily wastewater using low cost ceramic membrane: Comparative assessment of pore blocking and artificial neural network models,” Chem. Eng. Res. Des., vol. 88, no. 7, pp. 881–892, 2010, doi: 10.1016/j.cherd.2009.12.005.

[2]      P.-C. Chen and Z.-K. Xu, “Mineral-Coated Polymer Membranes with Superhydrophilicity and Underwater Superoleophobicity for Effective Oil/Water Separation,” Sci. Rep., vol. 3, no. 1, Sep. 2013, doi: 10.1038/srep02776.

[3]      A. Rahimzadeh, F. Z. Ashtiani, and A. Okhovat, “Application of adaptive neuro-fuzzy inference system as a reliable approach for prediction of oily wastewater microfiltration permeate volume,” J. Environ. Chem. Eng., vol. 4, no. 1, pp. 576–584, 2016, doi: 10.1016/j.jece.2015.12.011.

[4]      W. Ma et al., “Dual pH- and ammonia-vapor-responsive electrospun nanofibrous membranes for oil-water separations,” J. Memb. Sci., vol. 537, pp. 128–139, 2017, doi: https://doi.org/10.1016/j.memsci.2017.04.063.

[5]      Y. Zhu, W. Xie, F. Zhang, T. Xing, and J. Jin, “Superhydrophilic In-Situ-Cross-Linked Zwitterionic Polyelectrolyte/PVDF-Blend  Membrane for Highly Efficient Oil/Water Emulsion Separation.,” ACS Appl. Mater. Interfaces, vol. 9, no. 11, pp. 9603–9613, Mar. 2017, doi: 10.1021/acsami.6b15682.

[6]      H. Kang et al., “Superlyophobic anti-corrosive and self-cleaning titania robust mesh membrane with enhanced oil/water separation,” Sep. Purif. Technol., vol. 201, pp. 193–204, 2018, doi: https://doi.org/10.1016/j.seppur.2018.03.002.

[7]      N. H. Ismail et al., “Hydrophilic polymer-based membrane for oily wastewater treatment: A review,” Sep. Purif. Technol., vol. 233, no. August 2019, p. 116007, 2020, doi: 10.1016/j.seppur.2019.116007.

[8]      J. Usman et al., “Intelligent optimization for modelling superhydrophobic ceramic membrane oil flux and oil-water separation efficiency: Evidence from wastewater treatment and experimental laboratory,” Chemosphere, p. 138726, 2023.

[9]      H. Li, P. Mu, J. Li, and Q. Wang, “Inverse desert beetle-like ZIF-8/PAN composite nanofibrous membrane for highly efficient separation of oil-in-water emulsions,” J. Mater. Chem. A, vol. 9, no. 7, pp. 4167–4175, 2021, doi: 10.1039/D0TA08469G.

 

 

 

 

 

3-    The inlets of machine learning to train are still vaguely discussed. Need to clearly state them and how they were gathered from the conducted set of experiments and their conditions.

Response: Thank you for the positive comments. We have added it in the revise version.

Actions

For effective ML models in oil-water separation, data is collected from experiments, involving physical and chemical properties of the membrane, as well as operational conditions like pressure and temperature. This data undergoes preprocessing, including cleaning and normalization. After identifying the most relevant features through techniques like correlation analysis, the data is divided into training and validation sets. The model is then trained on the chosen features to predict separation efficiency, ensuring its predictions are based on real-world experimental conditions and their intricacies.

4-    What are the spinneret specs? Dimensions? Spinning conditions and flow rates?

Response: They are now update in the revise manuscript. We added the text version in the revise manuscript.

Actions

In the spinneret-based process, the following parameters and values are employed: a spinneret diameter of 1.2, internal and external diameters of 2.8 mm and 10 mm respectively, a dope extrusion rate of 10 mL/min, an air gap of 5 cm, a bore fluid injection rate of 10 mL/min, and the use of tap water as both internal and external coagulants. The spinning and external temperatures are maintained at 25°C. These specific settings constitute the operational conditions for the process, which is characterized by its precise control of variables to achieve the desired outcomes.

Parameters	Values
Spinneret diameter	1.2
Internal Diameter (mm)	2.8
External Diameter (mm)	10
Dope extrusion rate (mL/min)	10
Air gap (cm)	5
Bore fluid injection rate (mL/min)	10
Internal and external coagulants	Tap Water
Spinning temperature (oC)	25
External temperature (oC)	25

 

5-    What are the units of m_r and m_t? subscript r and t

Response: The units are for concentration of oil before and after extraction in mg.

 

6-    Figure 3 needs to be in a better quality. Readjust the boxes and their font. Charts and other plots need to be readjusted with the same font and style

Response: Thank you for the observation, we have updated the Figs.

 

7-    The K-fold cross-validation was employed. How many sub-divisions were conducted? Where is there any data not to be used for training and just for validation?

 

Response: Thank you for the positive feedback. We have added it in the revised version. We added the text version in the revised manuscript.

Actions

Prior to the final development of the model the simulation phase, a thorough external validation process was thoroughly conducted. This validation procedure relied on the precise 10-fold cross-validation method, strategically designed to fine-tune model performance, improve model integrity, and minimize potential errors in modelling oil-flux and separation efficiency. This process partitioned the dataset into 10-folds equal subsets, consecutively utilizing one subset for validation while training the model on the remaining nine, repeating this process 10 times to ensure comprehensive assessment of model generalization. The application of 10-fold cross-validation served a dual purpose: to guard against overfitting, ensuring that models learned meaningful patterns instead of memorizing training data, and to identify potential issues with model robustness and consistency. Consequently, this systematic approach enabled the optimization of model parameters and features in models with superior predictive capabilities, well-suited for real-world applications during the subsequent simulation phase of oil-flux and separation efficiency.

 

8-    What software was used? The codes were generated to open access code library was used?

 

Response: Comments well appreciated. We have added it in the revised version. We added the text version in the revised manuscript.

Actions

For model development and coding structure, MATLAB 2022b was used while other simulation was conducted using EViews-10 software. The graphical analysis was conducted using Origin Pro, Microsoft excel and R software.

 

9-    There is no doubt that machine learning can predict data based on what it’s trained on. Would you suggest that this machine learning study would only be applicable for a you home-made membranes considering the dimensions, materials and conditions that were used to fabricate the membranes since as far as I read there are no physical or chemical characteristics involved

 

Response: Thank you for the comment, machine learning models are highly dependent on the data they are trained on. For a study focused on homemade membranes, the predictions are most accurate when applied to those specific membranes, factoring in their unique dimensions, materials, and fabrication conditions. Even without directly considering physical or chemical characteristics, these nuances can be crucial to performance. While the model might offer insights for these particular membranes, its applicability to other types might be limited unless trained on a broader, more diverse dataset that encompasses various membrane characteristics and fabrication methods.

 

10- The machine learning essentially used parameter weighting to predict data. Is there any physical interpretation on how this weighting works?

 

Response: Thank you. In machine learning algorithms such as SVR, RLR, and MLR, weights are assigned to input features to determine their influence on the predicted outcome. These weights can be visualized as the pull or tilt a particular feature exerts on a prediction, with larger weights indicating a more significant influence. While the mathematical derivation of these weights is complex, their relative values provide insights into which features are most crucial for a given problem, effectively serving as a measure of the feature's importance in making accurate predictions.

 

Comments on the Quality of English Language

• The text needs to go through a formal revision. English, Equation placement, figures style should be unified (font, size,…) use the image format to adjust the aspect ratio instead to adjusting using the corners of the image.

 

Response: Thank you for the feedback. The English and style of the journal were checked appropriately.

 

 

 

 

 

 

 

 

Author Response File: Author Response.docx

Reviewer 2 Report

1-    The text needs to go through a formal revision. English, Equation placement, figures style should be unified (font, size,…) use the image format to adjust the aspect ratio instead to adjusting using the corners of the image.

2-    The transitioning from literature to machine learning is vague. It would be better to add discissions on the importance of utilizing machine learning and any potential previous studies on this. (The authors have stated there was no previous similar studies however, utilization of machine learning in different aspect to show its practicability would be helpful)

3-    The inlets of machine learning to train are still vaguely discussed. Need to clearly state them and how they were gathered from the conducted set of experiments and their conditions.

4-    What are the spinneret specs? Dimensions? Spinning conditions and flow rates?

5-    What are the units of m_r and m_t? subscript r and t

6-    Figure 3 needs to be in a better quality. Readjust the boxes and their font. Charts and other plots need to be re adjusted with the same font and style

7-    The K-fold cross validation was employed. How many sub-divisions were conducted? Where is there any data not to be used for training and just for validation?

8-    What software was used? The codes were generated to open access code library was used?

9-    There is no doubt that machine learning can predict data based on what it’s trained on. Would you suggest that this machine learning study would only be applicable for a you home-made membranes considering the dimensions, materials and conditions that were used to fabricate the membranes since as far as I read there are no physical or chemical characteristics involved

1- The machine learning essentially used parameter weighting to predict data. Is there any physical interpretation on how this weighting works?

1-    The text needs to go through a formal revision. English, Equation placement, figures style should be unified (font, size,…) use the image format to adjust the aspect ratio instead to adjusting using the corners of the image.

2-    The transitioning from literature to machine learning is vague. It would be better to add discissions on the importance of utilizing machine learning and any potential previous studies on this. (The authors have stated there was no previous similar studies however, utilization of machine learning in different aspect to show its practicability would be helpful)

3-    The inlets of machine learning to train are still vaguely discussed. Need to clearly state them and how they were gathered from the conducted set of experiments and their conditions.

4-    What are the spinneret specs? Dimensions? Spinning conditions and flow rates?

5-    What are the units of m_r and m_t? subscript r and t

6-    Figure 3 needs to be in a better quality. Readjust the boxes and their font. Charts and other plots need to be re adjusted with the same font and style

7-    The K-fold cross validation was employed. How many sub-divisions were conducted? Where is there any data not to be used for training and just for validation?

8-    What software was used? The codes were generated to open access code library was used?

9-    There is no doubt that machine learning can predict data based on what it’s trained on. Would you suggest that this machine learning study would only be applicable for a you home-made membranes considering the dimensions, materials and conditions that were used to fabricate the membranes since as far as I read there are no physical or chemical characteristics involved

1- The machine learning essentially used parameter weighting to predict data. Is there any physical interpretation on how this weighting works?

Author Response

Reviewer 2

1. Kindly break the abstract into more structured sections, such as Background, Methods, Results, and Conclusion, to make it even more reader-friendly.

 

Response: Thank you for the positive comments. We have adjusted and added it in the revise version.

Actions

Efficient oil-water separation using membranes directly aligns with removing oil pollutants from water sources, promoting water quality. Hence, mitigating environmental harm from oil spills and contamination, fostering ecosystem health for sustainable development. Computational learning, such as Artificial intelligence (AI), enhances membrane oil flux and separation efficiency by optimizing process parameters, leading to improved oil-water separation, and aligning AI with sustainable environmental protection and resource efficiency solutions. This study employed phase-inversion coupled with sintering to create the ceramic membrane. Stöber method was adopted to prepare the superhydrophobic silica sol-gel solutions. The data from the mentioned experimental were imposed into regression models viz: multi-regression regression analysis (MLR), support vector regression (SVR), and robust linear regression (RLR), to simulate three different scenarios (oil flux, separation efficiency, oil flux and separation efficiency). The outcomes were validated and evaluated using several statistical (R², MSE, R, and RMSE) and graphical visualization. For oil flux, the results show that the most effective simulation was achieved in SVR-M2 and the statistical criteria for the testing phase (R² = 0.9847, R = 0.9923, RMSE = 0.0333, MSE = 0.0011). Similarly, SVR-M2 was superior to other modelling techniques for the separation efficiency in the testing phase (R² = 0.9945, R = 0.9972, RMSE = 0.0282, MSE = 0.0008). Reliability outcomes promise to revolutionize how we model and optimize membrane-based oil-water separation processes, with implications for various industries seeking sustainable and efficient solutions.

 

2. Mention why efficient oil-water separation is crucial, especially in the context of environmental protection and sustainable development. Connect the research to real-world problems, such as oil spills and contamination.

 

Response: Thank you for the feedback. We have added it in the revise version. We added the text version in the revise manuscript.

Actions

Efficient oil-water separation is essential for environmental protection and sustainable development. Oil spills harm ecosystems, suffocate marine life, and disrupt oxygen balance in waters. Beyond ecological damage, oil-contaminated water jeopardizes human health, causing ailments and affecting water quality for consumption and agriculture. Economically, oil spills strain fisheries, tourism, and necessitate costly clean-ups. Moreover, as industries aim for sustainability, reducing waste and pollution through effective oil-water separation is crucial, exemplified by its importance in the petroleum industry for cleaner extractions. In essence, research in this domain is vital, addressing immediate environmental challenges and promoting a sustainable future.

3. Provide more detail about the methods used to create the ceramic membrane and the superhydrophobic silica sol-gel solutions.

Response: Thank you for the comment. We have added it in the revise version. We added the text version in the revise manuscript.

Actions

The well-known method of phase-inversion coupled with sintering was employed to create the ceramic membrane in this study [22]. Kaolin was first dried in an oven at 80°C for 24 hours. Following that, 1g of Arlacel P135 gel was dissolved in N-2-methyl-2-pyrrolidone (NMP). This solution was then poured into a ceramic dish with 25 g of ceramic clay powder. The blend then underwent a ball milling process for 48 hours using an NQM-2 planetary mill. Afterward, a binder, specifically polyethersulfone (PESF), was incorporated into the mixture, and it was milled for an additional 48 hours. The homogenized dope suspension was degassed before extrusion by vacuum pump for 10 minutes. The degassed dope suspension was then extruded in a single layer spinneret under the flow rate and an extrusion temperature of 10 mL/min and 25 ^oC, respectively. Distilled water was used as bore fluid and pumped using a syringe pump. Afterwards, the kaolin ceramic hollow fiber membranes were collected and immersed in water for 24 hours. In the end, the membranes were washed with water and allowed to dry at ambient temperature for a period of two to three days. Fig. 1 depicts the diagram outlining the process of creating the hollow fiber membrane. In the spinneret-based process, the following parameters and values are employed: a spinneret diameter of 1.2, internal and external diameters of 2.8 mm and 10 mm respectively, a dope extrusion rate of 10 mL/min, an air gap of 5 cm, a bore fluid injection rate of 10 mL/min, and the use of tap water as both internal and external coagulants. The spinning and external temperatures are maintained at 25°C. These specific settings constitute the operational conditions for the process, which is characterized by its precise control of variables to achieve the desired outcomes.

 

 

 

 

 

 

 

 

 

 

Fig. 1. The schematic demonstration of spinning process of ceramic membranes fabrication process

 

 

 

 

 

The fabricated precursor membrane was cured at 1350 °C using a tubular furnace (XY-1700 MAGNA). The curing began at room temperature, extending for 2 hours at a rate of 2°C/min until 600 °C was achieved. Subsequently, the temperature was raised to 1350 °C at a pace of 5°C/min and maintained for 5 hours. Finally, the temperature was gradually reduced back to ambient levels at 5 °C/min. A diagram showcasing the sintering process of the ceramic membrane can be seen in Figure 2.

 

 

 

 

 

 

 

 

 

 

 

Fig. 2.  Sintering Profile of the ceramic membrane

A modified Stöber method was adopted for the preparation of the superhydrophobic silica sol-gel solutions [23]: Initially, 0.24 M Tetraethoxysilicate (TEOS) and 4.64 M ethanol were combined and introduced into a separate solution containing 1.04 M ammonia, 4.00 M H2O, and 4.64 M ethanol. This blend was stirred and underwent a reaction at 60°C for 90 minutes to form colloidal silica. Following this, 0.24 M MTES and 4.64 M ethanol were incorporated into the previously prepared colloidal silica solutions. An additional 4.64 M of ethanol was added to the mix to instill hydrophobic properties in the silica sol. Then, the solutions were stirred continuously at 60 ^oC for 19 h and allowed to 3 days for ageing. Finally, dip-coating method was followed for the preparation of hydrophobic ceramic membrane.

 

4. Highlight how AI and computational learning were applied to enhance oil flux and separation efficiency. Mention the specific role of AI in optimizing process parameters and improving oil-water separation. This will help readers understand the novel aspect of your research.

 

Response: Thank you for suggestions. We have added it in the revise version. We added the text version in the revise manuscript.

Actions

The pressing challenge of oil-water separation in wastewater treatment has witnessed a revolutionary improvement with the integration of AI and computational learning. By employing membrane technology, a widely recognized method for separation, AI algorithms analyze vast sets of experimental data to optimize process parameters. The core advantage of AI lies in its ability to predict outcomes with enhanced precision, thereby ensuring the membrane's maximum efficiency in separating oil from water. Through continuous learning and adaptation, AI models can fine-tune the operational conditions, such as pressure, flow rate, and temperature, to achieve optimal separation results. In essence, AI not only streamlines the membrane-based oil-water separation processes but also elevates its efficacy, paving the way for more sustainable wastewater treatment solutions.

 

5. Kindly rewrite all equations and use multipliers as ×instead of .

Response: We have corrected all

                                                                                                                   (2)

In the formula, V represents the oil volume (measured in liters), A stands for the membrane's surface area (measured in square meters), and t is the duration of filtration (in hours).

The efficiency of separating oil and water, termed as Oil-water Separation Efficiency (OSE), is determined by the ratio of oil extracted (mr) from the initial solution (mt) by the membrane. It's expressed in the subsequent manner:

 

                                                                                                (3)

 

 

6. What are the sources of the equation used in this study?

Response: We have referenced all the source of the equations. Most of the equations are from our experimental published papers.

 

 

7. Where are the training and testing data?

Response: We have divided the data in to 70:30 for training and testing respectively. The data can be access and available upon request as indicated.

 

8. How are the results verified?

Response: Verification of SVR, RLR, and MLR model results is conducted through several approaches. Initially, a train-test data split assesses model performance on unseen data. Cross-validation ensures consistent performance across different data portions, while metrics like R² and MSE gauge model accuracy. Residual analysis inspects the differences between actual and predicted values, and domain knowledge ensures results align with industry standards. Comparing model predictions to simpler baselines and state-of-the-art models offers additional validation, and a feedback loop with real-world outcomes enables continuous model refinement.

 

9. When introducing the regression models (MLR, SVR, RLR), briefly explain what each model does and why they were chosen. This can provide context for readers who may not be familiar with these techniques.

 

Response: Multi-Linear Regression (MLR), Support Vector Regression (SVR), and Robust Linear Regression (RLR) are sophisticated predictive models utilized in almost all separation studies. MLR is favoured for its straightforward approach; it models direct linear relationships between input and output variables, making it relatively easy to interpret and apply. In contrast, SVR is adept at handling intricate, non-linear relationships in datasets, often providing superior accuracy, especially when data patterns aren't straightforwardly linear. RLR, on the other hand, stands out for its preventative measures against overfitting. By introducing a penalty for overly complex models, RLR ensures that the predictions remain robust and generalizable to new, unseen data. When used in tandem, these three models provide a well-rounded and thorough methodology, ensuring accurate and dependable predictions for both oil flux and separation efficiency.

 

10. Explain what SVR-M2 signifies and why it was superior to other modelling techniques.

Response: Thanks for the comments. This have been added to the revise version.

Actions

It is important to note that SVR-M2 is superior to other modelling techniques this can be attributed to several factors. SVR excels in capturing non-linear relationships within data, making it effective for modelling complex patterns. It also demonstrates robustness by being less sensitive to outliers, thus accommodating noisy datasets. SVR's flexibility, enabled by customizable kernel functions, ensures adaptability to diverse data structures, and its propensity for generalization aids in reliable predictions for unseen data. Moreover, SVR handles high-dimensional data efficiently and can be fine-tuned through parameter optimization, enhancing its predictive accuracy. The choice of SVR-M2 as superior to other techniques likely depends on the specific dataset, modelling objectives, and performance metrics in the given context.

 

11. While you've mentioned statistical metrics (R2, MSE, R, RMSE), briefly define what these metrics measure and why they are essential in evaluating the simulation results.

Response: Thank you for the positive comments. The statistical metrics used to evaluate simulation results include R², which measures the proportion of variance in the dependent variable explained by the model, indicating its fit to the data. MSE quantifies the average squared difference between predicted and actual values, helping gauge the error magnitude. The correlation coefficient, R, assesses the strength and direction of a linear relationship between variables. Meanwhile, RMSE offers an interpretable metric of the average error magnitude, being in the same units as the data. Together, these metrics provide a comprehensive evaluation of a model's accuracy and reliability in simulations.

 

12. How might the successful application of AI in membrane-based oil-water separation impact industries and environmental protection efforts? What are the potential next steps for research or practical applications?

Response: Thank you for the questions. These have been added to the revise manuscript.

Actions

The successful integration of AI with membrane-based oil-water separation promises enhanced operational efficiency, cost savings, and superior environmental protection for industries. By optimizing separation processes, industries can achieve faster, more cost-effective results while minimizing environmental impacts. Future research and applications may focus on expanding datasets, refining AI models, real-time monitoring, and tailoring solutions to specific industry needs. Such advancements, combined with IoT and collaborative efforts, position AI-driven oil-water separation as a pivotal solution for sustainable industrial practices and environmental conservation.

 

13. The conclusions may be written pointwise for clear understanding.

Response: We have made some point for the reviewer’s consumption. However, we appreciate if the single paragraph could be maintained in the manuscript.

• The research evaluated SVR, RLR, and MLR models for predicting oil flux and separation efficiency.
• All the AI models demonstrated exceptional performance across various combinations.
• SVR-M2 emerged as the top-performing model for oil flux predictions based on its training and testing metrics, while MLR-M1 lagged behind.
• In terms of separation efficiency, SVR-M2 again stood out as the most effective, with MLR-M1 being the least efficient.
• When simultaneously modelling both responses, MLR-1 and MLR-2 surpassed other techniques, with MLR-2 slightly outperforming MLR-1.
• The study suggests the potential of incorporating hybrid models, newer algorithms, and optimization techniques to further enhance filtration performance in the future.

 

Author Response File: Author Response.docx

Reviewer 3 Report

The authors present their findings on preparation of a Advancing sustainable wastewater treatment using enhanced membrane oil flux and separation efficiency through experimental-based chemometric learning. This research investigate the results also suggested that hybrid models, emerging algorithms and optimization methods can be used to enhance the filtration performance. As a result, I urge that the manuscript be published in its current form.

Author Response

Reviewer 3

The authors present their findings on preparation of a Advancing sustainable wastewater treatment using enhanced membrane oil flux and separation efficiency through experimental-based chemometric learning. This research investigates the results also suggested that hybrid models, emerging algorithms and optimization methods can be used to enhance the filtration performance. As a result, I urge that the manuscript be published in its current form.

Response: Thank you for the positive comments and accepting our original article.

 

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The authors have properly addressed the comments and the manuscript can be considered for publication

Check figures 7 and 8, the size, aspect ratio, font, axis title position should be corrected and readjusted for all plots and in figures

Author Response

Reviewer 2_Round 2

1. Check figures 7 and 8, the size, aspect ratio, font, axis title position should be corrected and readjusted for all plots and in figures.

 

Response: Thank you for the feedback. We have adjusted and added it in the revise version.

Actions

 

Fig. 7. Scatter plots of oil flux for LMH between the observed and predicted values

 

 

 

Fig. 8. Scatter plots of separation efficiency based on observed and predicted values.

 

 

 Fig. 9. Scatter plots of separation efficiency and oil flux for LMH

 

 

 

Fig. 10. Error graph of oil flux (a-b) and separation efficiency (c-d) for comparison

 

 

 

 

Fig. 11. Error graph of combined output (oil flux + separation efficiency) for comparison

 

Author Response File: Author Response.docx