Application of Remote Sensing and Machine Learning in Sustainable Agriculture
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe authors of the manuscript conducted a deep analysis of publications related to sustainable food production and the integration of advanced tools to improve environmental performance and operational efficiency into the field of modern agricultural production.
Overall, the manuscript is written at a fairly good scientific level; however, I have a number of questions and comments.
- The title of the manuscript generally reflects the content, but the abstract does not fully correspond to the text that follows. In the abstract, the authors talk exclusively about CEA, which may give the reader an incorrect idea of the article itself. In fact, the authors analyzed 70 literary sources, starting from 2001, when CEA was not yet discussed (due to the development of agriculture and related industries at that time). And, accordingly, the overwhelming majority of the articles do not relate to CEA; rather, they are related to the modernization of agriculture in general. Thus, in Table 1, only one article (reference No. 39) out of 10 presented relates directly to the controlled environments.
Accordingly, I believe that the authors need to rewrite the abstract considering the above, without placing such an emphasis on CEA specifically. Based on the materials analyzed by the authors, we can only speak about the current high prospects (and needs) for the introduction of RS and ML in artificial climate facilities.
- The authors demonstrated a good knowledge of the research topic. However, I believe that in line 91 the reference to the review article by Dsouza et al. [3] is not entirely correct; a reference to the works of the "classics" of the CEA topic - D. Despommier, Al-Kodmani, Kozai - would be more appropriate.
- Figure 1: The drawing should be given a more detailed title that reflects its essence. All figures must be accompanied by more detailed captions: in figure 2, indicate the topic of the articles, in figure 3, the topic and years (2001-2025), the same for figures 4 and 5.
- The years in table 1 need to be corrected: for a number of references they are incorrect.
- In line 311, the abbreviation UAV should be explained.
- Line 350 requires italics for the Latin name of the insect pest.
- In lines 390-391, indicate the city and country for each of the mentioned scientific institutions.
- Figure 5 should be placed after it is mentioned in the text.
- The English language needs some correction in places.
Comments for author File: Comments.pdf
The English language needs some correction in places.
Author Response
The authors of the manuscript conducted a deep analysis of publications related to sustainable food production and the integration of advanced tools to improve environmental performance and operational efficiency into the field of modern agricultural production.
Overall, the manuscript is written at a fairly good scientific level; however, I have a number of questions and comments.
- We sincerely thank you for taking the time to review our manuscript and for your constructive comments. In the following, we provide point-by-point responses to each of your comments and suggestions.
Comment 1: The title of the manuscript generally reflects the content, but the abstract does not fully correspond to the text that follows. In the abstract, the authors talk exclusively about CEA, which may give the reader an incorrect idea of the article itself. In fact, the authors analyzed 70 literary sources, starting from 2001, when CEA was not yet discussed (due to the development of agriculture and related industries at that time). And, accordingly, the overwhelming majority of the articles do not relate to CEA; rather, they are related to the modernization of agriculture in general. Thus, in Table 1, only one article (reference No. 39) out of 10 presented relates directly to the controlled environments.
Accordingly, I believe that the authors need to rewrite the abstract considering the above, without placing such an emphasis on CEA specifically. Based on the materials analyzed by the authors, we can only speak about the current high prospects (and needs) for the introduction of RS and ML in artificial climate facilities.
Response 1: Thank you very much for your valuable comment. In response to your suggestion, we have revised the abstract to better represent the content of the article. The updated version maintains the focus on the relevance of RS and ML in agriculture, while positioning CEA as a currently emerging and promising area, rather than the sole focus of the study. Thank you again for your insightful recommendation.
The modified version:
"Abstract: The growing demand for sustainable food production has driven significant advancements in modern agriculture, including the increasing interest in Controlled Environment Agriculture (CEA) - a high-tech solution designed to provide fresh, local, and organic products. Although the integration of various technologies in agriculture continues to expand, there are still many opportunities to improve environmental performance and operational efficiency. Recent advancements in Remote Sensing (RS) and Machine Learning (ML) offer promising tools for enhancing resource efficiency, improving sustainability, and optimizing processes across various agricultural settings. This study presents a bibliometric analysis of the application of Remote Sensing and Machine Learning in agriculture, highlighting publication trends, influential research contributions, and emerging themes in this interdisciplinary field. While the majority of the analyzed literature addresses general agricultural modernization, the growing relevance of RS and ML in artificial climate facilities and controlled environments is evident in more recent research. Furthermore, we explore how RS and ML technologies contribute to real-time monitoring, precision agriculture, and decision-making in agriculture."
Comment 2: The authors demonstrated a good knowledge of the research topic. However, I believe that in line 91 the reference to the review article by Dsouza et al. [3] is not entirely correct; a reference to the works of the "classics" of the CEA topic - D. Despommier, Al-Kodmani, Kozai - would be more appropriate.
Response 2: We appreciate your suggestion. Yet, in line 91, our intention was to highlight previous bibliometric studies specifically, as our focus in that paragraph was on the existing bibliometric analyses within the CEA domain. The work of Dsouza et al. [3] was cited precisely because it represents one of the few comprehensive bibliometric studies conducted in this area. While the contributions of the “classics” are undoubtedly central to the conceptual and technical foundations of CEA, they have not, to our knowledge, produced bibliometric or meta-analytical research, which is the narrower scope addressed in that sentence. However, we have now included a reference to Despommier in the second paragraph of the Introduction, acknowledging his contribution as a pioneer in the field of Controlled Environment Agriculture (CEA) and highlighting the key advantages of vertical farming. Accordingly, we have also updated the numbering of all cited references throughout the manuscript.
As one of the pioneers in this field, Despommier [3] outlines several advantages of vertical farming, including year-round crop production, elimination of weather-related losses and agricultural runoff, significant water savings, and opportunities for urban revitalization and ecosystem restoration.
Comment 3: Figure 1: The drawing should be given a more detailed title that reflects its essence. All figures must be accompanied by more detailed captions: in figure 2, indicate the topic of the articles, in figure 3, the topic and years (2001-2025), the same for figures 4 and 5.
Response 3: Thank you for the helpful suggestion. We have revised the titles of figures to better reflect the content and purpose in the context of our study. The new titles are:
"Figure 1. PRISMA Flow Diagram for the selection of studies on the use of Remote Sensing and Machine Learning in agriculture
Figure 2. Evolution of published articles on RS and ML in agriculture between 2001 and 2025
Figure 3. Country-level Distribution of Research Output on Remote Sensing and Machine Learning in Agriculture (2001-2025).
Figure 4. Network Visualization of Keyword Co-Occurrences in Publications on the Use of Remote Sensing and Machine Learning in Agriculture (2001–2025)
Figure 5. Overlay Visualization of Emerging Topics on the use of Remote Sensing and Machine Learning in Agriculture Based on Keyword Co-Occurrences"
Comment 4: The years in table 1 need to be corrected: for a number of references they are incorrect.
Response 4: Thank you for pointing this out. We have carefully reviewed and corrected the publication years in Table 1. The previous inaccuracies were due to a formatting oversight during manuscript preparation, and we apologize for the confusion.
Comment 5: In line 311, the abbreviation UAV should be explained.
Response 5: Thank you for your observation. We have revised the text to include the full term Unmanned Aerial Vehicle (UAV) at its first mention, as follows:
"Various systems have been developed that integrate autonomous Unmanned Aerial Vehicles (UAVs) with machine learning (ML) frameworks to support sustainable agriculture and environmental monitoring, aligning with the broader environmental conservation goals"
Comment 6: Line 350 requires italics for the Latin name of the insect pest.
Response 6: Thank you for your comment. We have corrected the formatting, and the Latin name of the insect pest is now written in italics as required.
Comment 7: In lines 390-391, indicate the city and country for each of the mentioned scientific institutions.
Response 7: Thank you for this suggesion. We modified the text as follows:
"The collaboration between Ain Shams University (Cairo, Egypt), the National Authority for Remote Sensing and Space Sciences (Cairo, Egypt), and the Institute of Olive Tree, Subtropical Crops and Viticulture (Crete, Greece) suggests a strong connection between academic research and practical applications in the field of sustainable agriculture."
Comment 8: Figure 5 should be placed after it is mentioned in the text.
Response 8: We have adjusted the placement of Figure 5 so that it now appears after its first mention in the text, in accordance with standard formatting guidelines.
Comment 9: The English language needs some correction in places.
Response 9: Thank you for your observation. We have carefully reviewed the manuscript and used Grammarly software to improve the clarity and correctness of the English language throughout the text.
Reviewer 2 Report
Comments and Suggestions for AuthorsAgriculture has been rapidly adopting modern technologies in recent years. Terms like Agriculture 4.0 and Smart Farming are now commonly used in both industry and academia. Each year, hundreds of research articles are published in this domain, along with numerous review papers covering various emerging directions.
One of the popular areas is the application of machine learning and remote sensing in agriculture. This field is gaining attention not only in scientific research but also in commercial and industrial projects. Several high-quality review papers have been published recently. For example:
Wang, J.; Wang, Y.; Li, G.; Qi, Z. Integration of Remote Sensing and Machine Learning for Precision Agriculture: A Comprehensive Perspective on Applications. Agronomy 2024, 14, 1975. https://doi.org/10.3390/agronomy14091975
Padhiary, M.; Saikia, P.; Roy, P., et al. (2025). A Review on Advancing Agricultural Efficiency through Geographic Information Systems, Remote Sensing, and Automated Systems. Cureus Journal of Engineering, 2: es44388-024-00559-7. https://doi.org/10.7759/s44388-024-00559-7
In contrast to these comprehensive and well-structured reviews, the paper under discussion presents a rather unusual approach by focusing on the application of remote sensing and machine learning in Controlled Environment Agriculture (CEA)—including greenhouses, vertical farms, and indoor farming systems.
While machine learning is indeed widely applied in CEA (e.g., for plant disease detection, environmental control, and yield optimization), the use of remote sensing in the conventional sense (i.e., satellite or aerial imagery) is largely irrelevant in such enclosed environments. "Proximal sensing techniques—such as hyperspectral imaging, near-infrared (NIR) spectroscopy, and chlorophyll fluorescence spectroscopy—have been effectively applied within greenhouses and indoor farms, but the authors do not present any information on these methods.
Furthermore, the organization of the paper, the selection of literature for review, and the described methodologies raise concerns regarding scientific rigor. However, given the fundamental conceptual mismatch—using traditional remote sensing in CEA—these structural issues become secondary.
Author Response
Thank you for taking the time to review our manuscript. We would like to offer the following clarifications regarding your comments:
Agriculture has been rapidly adopting modern technologies in recent years. Terms like Agriculture 4.0 and Smart Farming are now commonly used in both industry and academia. Each year, hundreds of research articles are published in this domain, along with numerous review papers covering various emerging directions.
One of the popular areas is the application of machine learning and remote sensing in agriculture. This field is gaining attention not only in scientific research but also in commercial and industrial projects. Several high-quality review papers have been published recently. For example:
Wang, J.; Wang, Y.; Li, G.; Qi, Z. Integration of Remote Sensing and Machine Learning for Precision Agriculture: A Comprehensive Perspective on Applications. Agronomy 2024, 14, 1975. https://doi.org/10.3390/agronomy14091975
Padhiary, M.; Saikia, P.; Roy, P., et al. (2025). A Review on Advancing Agricultural Efficiency through Geographic Information Systems, Remote Sensing, and Automated Systems. Cureus Journal of Engineering, 2: es44388-024-00559-7. https://doi.org/10.7759/s44388-024-00559-7
In contrast to these comprehensive and well-structured reviews, the paper under discussion presents a rather unusual approach by focusing on the application of remote sensing and machine learning in Controlled Environment Agriculture (CEA)—including greenhouses, vertical farms, and indoor farming systems.
- Our research is a bibliometric analysis, not a systematic literature review. The methodology was designed to map trends, key publications, and emerging research directions based on co-word and co-occurrence analysis from a curated dataset. As described in the methodology section, only a subset of papers (12 out of 70) was analyzed in depth based on their relevance and full-text availability.
While machine learning is indeed widely applied in CEA (e.g., for plant disease detection, environmental control, and yield optimization), the use of remote sensing in the conventional sense (i.e., satellite or aerial imagery) is largely irrelevant in such enclosed environments. "Proximal sensing techniques—such as hyperspectral imaging, near-infrared (NIR) spectroscopy, and chlorophyll fluorescence spectroscopy—have been effectively applied within greenhouses and indoor farms, but the authors do not present any information on these methods.
Furthermore, the organization of the paper, the selection of literature for review, and the described methodologies raise concerns regarding scientific rigor. However, given the fundamental conceptual mismatch—using traditional remote sensing in CEA—these structural issues become secondary.
- We agree that techniques such as hyperspectral imaging, NIR spectroscopy, and chlorophyll fluorescence are relevant within CEA systems. However, these terms did not emerge as significant keywords in our co-word analysis, which reflects the thematic structure of the existing literature rather than our own thematic decisions. As such, they were not included in the final conceptual mapping. To address this, we added the following clarification at the end of the first paragraph in the Cluster 4 analysis:
"On the other hand, proximal sensing – which involves sensors placed in close contact with plants or soils (e.g., chlorophyll meters, hyperspectral cameras, or root zone sensors) provides high-resolution, real-time data under artificial lighting and controlled conditions, making them critical for precision monitoring in greenhouses or vertical farms. Although the term does not appear explicitly in our dataset, the technologies described in Cluster 4 align conceptually with proximal sensing methods."
- We also acknowledge this as a limitation of our research, as follows:
One limitation of our approach is that the topic-based search strategy, while ensuring relevance and focus, may have excluded relevant studies that do not explicitly mention “controlled environment agriculture” in their indexed fields. Therefore, some relevant technologies and terms related to RS and ML may not have been included as prominent keywords in our bibliometric analysis.
Reviewer 3 Report
Comments and Suggestions for AuthorsThe paper is a review of remote sensing and ML in agriculture. The paper is well organized and well written. However, some points need to be clarified.
Throughout the text, "machine learning", "remote sensing", "CEA", "RF" and other abbreviations are either indicated or omitted. Reread and check all text for all abbreviations.
Line 134. RQ1: I suggest to include "Controlled Environment Agriculture (CEA)?" here, instead of RQ2.
Line 145. Just these three keywords?
What does "PRISMA" mean?
The reference to Fig. 3 is absent in the text (lines194-200).
Table 1. Check years! - "27"
In fact, you mixed the "3. Results" and "4. Discussion" sections. Results should report results of the study, avoiding references.
In fact, I wonder why, for instance, papers https://doi.org/10.1038/s41598-023-44132-4 or https://doi.org/10.1007/s11119-024-10128-x (and numerous! other) aren't included in the analyses, as they meet the rules (RS, ML).
The conclusion section needs to be presented.
Author Response
We are grateful for your time and thoughtful review of our work. Your insightful observations have helped us improve the quality of the manuscript. Please find our detailed responses to each of your comments below.
The paper is a review of remote sensing and ML in agriculture. The paper is well organized and well written. However, some points need to be clarified.
1. Throughout the text, "machine learning", "remote sensing", "CEA", "RF" and other abbreviations are either indicated or omitted. Reread and check all text for all abbreviations.
Thank you for your observation. We confirm that all abbreviations were spelled out in full upon their first occurrence in the manuscript, with the exception of UAV. We have now clarified this by explicitly defining UAV as Unmanned Aerial Vehicle at its first mention.
2. Line 134. RQ1: I suggest to include "Controlled Environment Agriculture (CEA)?" here, instead of RQ2.
Thank you for the suggestion. We changed as follows:
"RQ1: What are the key publication trends, influential articles, and the most productive authors and countries in the field of Machine Learning and Remote Sensing applied to Controlled Environment Agriculture (CEA)?
RQ2: What are the research directions on the use of Machine Learning and Remote Sensing in sustainable agriculture?"
3. Line 145. Just these three keywords?
We conducted a topic search using the Web of Science Core Collection, applying the following structure: ("machine learning" AND "controlled environment agriculture" AND "sustainable") OR ("remote sensing" AND "controlled environment agriculture" AND "sustainable"), as it is mention in Figure 1. We chose this structure to focus specifically on the intersection of these technologies within the context of sustainability in CEA. While we acknowledge that this may have excluded some relevant studies that do not explicitly mention “sustainable,” we prioritized thematic precision to stay aligned with our research objectives
4. What does "PRISMA" mean?
Thank you for pointing this out. We now clarify in the manuscript that PRISMA stands for Preferred Reporting Items for Systematic Reviews and Meta-Analyses. The PRISMA flow diagram (Figure 1) was used to transparently report the selection process of the papers included in our bibliometric analysis. We have added this explanation to the manuscript for clarity.
5. The reference to Fig. 3 is absent in the text (lines194-200).
Thank you for pointing this out. We have now added a direct reference to Figure 3 in the revised manuscript, as follows:
"Analysis of the distribution of scientific production by country, presented in Figure 3, reveals a clear imbalance, with a few nations contributing a substantial share of the publications."
This ensures the figure is properly contextualized within the discussion.
6. Table 1. Check years! - "27"
Thank you for pointing this out. We have carefully reviewed and corrected the publication years in Table 1. The previous inaccuracies were due to a formatting oversight during manuscript preparation, and we apologize for the confusion.
7. In fact, you mixed the "3. Results" and "4. Discussion" sections. Results should report results of the study, avoiding references.
Thank you for this observation. We understand the importance of maintaining a clear distinction between the "Results" and "Discussion" sections in academic manuscripts. However, given the bibliometric nature of our study, we would like to clarify that the references mentioned in the "Results" section are not external sources introduced to support interpretations or arguments, as is typical in a discussion, but are instead part of the analyzed dataset itself. In bibliometric studies, the results naturally include references to the relevant articles, authors, journals, and clusters, as these are the units of analysis. Their inclusion is necessary to faithfully present the outcomes of our co-word analysis, performance analysis, and clustering.
8. In fact, I wonder why, for instance, papers https://doi.org/10.1038/s41598-023-44132-4 or https://doi.org/10.1007/s11119-024-10128-x (and numerous! other) aren't included in the analyses, as they meet the rules (RS, ML).
Thank you for this valuable observation. As mentioned in the methodology section, we conducted a topic search in the Web of Science Core Collection using the following search string:
("machine learning" AND "controlled environment agriculture" AND "sustainable") OR ("remote sensing" AND "controlled environment agriculture" AND "sustainable").
Upon rechecking, the two papers referenced do not include "controlled environment agriculture" as a topic term (i.e., in title, abstract, or keywords indexed in Web of Science). Since our search relied strictly on topic-based indexing to ensure relevance and focus, these articles were not captured by the query. We acknowledge this as a limitation of our approach, and we now make this more explicit in the revised manuscript, as follows:
"One limitation of our approach is that the topic-based search strategy, while ensuring relevance and focus, may have excluded relevant studies that do not explicitly mention “controlled environment agriculture” in their indexed fields."
9. The conclusion section needs to be presented.
Thank you for your observation. According to the journal’s guidelines, the Conclusion section is optional and typically recommended only when the Discussion section is unusually long or complex. Given that our discussion is concise and already includes a clear summary of key findings and their implications, we have opted not to add a separate Conclusion section. We believe this approach maintains clarity without redundancy.
Reviewer 4 Report
Comments and Suggestions for AuthorsThe manuscript “Application of Remote Sensing and Machine Learning in Sustainable Agriculture" highlights the important factors for sustainable architecture.
The authors present good insights and analysis. But I would recommend it make some revisions before the acceptance.
- Integration of remote sensing and ML techniques is a popular trend with many papers in the frontier, the paper would benefit from the inclusion of more recent studies published in high-impact journals (e.g., Nature, Science, PNAS), which often reflect the most up-to-date and frontier-level advancements in the field.
- What’s the advantage of disadvantage of each cluster? What about the evaluations on different approaches?
- Figure format:
- Improve figure captions: too short and simple. E.g., Figure 1
- Font in figures (including capital or not letter): not same as that in the text, e.g., Figure 1 and 2
- No axis name for some plots, e.g., Figure 2
- some figures are blurring and not clear to read, like Figrue 5
Author Response
The manuscript “Application of Remote Sensing and Machine Learning in Sustainable Agriculture" highlights the important factors for sustainable architecture.
The authors present good insights and analysis. But I would recommend it make some revisions before the acceptance.
We are grateful for your time and thoughtful review of our work. Your insightful observations have helped us improve the quality of the manuscript. Please find our detailed responses to each of your comments below.
1. Integration of remote sensing and ML techniques is a popular trend with many papers in the frontier, the paper would benefit from the inclusion of more recent studies published in high-impact journals (e.g., Nature, Science, PNAS), which often reflect the most up-to-date and frontier-level advancements in the field.
We appreciate your valuable suggestion regarding the inclusion of more recent studies published in high-impact journals. Our search was conducted in the Web of Science Core Collection, which covers a wide range of high-impact journals. No filter was applied regarding publication years, allowing for a comprehensive analysis of the temporal evolution of the research field. However, the papers included in our analysis were identified based on a structured topic-based search strategy aligned with our bibliometric methodology. Consequently, only publications matching these predefined criteria were included. We acknowledge that this approach may have excluded some relevant frontier-level studies and have now addressed this as a limitation in the revised manuscript.
2. What’s the advantage of disadvantage of each cluster? What about the evaluations on different approaches?
Thank you for your insightful comment and valuable suggestion. We have integrated a paragraph into the discussion section that highlights the advantages and disadvantages of each cluster, as well as evaluations of the different approaches. This paragraph outlines the strengths and challenges specific to each cluster, along with considerations regarding data quality, technical capacity, and contextual factors that influence the performance and scalability of the proposed solutions.
Each cluster presents distinct advantages and challenges. Cluster 1 integrates remote sensing and ecological approaches to enhance climate adaptation and soil management, though it may face data quality sensitivities and environmental concerns related to some technologies like plastic greenhouses. Cluster 2 focuses on AI-powered vision for precise crop and pest monitoring, showing high accuracy with deep learning models but requiring large datasets and advanced technical capacity. Cluster 3 centers on IoT and big data for smart farming, improving resource use through sensor networks, yet faces integration complexity and adoption barriers due to cost and skills needed. Cluster 4 focuses on intelligent systems in controlled environments, offering real-time optimization and innovative automation, though substantial investment and model generalizability remain challenges. Evaluations across clusters highlight that while each approach advances sustainable agriculture, their performance and scalability depend strongly on data quality, technical capacity, and contextual factors.
3. Figure format:
Improve figure captions: too short and simple. E.g., Figure 1
We would like to kindly clarify that the PRISMA diagram should be interpreted in conjunction with the explanation provided in the Materials and Methods section. We therefore prefer to retain the current format of the PRISMA figure, as it complements - rather than duplicates - the information already presented in the methodology.
Font in figures (including capital or not letter): not same as that in the text, e.g., Figure 1 and 2
Thank you for pointing out the inconsistency regarding the fonts used in the figures. We have now revised the figures to ensure that the font style is consistent with the manuscript text throughout. Specifically, we have standardized the fonts in all figures to match the manuscript, except for Figures 4 and 5, which are direct exports from VOSviewer. As this software does not support customization to match the manuscript font, we have retained the original style in those figures. Additionally, we have corrected the use of capital letters in Figure 1 to align with proper formatting conventions.
No axis name for some plots, e.g., Figure 2
Thank you for your observation. We have now included axis labels in all plots.
some figures are blurring and not clear to read, like Figrue 5
Thank you for your observation. Figure 5 was generated using VOSviewer and illustrates the overlay visualization of keyword co-occurrences. Due to the large number of keywords included in the analysis, the available space on the map becomes limited. As a result, VOSviewer automatically compresses and adjusts the positioning of nodes to optimize readability and layout. Inevitably, keywords with lower frequency or relevance are rendered smaller and may appear less visible. Unfortunately, these visual limitations are inherent to the software and cannot be manually adjusted without altering the structure and meaning of the visualization.
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThe authors took my comments into account and made the appropriate corrections to the manuscript. I am satisfied and recommend accepting the manuscript for publication.
Reviewer 2 Report
Comments and Suggestions for AuthorsAs the authors state in their response, “they have created a systematic literature review, and the methodology was designed to map trends, key publications, and emerging research directions based on co-word and co-occurrence analysis. As described in the methodology section, only a subset of papers (12 out of 70) was analyzed in depth based on their relevance and full-text availability.”
I have been involved in various projects related to the application of AI in agriculture since 2017, and I can confidently say that there are hundreds, not merely dozens, of papers focused on the application of remote sensing and machine learning in sustainable agriculture.
A major issue with this manuscript is the inconsistent use of terminology. While the title refers to “Sustainable Agriculture”, the body of the paper predominantly focuses on Controlled Environment Agriculture (CEA). These are not interchangeable terms.
As I already mentioned in my initial review, there is no practical application of remote sensing (satellite or aerial imagery) in Controlled Environment Agriculture (CEA), such as vertical farms or greenhouses.
To produce a high-quality review suitable for publication in a journal like Sustainability, the authors should significantly improve their understanding of AI and remote sensing applications in agriculture, ideally supported by firsthand experience.
Reviewer 3 Report
Comments and Suggestions for AuthorsAll suggestions and comments were revised. No more comments.