Combining Fuzzy Logic and Genetic Algorithms to Optimize Cost, Time and Quality in Modern Agriculture

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This study focuses on the multi-objective optimization challenges (cost, time, quality) in agricultural project management. In response to the limitations of traditional methods in dealing with uncertainty and multi-objective conflicts, an innovative framework combining fuzzy logic and genetic algorithm (GA) is proposed. The author quantifies the uncertainty in agricultural activities (such as weather fluctuations and resource supply) through triangular fuzzy quantification, and for the first time combines alpha cutting technology with NSGA-II algorithm to achieve risk preference driven Pareto solution set generation. The case verification covers multi regional data of the four major global staple crops (rice, barley, wheat, corn), providing a tool for agricultural decision-making that combines theoretical rigor and practical flexibility. The innovation of research methods is reflected in the dynamic coupling mechanism between fuzzy rules and genetic algorithms, as well as the universal verification strategy across crops and climates. However, in order to further improve the quality and influence of the paper, it is recommended that the author conduct more in-depth exploration and supplementation in the following areas:

1. Although the hybrid design of fuzzy genetic algorithm is innovative, the article does not clearly explain the construction logic of fuzzy rule base (such as how expert experience is transformed into fuzzy IF-THEN rules) and the differences from classical fuzzy optimization models (such as Zimmermann method). Suggest adding charts to demonstrate the process of generating fuzzy rules, and adding a comparison with fuzzy stochastic programming in reference [22] in the discussion section to quantify the advantages of this method in terms of convergence speed and solution diversity.
2. The data source of the case study is authoritative and covers diverse scenarios of multiple regions and crops, enhancing the universality of the conclusions. However, the description of data preprocessing methods (such as how to convert historical data into fuzzy numbers) and practical application backgrounds (such as differences in growth cycles of different crops) is relatively brief. Suggest supplementing the data standardization process, analyzing the impact of regional climate and soil conditions on model inputs, and detailing the implementation of specific agricultural activities in the case study.
3. The paper elaborates on the mathematical modeling process of fuzzy logic and genetic algorithm, including the definition of triangular fuzzy numbers, the cross mutation strategy of genetic algorithm, and the process of obtaining Pareto optimal solutions. However, the selection criteria for key parameters such as values, population size, and iteration times need to be supplemented with explanations. Suggest adding experimental validation or theoretical support for parameter settings, such as discussing the impact of different parameter combinations on the stability of results.
4. The study revealed the impact mechanism of risk preference on optimization results by comparing different values (0 to 1), such as focusing more on cost stability under high alpha values. However, the interpretation of the economic significance of the Pareto solution set in the results section is insufficient, such as not quantifying the actual agricultural benefits of each target weight (such as the impact of cost reduction percentage or quality improvement on market value). Suggest adding a benefit evaluation of Pareto solutions, discussing the applicability of different weights in specific agricultural scenarios (such as food security priorities), and supplementing visualization tools (such as radar charts) to visually display multi-objective trade-off relationships.
5. The second paragraph on page 24 of the original text mentions that "this study is consistent with the United Nations Sustainable Development Goals (SDGs)", but only provides a general list of SDG2 (Zero Hunger), SDG13 (Climate Action) and other goals, which have weak relevance to this study. It is suggested to use some brief indicators or case studies to illustrate how the model actually supports these goals.
6. This paper mainly focuses on multi-objective optimization problems. In fact, there are many latest multi-objective optimization algorithms for multi-agent systems that can be used as references, such as "Multi-objective multi-agent planning for discovering and tracking multiple mobile objects", "Barycentric Coordinate-Based Distributed Localization for Wireless Sensor Networks Under False-Data-Injection Attacks".

Author Response

COMMUNICATION TO THE REVIEWER 1

Dear Reviewer,

We would like to express our sincere gratitude for the time and effort you have dedicated to reviewing our manuscript. Your insightful comments and constructive suggestions have been invaluable in enhancing the quality and clarity of our work. We have carefully considered each of your suggestions and have made the necessary revisions to address your concerns.

In the following of this document, we have provided detailed responses to each of your comments. Adjustments made in the main manuscript are in red color (English corrections are in green) to facilitate your review. We hope that these revisions meet your expectations and improve the overall quality of our research.

 

Comments and Suggestions for Authors:

This study focuses on the multi-objective optimization challenges (cost, time, quality) in agricultural project management. In response to the limitations of traditional methods in dealing with uncertainty and multi-objective conflicts, an innovative framework combining fuzzy logic and genetic algorithm (GA) is proposed. The author quantifies the uncertainty in agricultural activities (such as weather fluctuations and resource supply) through triangular fuzzy quantification, and for the first time combines alpha cutting technology with NSGA-II algorithm to achieve risk preference driven Pareto solution set generation. The case verification covers multi regional data of the four major global staple crops (rice, barley, wheat, corn), providing a tool for agricultural decision-making that combines theoretical rigor and practical flexibility. The innovation of research methods is reflected in the dynamic coupling mechanism between fuzzy rules and genetic algorithms, as well as the universal verification strategy across crops and climates. However, in order to further improve the quality and influence of the paper, it is recommended that the author conduct more in-depth exploration and supplementation in the following areas:

Comments 1:

“Although the hybrid design of fuzzy genetic algorithm is innovative, the article does not clearly explain the construction logic of fuzzy rule base (such as how expert experience is transformed into fuzzy IF-THEN rules) and the differences from classical fuzzy optimization models (such as Zimmermann method). Suggest adding charts to demonstrate the process of generating fuzzy rules, and adding a comparison with fuzzy stochastic programming in reference [22] in the discussion section to quantify the advantages of this method in terms of convergence speed and solution diversity.”

Response 1:

We have explained the issue in detail, considering the issue you mentioned. You can look title 1.3, please.

Comments 2:

“The data source of the case study is authoritative and covers diverse scenarios of multiple regions and crops, enhancing the universality of the conclusions. However, the description of data preprocessing methods (such as how to convert historical data into fuzzy numbers) and practical application backgrounds (such as differences in growth cycles of different crops) is relatively brief. Suggest supplementing the data standardization process, analyzing the impact of regional climate and soil conditions on model inputs, and detailing the implementation of specific agricultural activities in the case study.”

Response 2:

We have explained the issue in detail, considering the issue you mentioned. You can look title 2.3, please.

Comments 3:

“The paper elaborates on the mathematical modeling process of fuzzy logic and genetic algorithm, including the definition of triangular fuzzy numbers, the cross mutation strategy of genetic algorithm, and the process of obtaining Pareto optimal solutions. However, the selection criteria for key parameters such as values, population size, and iteration times need to be supplemented with explanations. Suggest adding experimental validation or theoretical support for parameter settings, such as discussing the impact of different parameter combinations on the stability of results.”

Response 3:

The optimization performance of genetic algorithms is heavily influenced by the choice of key parameters such as population size, mutation rate, and iteration count. These parameters determine the efficiency and accuracy of the solution search process. While standard heuristic values exist, their effectiveness varies across different problem domains.

This study conducts an extensive sensitivity analysis to justify parameter selection. Population size, a crucial determinant of solution diversity, is tested within the range of 50 to 500 individuals, with results indicating that a size of 100 balances computational efficiency and solution quality. Mutation rate, which introduces variability into the population to prevent premature convergence, is optimized through experimentation, with a rate of 0.02 yielding the best performance in agricultural scenarios. The number of generations is capped at 90 to ensure a balance between exploration and computational efficiency. Comparative experiments with alternative parameter settings further validate the robustness of these selections, demonstrating that the chosen values provide stable and consistent optimization results across multiple case studies.

Comments 4:

“The study revealed the impact mechanism of risk preference on optimization results by comparing different values (0 to 1), such as focusing more on cost stability under high alpha values. However, the interpretation of the economic significance of the Pareto solution set in the results section is insufficient, such as not quantifying the actual agricultural benefits of each target weight (such as the impact of cost reduction percentage or quality improvement on market value). Suggest adding a benefit evaluation of Pareto solutions, discussing the applicability of different weights in specific agricultural scenarios (such as food security priorities), and supplementing visualization tools (such as radar charts) to visually display multi-objective trade-off relationships.”

Response 4:

A critical aspect of multi-objective optimization is understanding the practical implications of the generated Pareto solutions. While the NSGA-II algorithm provides a diverse set of trade-off solutions between cost, time, and quality, the economic significance of these solutions must be carefully analyzed.

This study quantifies cost savings and quality improvements in monetary terms to enhance decision-making for stakeholders. For example, optimizing irrigation schedules using the proposed model leads to a 15–20% reduction in water consumption, translating into substantial cost savings for farmers. Similarly, improved crop rotation strategies contribute to increased yield stability, reducing reliance on expensive fertilizers and pesticides. Market impact analysis explores how different weightings of cost, time, and quality affect agricultural profitability. Additionally, visualization tools such as radar charts are used to illustrate the trade-offs between objectives, providing an intuitive means for decision-makers to assess the suitability of various solutions.

You can look Figure, 4,5, and 6, please.

Comments 5:

“The second paragraph on page 24 of the original text mentions that "this study is consistent with the United Nations Sustainable Development Goals (SDGs)", but only provides a general list of SDG2 (Zero Hunger), SDG13 (Climate Action) and other goals, which have weak relevance to this study. It is suggested to use some brief indicators or case studies to illustrate how the model actually supports these goals.”

Response 5:

Global food security and climate resilience are critical concerns addressed by the United Nations Sustainable Development Goals (SDGs). This study explicitly aligns with SDG2 (Zero Hunger) by promoting optimized agricultural practices that enhance productivity while minimizing resource waste. By incorporating fuzzy logic and genetic algorithms into farm management strategies, the model helps improve efficiency and sustainability in food production systems.

Furthermore, the study contributes to SDG13 (Climate Action) by integrating climate adaptation strategies into agricultural decision-making. The use of climate risk modeling in the optimization process enables farmers to proactively adjust planting schedules and resource allocation based on projected weather conditions. Case studies demonstrate the practical impact of these optimizations, showing how targeted interventions can mitigate climate-induced yield variability and enhance overall resilience in agricultural supply chains.

Comments 6:

“This paper mainly focuses on multi-objective optimization problems. In fact, there are many latest multi-objective optimization algorithms for multi-agent systems that can be used as references, such as "Multi-objective multi-agent planning for discovering and tracking multiple mobile objects", "Barycentric Coordinate-Based Distributed Localization for Wireless Sensor Networks Under False-Data-Injection Attacks".

Response 6:

The field of multi-objective optimization has witnessed significant advancements in recent years. To ensure that this study remains at the forefront of computational innovation, references to cutting-edge methodologies are incorporated.

For instance, research on "Multi-objective multi-agent planning for discovering and tracking multiple mobile objects" offers insights into adaptive optimization techniques that could enhance model scalability (Chen et al., 2021). Similarly, "Barycentric Coordinate-Based Distributed Localization for Wireless Sensor Networks Under False-Data-Injection Attacks" provides a framework for handling adversarial conditions, which could be relevant in scenarios where agricultural sensors are exposed to environmental interference (Li & Zhang, 2022). By integrating these contemporary research findings, this study strengthens its methodological foundation and demonstrates its relevance to the evolving field of computational optimization.

Final Comment:

We believe these revisions have significantly improved the clarity and robustness of our manuscript. Thank you once again for your valuable feedback.

Best regards.

Reviewer 2 Report

Comments and Suggestions for Authors

The present manuscript provides a novel methodology to efficiently manage different aspects that modern agriculture focuses on. In a changing world, where climate change, environmental conditions, sociopolitical situations, and a growing population density are prevalent, the efficiency and increase in agricultural production are fundamental to meet all the demand.

However, there are a number of points that I believe should be reviewed before the publication of the scientific article.

I think the Introduction is divided into too many sections, which makes it difficult to quickly read the document. In some cases, each section has barely 3-4 lines (e.g., 104-107; 110-115). Could a more cohesive structure be created where definitions (Sections 1.2-1.4) do not appear, but all the information is integrated in a more elaborate manner?

In particular, I believe that the real introduction to the topic is found in section 2 of the Literature Review, where the reader is finally contextualized after the previous list of technical terms. Is there any economic data that allows us to assess the impact of the examples presented? For example, it is mentioned that in rice cultivation, these models are used to evaluate water usage under uncertain precipitation conditions. If these models and predictions did not exist, are the economic losses resulting from this environmental impact known?

Please review the figure and table captions, as they are sometimes not explanatory (for example, Figure 1, describe what is on the right and left of the image; the same with Figure 3). Table 4 takes up considerable space in the manuscript and makes it difficult to follow the text (it spans 4 pages of the document). Could it be moved to the supplementary material section?

Unfortunately, what I find a bit lacking in the text, compared to the enormous work done in previous sections, is the discussion. It lacks citations. I believe it is necessary to use bibliographic references that support and ensure the veracity of the work done and highlight the need to implement and apply all the technological and computational developments proposed in the manuscript in the agricultural context. Please review this section and include a serious and constructive argument that allows to highlight the value of everything previously proposed.

Author Response

COMMUNICATION TO THE REVIEWER 2

Dear Reviewer,

We would like to express our sincere gratitude for the time and effort you have dedicated to reviewing our manuscript. Your insightful comments and constructive suggestions have been invaluable in enhancing the quality and clarity of our work. We have carefully considered each of your suggestions and have made the necessary revisions to address your concerns.

In the following of this document, we have provided detailed responses to each of your comments. Adjustments made in the main manuscript are in red color (English corrections are in green) to facilitate your review. We hope that these revisions meet your expectations and improve the overall quality of our research.

Comments and Suggestions for Authors:

“The present manuscript provides a novel methodology to efficiently manage different aspects that modern agriculture focuses on. In a changing world, where climate change, environmental conditions, sociopolitical situations, and a growing population density are prevalent, the efficiency and increase in agricultural production are fundamental to meet all the demand. However, there are a number of points that I believe should be reviewed before the publication of the scientific article.”

Comments 1:

“I think the Introduction is divided into too many sections, which makes it difficult to quickly read the document. In some cases, each section has barely 3-4 lines (e.g., 104-107; 110-115). Could a more cohesive structure be created where definitions (Sections 1.2-1.4) do not appear, but all the information is integrated in a more elaborate manner?.”

Response 1:

We have stated the suggestions of you and other referees by making detailed explanations under subheadings. We wanted to give the literature in the introduction. Therefore, it was necessary to go into some detail. We have used new sources. You can see them in the text.

Comments 2:

“In particular, I believe that the real introduction to the topic is found in section 2 of the Literature Review, where the reader is finally contextualized after the previous list of technical terms. Is there any economic data that allows us to assess the impact of the examples presented? For example, it is mentioned that in rice cultivation, these models are used to evaluate water usage under uncertain precipitation conditions. If these models and predictions did not exist, are the economic losses resulting from this environmental impact known?”

Response 2:

We have stated your suggestions under the literature review heading.

Comments 3:

“Please review the figure and table captions, as they are sometimes not explanatory (for example, Figure 1, describe what is on the right and left of the image; the same with Figure 3). Table 4 takes up considerable space in the manuscript and makes it difficult to follow the text (it spans 4 pages of the document). Could it be moved to the supplementary material section?”

Response 3:

We explained the way you specified.

Comments 4:

“Unfortunately, what I find a bit lacking in the text, compared to the enormous work done in previous sections, is the discussion. It lacks citations. I believe it is necessary to use bibliographic references that support and ensure the veracity of the work done and highlight the need to implement and apply all the technological and computational developments proposed in the manuscript in the agricultural context. Please review this section and include a serious and constructive argument that allows to highlight the value of everything previously proposed.”

Response 4:

We revised the study and explained many topics with new sources.

Final Comment:

We believe these revisions have significantly improved the clarity and robustness of our manuscript. Thank you once again for your valuable feedback.

Best regards.

 

 

Reviewer 3 Report

Comments and Suggestions for Authors

Comments and Suggestions for Authors

1. Some figures and tables need clearer labels and more detailed explanations. The resolution of the Figure 3 should be increased.
2. The manuscript contains several typos and grammatical errors that need correction.
3. What are the specific advantages of this hybrid approach over using either technique independently?
4. The use of mathematical notation should be consistent and explained clearly.
5. The literature review needs significant strengthening. It should provide a more focused and critical overview of relevant research.
6. The writing style and organization need some improvement.

Comments on the Quality of English Language

The paper could also use some improvement in writing style for clarity.

Author Response

COMMUNICATION TO THE REVIEWER 3

Dear Reviewer,

We would like to express our sincere gratitude for the time and effort you have dedicated to reviewing our manuscript. Your insightful comments and constructive suggestions have been invaluable in enhancing the quality and clarity of our work. We have carefully considered each of your suggestions and have made the necessary revisions to address your concerns.

In the following of this document, we have provided detailed responses to each of your comments. Adjustments made in the main manuscript are in red color (English corrections are in green) to facilitate your review. We hope that these revisions meet your expectations and improve the overall quality of our research.

Comments 1:

“Some figures and tables need clearer labels and more detailed explanations. The resolution of the Figure 3 should be increased.”

Response 1:

We explained the tables, figures and formulas in more detail.

Comments 2:

“The manuscript contains several typos and grammatical errors that need correction.”

Response 2:

We reviewed paper again and made correction several typos and grammatical errors.

Comments 3:

“What are the specific advantages of this hybrid approach over using either technique independently?”

Response 3:

We made explanations in the text.

Comments 4:

“The use of mathematical notation should be consistent and explained clearly.”

Response 4:

We explained the formulas in more detail.

Comments 5:

“The literature review needs significant strengthening. It should provide a more focused and critical overview of relevant research.”

Response 5:

We expanded the introduction and literature sections with new sources.

Comments 6:

“The writing style and organization need some improvement.”

Response 6:

We had improvements in “The writing style and organization."

Final Comment:

We believe these revisions have significantly improved the clarity and robustness of our manuscript. Thank you once again for your valuable feedback.

Best regards.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

No further comments

Comments on the Quality of English Language

No further comments