Improving CO₂ Absorption Using Artificial Intelligence and Modern Optimization for a Sustainable Environment

Round 1

Reviewer 1 Report

Comments:

1) Line 188-189: Comment: Typo error. Please proofread and check the overall manuscript. "A variable is not belonging, fully belonging and partially belonging to a MF if the mapping value is 0, 1 and ]0 1[, respectively. The fuzzy values are then supplied to"...

2) Comment: Any comparison data with other studies? 

3) Comment: In terms of economical aspects, is it possible this type of model being applied in large-scale or industrial scale process?

4) Comment: How many data points do you use? Not mention in the methodology section. Is it enough to predict the performance? 

5) Comment: Based on the accuracy results, is it produce high performance prediction?

 

 

 

None

Author Response

Reviewer 1 Comments:

First of all, the authors would like to thank the reviewer for the efforts and time spent for reviewing our work and the replies of the concerns are shown below.

1) Line 188-189: Comment: Typo error. Please proofread and check the overall manuscript. "A variable is not belonging, fully belonging and partially belonging to a MF if the mapping value is 0, 1 and ]0 1[, respectively. The fuzzy values are then supplied to"...

Reply: The authors would like to thank the reviewer for the valuable comment

The typo error has been corrected.

2) Comment: Any comparison data with other studies? 

Reply: The authors would like to thank the reviewer for the valuable comment

Please refer to Table 2. We compared the obtained optimized results with the experimental work and the response surface methodology. Regarding similar studied, an extensive search has been done and we have not encountered any similar studies that used the modern optimization to boost the mol fraction in terms of three operating parameters; the con-centration of tetrabutylphosphonium methanesulfonate [TBP][MeSO3], temperature, and pressure of CO₂.

3) Comment: In terms of economical aspects, is it possible this type of model being applied in large-scale or industrial scale process?

Reply: The authors would like to thank the reviewer for the valuable comment

Of course, the model can be applied in large-scale or industrial scale process. For more clarification, the following statements have been added to the “Results and Discussion” section.

“In the current study, the model has been built with only 20 data samples and produces competitive predictions. However, with more data samples, building the model will be easier and hence it can be applied in large-scale or industrial-scale processes.”

 

 

4) Comment: How many data points do you use? Not mention in the methodology section. Is it enough to predict the performance? 

Reply: The authors would like to thank the reviewer for the valuable comment

Please refer to page 10, it is mentioned that “The available 20-sample experimental dataset was partitioned with a 70:30 ratio to obtain 14 points for the training phase. For comparison, the remaining 6 points were reserved for the testing phase.”

Regarding the prediction accuracy, please refer to page 12, it is mentioned that “Fig. 6 supports the outstanding prediction accuracy of the ANFIS model, as shown in Fig. 5, by plotting the predicted data points around the 100% prediction accuracy line. This demonstration was performed for both training and testing predictions, where it shows that the model was trained with almost 100% accuracy (upper plot). To demonstrate that the model was not overtrained, the plots for the testing data points proved that the predictions (lower plot) were close to the 100% accuracy line.”

 

5) Comment: Based on the accuracy results, is it produce high performance prediction?

Reply: The authors would like to thank the reviewer for the valuable comment

Yes, the model produces high performance predictions.

Referring to Table 1, the low RMSE values and the high coefficient of determination (R²) values for both training and testing phases demonstrate that the prediction accuracy of the obtained fuzzy model is high. The following statements are mentioned in Section “5.1. Modeling Phase”:

“Compared with the literature [28], where they used the ANOVA statistical method to obtain the model, the RMSE and predicted R² for the entire samples were found to be 0.1174 and 0.8443, respectively. However, the ANFIS model yielded values of 0.0126 and 0.9758 for the same markers, respectively. This implies that the RMSE decreased by 9.32 times, and the signal tracking increased by 15.58% when using the ANFSI modeling technique instead of ANOVA. According to this comparison, the ANFIS outperformed the classical ANOVA modeling techniques.”

 

 

Author Response File: Author Response.docx

Reviewer 2 Report

Manuscript ID: sustainability-2414783-peer-review-v1

Manuscript Tile: Improving CO2 Absorption using Artificial Intelligence and Modern Optimization for Sustainable Environment

Authors: Ahmed M Nassef

The study show potential of using AI and modern optimization for enhancing CO2 absorption processes, with a focus on promoting a sustainable environment. However, there are some limitations in the study which are important in order to enhance the readability of the manuscript. These are provided below.

1.     The study is conducted to enhance the solubility of carbon dioxide (CO2) through the integration of artificial intelligence (AI) and modern optimization techniques, specifically focusing on the use of MEA (Monoethanolamine) and [TBP][MeSO3] as solvents. But how to validate the method or model used in the present study? Because it is very important to provide reliable results with clear model validation. It should be provided in the manuscript.

2.     It is essential to have a clear understanding of the mechanisms involved in CO2 absorption by using MEA and [TBP][MeSO3]. There is a lack of the CO2 absorption mechanism for the selected ionic solvent. Please clarify it.

3.     In the present study, two types of optimization algorithms like an adaptive neuro-fuzzy inference system (ANFIS) an improved grey wolf optimizer (IGWO) are used. Choosing appropriate optimization algorithms is crucial for maximizing the effectiveness of the CO2 absorption process. So, what is the reason to choose these algorithms and how they are important?

4.     This study seems to be very far from the experimental method and experimental conditions. Overcoming the gap between the proposed study and experimental methods and conditions is crucial to ensure the reliability and applicability of the findings for future studies. So how to overcome these factors and how it can be reliable for future studies?

5.     Make sure that in whole manuscript for the CO₂ , ‘2’ should be in subscript.

6.     In the Nomenclature table, it is important to provide all abbreviations in a uniform format for clarity and consistency.

Comments for author File: Comments.pdf

Minor improvements can be made 

Author Response

Reviewer 2 Comments:

 

Manuscript ID: sustainability-2414783-peer-review-v1

Manuscript Tile: Improving CO2 Absorption using Artificial Intelligence and Modern Optimization for Sustainable Environment

Authors: Ahmed M Nassef

The study show potential of using AI and modern optimization for enhancing CO2 absorption processes, with a focus on promoting a sustainable environment. However, there are some limitations in the study which are important in order to enhance the readability of the manuscript. These are provided below.

First of all, the authors would like to thank the reviewer for the efforts and time spent for reviewing our work and the replies of the concerns are shown below.

1. The study is conducted to enhance the solubility of carbon dioxide (CO2) through the integration of artificial intelligence (AI) and modern optimization techniques, specifically focusing on the use of MEA (Monoethanolamine) and [TBP][MeSO3] as solvents. But how to validate the method or model used in the present study? Because it is very important to provide reliable results with clear model validation. It should be provided in the manuscript.

Reply: The authors would like to thank the reviewer for the valuable comment

To build a concrete model and to overcome the problem of overfitting, the authors selected carefully the three factors that affect the reliability of the model predictions which are: (1) the modelling tool; (2) the ratio of training to testing samples; and (3) the number of training epochs. In this study, the ANFIS as a general approximator is adopted to build the system’s model due to its ability to handle effectively any complex and non-linear dataset. Also, the subtractive Clustering Algorithm (SC) is applied to generate the fuzzy rules. SC usually generates the rules with the minimum overlap between data points clusters to guarantee the general approximation.  Additionally, the data samples were divided with a ratio of 70:30 for training and testing, respectively. Accordingly, the number of training points was 14 and the remaining 6 points were kept for testing.  In fact, distributing the number of data points with this ratio is considered the best, specifically in the case of small data samples. Furthermore, the model was trained with a relatively small number of epochs. The resulting small number of testing’s MSE illustrates that the three modelling factors have been selected appropriately hence, the obtained ANFIS model is robust and its predictions are trustable.

 

2. It is essential to have a clear understanding of the mechanisms involved in CO2 absorption by using MEA and [TBP][MeSO3]. There is a lack of the CO2 absorption mechanism for the selected ionic solvent. Please clarify it.

Reply: The authors would like to thank the reviewer for the valuable comment. The following statements have been added to the “Dataset” section.

“The MEA and [TBP][MeSO3] were selected to be mixed, producing aqueous hybrid solvent for CO₂ removal. The MEA concentration was kept constant at 30 wt% as per typical amine concentrations used in commercialized CO₂ absorption technology.”

3. In the present study, two types of optimization algorithms like an adaptive neuro-fuzzy inference system (ANFIS) an improved grey wolf optimizer (IGWO) are used. Choosing appropriate optimization algorithms is crucial for maximizing the effectiveness of the CO2 absorption process. So, what is the reason to choose these algorithms and how they are important?

Reply: The authors would like to thank the reviewer for the valuable comment

The authors would like to clarify that the ANFIS used in this work is a modeling tool to build the system’s model and the IGWO is used as an optimization algorithm. Furthermore, we have applied numerous optimization algorithms including the IGWO to obtain the optimal parameters. The results showed that the IGWO produced the best set of optimal parameters in comparison to the other optimizers in terms of the highest average value and the lowest standard deviation as shown in Table 3. So, in this work, the ANFIS is used to build the fuzzy model and the IGWO is used to obtain the optimal parameters of the system.

 

4. This study seems to be very far from the experimental method and experimental conditions. Overcoming the gap between the proposed study and experimental methods and conditions is crucial to ensure the reliability and applicability of the findings for future studies. So how to overcome these factors and how it can be reliable for future studies?

Reply: The authors would like to thank the reviewer for the valuable comment.

The current study is the next stage after experimental work. The proposed methodology includes two phases: fuzzy modelling and parameter estimation. In the first phase, the ANFIS model was developed using the experimental data sets. Then using optimization algorithms to determine the best values of the concentration of tetrabutylphosphonium methanesulfonate [TBP][MeSO3], temperature, and pressure of CO₂. During the optimization process, the target is maximizing the mol fraction.

 

5. Make sure that in whole manuscript for the CO₂, ‘2’ should be in subscript.

Reply: The authors would like to thank the reviewer for the valuable comment.

 We considered your comment.

 

6. In the Nomenclature table, it is important to provide all abbreviations in a uniform format for clarity and consistency.

Reply: The authors would like to thank the reviewer for the valuable comment.

We revised the nomenclature table.

 

 

 

Author Response File: Author Response.docx

Reviewer 3 Report

1. the innovative point or problem of the study needs to be condensed at the word introduction stage

2. a research roadmap needs to be added to help readers understand the full text

3. some writing details need to be paid attention to, for example, many CO₂ in the full text "2" without line markers, in the abstract stage has been written carbon dioxide (CO₂) in the conclusion reappears

4. It is recommended that the conclusion be written in separate articles, as a large paragraph is not very clear.

Some details of English writing need further improvement

Author Response

Reviewer 3 Comments:

First of all, the authors would like to thank the reviewer for the efforts and time spent for reviewing our work and the replies of the concerns are shown below.

1. the innovative point or problem of the study needs to be condensed at the word introduction stage

Reply: The authors would like to thank the reviewer for the valuable comment.

The main contribution of the paper is outlined at the end of the “Introduction” section as follows:

The main contribution of the paper can be summarized as follows.

• A new application of improved grey wolf optimizer is proposed to improve CO₂
• The optimal values of concentration of [TBP][MeSO3], temperature, and pressure of CO2 are determined.
• The value of mol fraction is increased.

2. a research roadmap needs to be added to help readers understand the full text

Reply: The authors would like to thank the reviewer for the valuable comment.

The research roadmap is mentioned in the “Introduction” section as follows:

“The objective of this study was to fill this research gap by applying advanced optimization methods and artificial intelligence techniques, to design and optimize capture solvents with high CO₂ solubility and selectivity. Specifically, identify the optimal values of various parameters, such as concentration, temperature, and pressure of CO₂ that produced the highest value of mol fraction. To achieve this objective, the ANFIS was used to develop a model that could accurately predict the solubility of CO₂ in the capture solvents. The optimal values of various parameters such as concentration of [TBP][MeSO₃], temperature, and pressure of CO₂ that produce the highest value of mol fraction were identified using five recent and significant metaheuristic algorithms include particle swarm optimization (PSO), slim mould algorithm (SMA), Harris Hawks optimization (HHO), grey wolf optimizer (GWO), and improved grey wolf optimizer (IGWO)). The novelty of this study lies in the combination of an advanced optimization method to improve the solubility of CO₂ in the capture solvents. The combination of the robustness of ANFIS modeling and metaheuristic optimization methods has proven to be highly efficient in finding reliable and feasible outcomes [42,43]. This approach has the potential to significantly improve the efficiency and cost-effectiveness of the CO₂ capture processes.  Ultimately, the findings of this study will contribute to the development of more efficient and cost-effective CCS technologies, that can help mitigate the impacts of climate change.”

3. some writing details need to be paid attention to, for example, many CO₂in the full text "2" without line markers, in the abstract stage has been written carbon dioxide (CO₂) in the conclusion reappears

Reply: The authors would like to thank the reviewer for the valuable comment.

We have adjusted this issue.

4. It is recommended that the conclusion be written in separate articles, as a large paragraph is not very clear.

Reply: The authors would like to thank the reviewer for the valuable comment.

The “Conclusion” section has been split into separate paragraphs to be very clear to the reader.

 

 

 

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

The “CO₂” format in the references needs to be fixed again

Author Response

Reviewer 3 Comments:

First of all, the authors would like to thank the reviewer for the efforts and time spent for reviewing our work and the replies of the concerns are shown below.

 

Comment: The “CO₂” format in the references needs to be fixed again

Reply: The authors would like to thank the reviewer for the valuable comment.

The “CO₂” format in the references has been fixed.

Author Response File: Author Response.docx