New Generation Sustainable Technologies for Soilless Vegetable Production

Comment

Response

Comment 1: Since this paper is a review paper, detailed descriptions for screening studies, selection criteria, and selection results are necessary.

Thank you for your insightful comment number 1. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the revisions I have implemented in the manuscript.

1.4. Methodology for Literature Selection and Analysis in Soilless Agricultural Technologies.

In the pursuit of a comprehensive review of the current literature on soilless plant production, we meticulously established a set of selection criteria to ensure the inclusion of articles that were not only thematically relevant but also contributed significantly to the collective understanding of soilless agricultural practices, with a particular focus on technological innovation and sustainability. Our selection process prioritized articles that offered an all-encompassing view of the policies, technological advancements, and practical applications pertinent to soilless culture, especially hydroponics. We focused on studies delved into soilless cultivation methods, emphasizing hydroponics, bioponics, and related innovative technologies. Research discussing integrating emerging technologies, such as sensors, artificial intelligence, and automation systems, was deemed essential to capture the evolving landscape of soilless farming. Sustainability and efficiency were at the forefront of our selection criteria. Articles that examined the sustainability aspects of soilless systems, including but not limited to resource management, energy consumption, and environmental impacts, were considered critical for inclusion.

Furthermore, we sought out case studies and real-world implementations of hydroponic systems that provided empirical data or firsthand accounts, thus ensuring that the review was grounded in practical, actionable insights. In recognizing the rapid pace of technological advancement in this field, we preferred recent publications, particularly those from the last few years, to ensure that our review reflected the most current state of the art. Our selection process yielded diverse studies that spanned a broad spectrum of research areas within soilless agriculture. This included articles that provided in-depth policy and economic analyses, explored innovative technologies for enhancing plant growth in hydroponic systems, and discussed resource management strategies aimed at reducing greenhouse gas emissions in greenhouse systems. Additionally, we included works that explored the concept of smart agriculture, such as the use of smart greenhouses and the assessment of solar energy, underscoring a growing trend towards precision agriculture and the adoption of renewable energy sources. We also addressed the challenges and prospects of adopting climate-smart agricultural practices, reflecting on the barriers to adoption and the potential for future opportunities. Case studies and practical experiences were also integral to our selection, providing valuable insights into the real-world implementation of hydroponic systems. Through this rigorous selection methodology, our review encapsulates a wide array of topics within soilless agriculture, offering a nuanced and well-rounded understanding of the field that spans from high-level policy analysis to detailed technological applications.

These modifications can be found in the manuscript from lines 83 to 118.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 2: It is essential to add references to each technology in Table 1 through Table 6.

Dear Reviewer, thank you for your valuable feedback and suggestions regarding my manuscript.

These modifications can be found in the manuscript in the following lines:

Table 1: from 160 to 162

Table 2: from 290 to 291

Table 3: from 537 to 538

Table 4: from 613 to 614

Table 5: from 781 to 782

Table 6: from 995 to 996

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 3: Future directions and challenges are derived from the reviewed studies, so their relations should be specific.

Thank you for your insightful comment. To address this, we incorporated several modifications and additions throughout the manuscript, which we hope clarify the future impact and concerns of incorporating new technologies in soilless production.

These modifications can be found throughout the manuscript, but mainly between lines 161 to 202, 511 to 535, 608 to 670, 782 to 806, 934 to 975, and 996 to 1023.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment

Response

Comment 1: Lines 33-34: It is not always true that the method offers higher yields

Dear Reviewer, thank you for your comment. In this sense, and considering the vast review we carried out regarding this topic, we could not find studies that explicitly state that yield is not increased in soilless cultures. To bolster this statement, we added the following references, which provide comprehensive evidence and insights into the advantages of soilless culture systems:

1. Gebereegziher, W. G. (2023). Soilless culture technology to transform vegetable farming and reduce land pressure and degradation in drylands. In Cogent Food and Agriculture (Vol. 9, Issue 2). Informa Healthcare. https://doi.org/10.1080/23311932.2023.2265106
2. Massa, D., Magán, J. J., Montesano, F. F., & Tzortzakis, N. (2020). Minimizing water and nutrient losses from soilless cropping in southern Europe. In Agricultural Water Management (Vol. 241). Elsevier B.V. https://doi.org/10.1016/j.agwat.2020.106395
3. Tzortzakis, N., Nicola, S., Savvas, D., & Voogt, W. (2020). Editorial: Soilless Cultivation Through an Intensive Crop Production Scheme. Management Strategies, Challenges, and Future Directions. In Frontiers in Plant Science (Vol. 11). Frontiers Media S.A. https://doi.org/10.3389/fpls.2020.00363

These references have been carefully selected to provide a broader perspective and support for the advantages of soilless culture systems in agricultural practices. These additions will significantly enhance the manuscript and provide a more robust foundation for the claims presented.

The additions can be found between lines 32 to 33.

Comment 2: Lines 316-317: The authors introduce the concept of equity without going into depth on the issue. This is too generic and further investigation is necessary.

Thank you for your comment regarding the brief mention of the concept of equity on lines 316-317 of our manuscript. After carefully considering your feedback, we have concluded that an in-depth discussion of equity is beyond the scope of our study's primary objectives. To maintain the focus and coherence of our research, we have removed the direct references to "equity" from these sections. This decision ensures that the manuscript remains concentrated on its core topics without the potential distraction of an underexplored concept.

The revisions have been made throughout the manuscript.

Comment 3: Line 378: remove the comma after [79]

Dear Reviewer, thank you for your feedback.

These modifications can be found in the manuscript in line 452.

Comment 4: Lines 449-450: The authors should better specify the data security risks. I believe it is overrated.

Thank you for your insightful comment number 4. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the revisions I have implemented in the manuscript.

This subject is discussed in sections 6.4 and 8.3. Nevertheless, a new text was included in section 5.4 to address this concern:

“In this regard, the adoption of smart sensing and monitoring technologies is accompanied by security issues that can compromise farming operations, data integrity, and privacy. Small vulnerabilities can become cybersecurity threats, considering that smart farms are very interconnected systems and farmers have limited awareness of the risks associated with smart agriculture systems [158]; if someone exploits those vulnerabilities, it can create the potential to disrupt the economies of countries. These attacks can be at the data level (leakage of confidential data, insertion of false data, misconfiguration), at the network and equipment level (radio frequency jamming or signal disruption, malware injection, denial of service DoS and distributed denial of service DDoS, Botnet or central malicious system, data transit attacks, autonomous system hijacking, node capture), at the chain level of supplies (third party attacks, software update attacks, data fabrication) or other types of attacks (unauthorized access, cloud computing attacks) [159,160]”

References:

158. Otieno An Extensive Survey of Smart Agriculture Technologies: Current Security Posture. World Journal of Advanced Research and Reviews 2023, 18, 1207–1231, doi:10.30574/wjarr.2023.18.3.1241.

159. Rettore de Araujo Zanella, A.; da Silva, E.; Pessoa Albini, L.C. Security Challenges to Smart Agriculture: Current State, Key Issues, and Future Directions. Array 2020, 8, 100048, doi:10.1016/J.ARRAY.2020.100048.

160. Demestichas, K.; Peppes, N.; Alexakis, T. Survey on Security Threats in Agricultural Iot and Smart Farming. Sensors (Switzerland) 2020, 20, 1–17.

These modifications can be found in the manuscript from lines 550 to 562.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 5: Line 513: Enter . at the end of the phrase

Dear Reviewer, thank you for your feedback regarding the manuscript. Considering all the comments from the reviewers, extensive changes were made throughout the text, and the text from that line is no longer there.

Comment 6: Line 528: Authors should explain the ethics aspects of this paragraph

Thank you for your insightful comment on number 6. I value the opportunity to refine our manuscript based on your feedback. Below is our detailed response to your comment and the specific revisions we have implemented in the manuscript.

“Third, the ethical issue regarding the use of AI in agricultural production has gained great interest over the past few years, which can be related to concerns of issues derived from inadequate design and setup of intelligent systems, which could lead to negative outcomes in agricultural production, such as violations of farmers' privacy, harm to animal welfare due to the incorporation of robotic technologies, among others [216–218].”

References:

216.     Uddin, M.; Chowdhury, A.; Kabir, M.A. Legal and Ethical Aspects of Deploying Artificial Intelligence in Climate-Smart Agriculture. AI Soc 2022, doi:10.1007/s00146-022-01421-2.

217.     Dara, R.; Yang, Q.; Joy, R.; Flor, B.; Whitfield, S.; Mehdi, S.; Fard, H.; Kaur, J. Recommendations for Ethical and Responsible Use of Artificial Intelligence in Digital Agriculture. Front Artif Intell 2022, 5, doi:10.3389/frai.2022.884192.

218.     Ryan, M. The Social and Ethical Impacts of Artificial Intel-ligence in Agriculture: Mapping the Agricultural AI Litera-ture. AI Soc 2022, doi:10.1007/s00146-021-01377-9.

These modifications can be found in the manuscript from lines 727 to 732.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 7: Line 558-561: those equations are known to overestimate or underestimate the Etc depending on the period

Thank you for your insightful comment number 7. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the specific revisions I have implemented in the manuscript.

“This is because in certain climatic conditions, PM and HG equations can overestimate or underestimate ETc, as has been evidenced by several authors [227–236].”

References:

227. Moradi, A. Evaluation of the FAO Proposed Models for Reference Crop Evapotranspiration (ETo) Estimation in Hajiabad Watershed of Hormozgan Province. Watershed Management Research Journal 2023, 36, 121–133, doi:10.22092/wmrj.2022.358978.1477.

228. Hua, D.; Hao, X.; Zhang, Y.; Qin, J. Uncertainty Assess-ment of Potential Evapotranspiration in Arid Areas, as Es-timated by the Penman-Monteith Method. J Arid Land 2020, 12, 166–180, doi:10.1007/s40333-020-0093-7.

229. Ndulue, E.; Ranjan, R.S. Performance of the FAO Penman-Monteith Equation under Limiting Conditions and Four-teen Reference Evapotranspiration Models in Southern Manitoba. Theor Appl Climatol 2021, 143, 1285–1298, doi:10.1007/s00704-020-03505-9.

230. Song, X.; Lu, F.; Xiao, W.; Zhu, K.; Zhou, Y.; Xie, Z. Per-formance of 12 Reference Evapotranspiration Estimation Methods Compared with the Penman–Monteith Method and the Potential Influences in Northeast China. Meteorolog-ical Applications 2019, 26, 83–96, doi:https://doi.org/10.1002/met.1739.

231. Paredes, P.; Pereira, L.S.; Almorox, J.; Darouich, H. Reference Grass Evapotranspiration with Reduced Data Sets: Parameterization of the FAO Penman-Monteith Temperature Approach and the Hargeaves-Samani Equation Using Local Climatic Variables. Agric Water Manag 2020, 240, 106210, doi:10.1016/J.AGWAT.2020.106210.

232. Djaman, K.; O’Neill, M.; Diop, L.; Bodian, A.; Allen, S.; Koudahe, K.; Lombard, K. Evaluation of the Penman-Monteith and Other 34 Reference Evapotranspiration Equations under Limited Data in a Semiarid Dry Climate. Theor Appl Climatol 2019, 137, 729–743, doi:10.1007/s00704-018-2624-0.

233. Moratiel, R.; Bravo, R.; Saa, A.; Tarquis, A.M.; Almorox, J. Estimation of Evapotranspiration by the Food and Agricultural Organization of the United Nations (FAO) Penman–Monteith Temperature (PMT) and Hargreaves–Samani (HS) Models under Temporal and Spatial Criteria – a Case Study in Duero Basin (Spain). Natural Hazards and Earth System Sciences 2020, 20, 859–875, doi:10.5194/nhess-20-859-2020.

234. Cui, N.; He, Z.; Jiang, S.; Wang, M.; Yu, X.; Zhao, L.; Qiu, R.; Gong, D.; Wang, Y.; Feng, Y. Inter-Comparison of the Penman-Monteith Type Model in Modeling the Evapotran-spiration and Its Components in an Orchard Plantation of Southwest China. Agric Water Manag 2023, 289, 108541, doi:10.1016/J.AGWAT.2023.108541.

235. Kim, H.J.; Chandrasekara, S.; Kwon, H.H.; Lima, C.; Kim, T. woong A Novel Multi-Scale Parameter Estimation Approach to the Hargreaves-Samani Equation for Estimation of Penman-Monteith Reference Evapotranspiration. Agric Water Manag 2023, 275, 108038, doi:10.1016/J.AGWAT.2022.108038.

236. Zheng, S.; Wang, T.; Wei, X. Estimating Grapevine Transpiration in Greenhouse with Three Different Methods in a Penman–Monteith Model in Northeast China. Irrig Sci 2022, 40, 13–27, doi:10.1007/s00271-021-00753-z.

These modifications can be found in the manuscript from lines 771 to 773.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 8: Line 701: It is not clear what farmers' intellectual property is.

Thank you for your insightful comment number 8. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the specific revisions I have implemented in the manuscript.

In the context of the rapid advancement of next-generation technologies in soilless vegetable production, "data and intellectual property of farmers" takes on a multifaceted dimension that intersects with privacy, security, and economic interests [163]. As we integrate sophisticated AI and real-time monitoring systems into agricultural practices, these systems invariably collect and process vast data points [164,165]. This data, ranging from crop health metrics to environmental conditions within soilless systems, constitutes an asset central to the operational success and innovation in modern farming. In this sense, farmers' intellectual property extends beyond the traditional understanding of crop varieties or farming techniques. It now includes the unique datasets and the proprietary algorithms developed to interpret this data, optimize production, and manage resources efficiently. The data collected through these advanced systems can reveal insights into the micro-level responses of crops to various stimuli, which, when analyzed, contribute to the macro-level strategies for improving yield and sustainability. However, the aggregation and analysis of such data also raise significant concerns regarding ownership and control. Who has the right to access, analyze, and benefit from this data? How can farmers protect their data from being exploited by larger entities that can process and utilize this information at a scale far beyond the individual farmer's capability? These questions underscore the need for robust regulatory frameworks that recognize the value of this data and the intellectual property it generates [163]. Regulatory guidelines must be crafted to ensure that farmers retain control over their data and their intellectual contributions to soilless agriculture. This involves establishing clear data governance policies that address consent, access rights, and the distribution of benefits derived from data use.

“In the context of the rapid advancement of next-generation technologies in soilless vegetable production, "data and intellectual property of farmers" takes on a multifacet-ed dimension that intersects with privacy, security, and economic interests [309]. As we integrate sophisticated AI and real-time monitoring systems into agricultural practices, these systems invariably collect and process vast data points [310,311]. This data, rang-ing from crop health metrics to environmental conditions within soilless systems, consti-tutes an asset central to the operational success and innovation in modern farming. Farmers' intellectual property extends beyond the traditional understanding of crop va-rieties or farming techniques. It now includes the unique datasets and the proprietary algorithms developed to interpret this data, optimize production, and manage resources efficiently. The data collected through these advanced systems can reveal insights into the micro-level responses of crops to various stimuli, which, when analyzed, contribute to the macro-level strategies for improving yield and sustainability. However, the ag-gregation and analysis of such data also raise significant concerns regarding ownership and control. Who has the right to access, analyze, and benefit from this data? How can farmers protect their data from being exploited by larger entities that can process and utilize this information at a scale far beyond the individual farmer's capability? These questions underscore the need for robust regulatory frameworks that recognize the value of this data and the intellectual property it generates [309]. Regulatory guidelines must be crafted to ensure that farmers retain control over their data and their intellectual contributions to soilless agriculture. This involves establishing clear data governance policies that address consent, access rights, and the distribution of benefits derived from data use.

Moreover, these guidelines must safeguard against unauthorized use of data, pre-vent data breaches, and ensure that farmers' data is not used in ways that could harm their competitive position or violate their privacy [310,311]. As we consider integrating new materials, energy sources, and potentially genetically modified crops into soilless farming systems, the scope of intellectual property also expands. It now encompasses the innovative use of alternative substrates, the development of crops specifically tai-lored to soilless conditions, and the creation of new technologies for energy efficiency [312,313]. Each area brings with it the need for updated safety and environmental im-pact assessments and the potential for new patents and trademarks. Standardization efforts are critical to ensure that these new technologies can be seamlessly integrated with existing systems, but they must be a balanced protection of farmers' intellectual property rights [314]. Without such protections, there is a risk that the benefits of innovation will accrue only to those with the resources to exploit them, potentially widening the gap between large-scale operations and smaller, resource-constrained farmers.

Furthermore, access to technology is a pressing concern [310]. Policies must be de-signed to ensure that all farmers, regardless of scale, can benefit from technological advancements. This includes considering the potential impacts of technology adoption, such as the job displacement due to automation [315]. Policy frameworks must protect data and intellectual property and address the socioeconomic impacts of technology adoption, ensuring that the transition to more advanced systems is just and inclusive.”

References:

309.     König, B.; Janker, J.; Reinhardt, T.; Villarroel, M.; Junge, R. Analysis of Aquaponics as an Emerging Technological Innovation System. J Clean Prod 2018, 180, 232–243, doi:10.1016/J.JCLEPRO.2018.01.037.

310.     Gardezi, M.; Joshi, B.; Rizzo, D.M.; Ryan, M.; Prutzer, E.; Brugler, S.; Dadkhah, A. Artificial Intelligence in Farming: Challenges and Opportunities for Building Trust. Agron J 2023, 1–12, doi:https://doi.org/10.1002/agj2.21353.

311.     Goh, H.-H.; Vinuesa, R. Regulating Artificial intelligence Applications to achieve the Sustainable Development Goals. Discover Sustainability 2021, 2, doi:10.1007/s43621-021-00064-5.

312.     Fields, J.S.; Owen, J.; Lamm, A.; Altland, J.E.; Jackson, B.E.; Zheng, Y.; Oki, L.; Fontenot, K.; Samtani, J.; Camp-bell, B. Soilless Substrate Science: A North American Needs Assessment to Steer Soilless Substrate Research into the Fu-ture. In Proceedings of the Acta Horticulturae; International Society for Horticultural Science (ISHS), Leuven, Belgium, August 20 2021; pp. 313–318.

313.     Türkten, H.; Ceyhan, V. Environmental Efficiency in Greenhouse Tomato Production Using Soilless Farming Technology. J Clean Prod 2023, 398, 136482, doi:https://doi.org/10.1016/j.jclepro.2023.136482.

314.     Qian, C.; Murphy, S.I.; Orsi, R.H.; Wiedmann, M. How Can AI Help Improve Food Safety? Annu Rev Food Sci Technol 2023, 14, 517–538, doi:10.1146/annurev-food-060721-013815.

315.     Sun, W.; Zhang, Z.; Chen, Y.; Luan, F. Heterogeneous Effects of Robots on Employment in Agriculture, Industry, and Services Sectors. Technol Soc 2023, 75, 102371, doi:https://doi.org/10.1016/j.techsoc.2023.102371.

These modifications can be found in the manuscript from lines 934 to 975.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 9: Line 708: Once again, the authors do not specify the aspects relating to ethics

Thank you so much for your observation about our manuscript, specifically your comment on line 708 about the mention of ethics. We appreciate your attention to detail and the importance of clarity in our research. After reviewing your comment and considering the focus and objectives of our study, we have decided to remove the direct references to ethics from this section of the manuscript. This decision was made because an in-depth discussion of ethical aspects is not central to the primary aims of our research. We believe that maintaining these references without the necessary depth could potentially divert attention from the main topics and findings of our study. The relevant sections have been carefully revised to ensure that the manuscript remains focused on its key themes and objectives.

Nevertheless, in section 6.4, a brief discussion regarding the ethical considerations of AI-driven cultivation is incorporated as requested by Reviewer 2 (Lines 727-732).

These changes can be found in the revised manuscript.

Comment

Response

Comment 1: A further in-depth discussion on the benefits and disadvantages of the recent hydroponic technologies shown in Tab. 1 is necessary. For example, it seems that a common disadvantage of these technologies is the high investment, installation, maintenance and operating costs; an in-depth analysis of the extent of these costs would allow the reader to better compare the critical issues of the different technologies.

Thank you for your insightful comment number 1. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the revisions I have implemented in the manuscript.

“As seen in Table 1, advantages and disadvantages are observed when incorporating technologies in the productive soilless system, which must be taken into account before considering implementing hydroponic systems. In terms of the advantages, hydroponic systems can be equipped with automation and sensor technology, allowing for remote monitoring and control [53]. This enables growers to make real-time adjustments to environmental conditions, nutrient delivery, and other parameters [54]. In this sense, the main advantages of the incorporation of advanced technologies in hydroponics are related to a higher efficiency and optimization in the use of resources, being able to precisely control the delivery of water, nutrients, and light to plants, minimizing waste and optimizing resource utilization [45,55,56]. In addition to this, hydroponics typically uses significantly less water compared to traditional soil-based agriculture [57], which can be especially advantageous in regions with water scarcity or drought conditions. Also, the controlled environment in hydroponics allows for accelerated plant growth [28], which means quicker crop turnover and increased productivity, providing a stable and controlled environment for plants, resulting in consistent product quality, reducing the risk of soil-borne diseases and pests. Finally, it is also important to consider that the local climate, market demand, and regulatory factors play a role in determining the extent to which advanced hydroponic technologies are advantageous for a particular agricultural operation. In this sense, when these technologies are well-planned and managed, they can provide significant benefits in terms of resource efficiency, product quality, and yield increase.

Regarding the disadvantages of these technologies, several of them are mentioned in Table 1, however, the most common disadvantage is related to the high initial investment costs, which in hydroponic systems, are mainly related to costs that include items such as grow lights, pumps, nutrient delivery systems, climate control systems, and specialized growing media [58], which are items that allow to generate an advanced technological production system. These costs can vary significantly depending on the scale and complexity of the hydroponic setup. For instance, for large-scale hydroponic operations, the construction or retrofitting of greenhouses or indoor growing spaces can be a substantial expense, influenced by factors like location, size, and design, however, studies such as the one of [59] have tested the incorporation of technologies such as the use of hybrid renewable energy systems (HRES) to reduce operating cost and emissions, concluding that the final cost of cultivating lettuce under the established experimental conditions was similar with the cost of traditionally imported lettuce, which would indicate a high potential in terms of competitiveness of hydroponically grown produce. Another disadvantage of incorporating new technologies in hydroponic systems is that they require technical knowledge and expertise to operate them [47,60]. This includes cleaning, nutrient replenishment, equipment checks, and maintenance costs. Finally, hydroponic systems often rely on artificial lighting and climate control, which can lead to high energy bills. These disadvantages highlight the need to incorporate cost-effective solutions that aid in lowering the final production costs, generating a more competitive final product, and fulfilling the future needs to increase food production.”

References:

28.       Nguyen, N.T.; McInturf, S.A.; Mendoza-Cózatl, D.G. Hydroponics: A Versatile System to Study Nutrient Allocation and Plant Responses to Nutrient Availability and Exposure to Toxic Elements. Journal of Visualized Experiments 2016, 2016, doi:10.3791/54317.

45.       Velazquez-Gonzalez, R.S.; Garcia-Garcia, A.L.; Ventura-Zapata, E.; Barceinas-Sanchez, J.D.O.; Sosa-Savedra, J.C. A Review on Hydroponics and the Technologies Associated for Medium-and Small-Scale Operations. Agriculture (Swit-zerland) 2022, 12.

47.       Herman; Surantha, N. Intelligent Monitoring and Controlling System for Hydroponics Precision Agriculture. In Proceedings of the 2019 7th International Conference on Information and Communication Technology, ICoICT 2019; Institute of Electrical and Electronics Engineers Inc., July 1 2019.

53.       Tiglao, N.M.; Alipio, M.; Balanay, J.V.; Saldivar, E.; Tiston, J.L. Agrinex: A Low-Cost Wireless Mesh-Based Smart Irrigation System. Measurement (Lond) 2020, 161, doi:10.1016/j.measurement.2020.107874.

54.       Alipio, M.I.; Dela Cruz, A.E.M.; Doria, J.D.A.; Fruto, R.M.S. On the Design of Nutrient Film Technique Hydro-ponics Farm for Smart Agriculture. Engineering in Agricul-ture, Environment and Food 2019, 12, 315–324, doi:10.1016/j.eaef.2019.02.008.

55.       Benke, K.; Tomkins, B. Future Food-Production Systems: Vertical Farming and Controlled-Environment Agriculture. Sustainability: Science, Practice and Policy 2017, 13, 13–26, doi:10.1080/15487733.2017.1394054.

56.       Carotti, L.; Pistillo, A.; Zauli, I.; Meneghello, D.; Martin, M.; Pennisi, G.; Gianquinto, G.; Orsini, F. Improving Wa-ter Use Efficiency in Vertical Farming: Effects of Growing Systems, Far-Red Radiation and Planting Density on Lettuce Cultivation. Agric Water Manag 2023, 285, doi:10.1016/j.agwat.2023.108365.

57.       Kennard, N.; Stirling, R.; Prashar, A.; Lopez-Capel, E. Evaluation of Recycled Materials as Hydroponic Growing Media. Agronomy 2020, 10, doi:10.3390/agronomy10081092.

58.       Souza, V.; Gimenes, R.M.T.; de Almeida, M.G.; Farinha, M.U.S.; Bernardo, L.V.M.; Ruviaro, C.F. Economic Feasibility of Adopting a Hydroponics System on Substrate in Small Rural Properties. Clean Technol Environ Policy 2023, doi:10.1007/s10098-023-02529-9.

59.       Udovichenko, A.; Fleck, B.A.; Weis, T.; Zhong, L. Framework for Design and Optimization of a Retrofitted Light Industrial Space with a Renewable Energy-Assisted Hydroponics Facility in a Rural Northern Canadian Community. Journal of Building Engineering 2021, 37, doi:10.1016/j.jobe.2021.102160.

60.       Folorunso, E.A.; Schmautz, Z.; Gebauer, R.; Mraz, J. The Economic Viability of Commercial-Scale Hydroponics: Nigeria as a Case Study. Heliyon 2023, 9, doi:10.1016/j.heliyon.2023.e18979.

These modifications can be found in the manuscript from lines 161 to 202.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 2: The same goes for the benefits and disadvantages of real-time monitoring systems described in Tab. 3. and for the benefits and advantages of AI applications described in Tab. 4.

Thank you for your insightful comment number 2. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the specific revisions I have implemented in the manuscript.

“Table 3 summarizes different real-time monitoring systems, their advantages, and disadvantages in the smart farming agriculture field. The yield and success of a crop depend on the parameters measured by these sensors for the continuous monitoring of environmental conditions and the automation of various aspects of farming operations [113]. The advantage of this approach is that sensors are lightweight, suitable to be de-ployed in harsh conditions and have improved accuracy, removing or reducing the risk of human error inherent to manual data capturing, allowing real-time monitoring and remote access when are integrated to network gateways. Those systems can contribute to increase plant growth [114–116], reduce water consumption [117,118] improve environmental and agricultural parameters [119–123], reduce manpower [124], allow remote monitoring [125–128] and function as an early warning system [129]. Also, IoT devices can allow increased automation of operations. However, real-time monitoring require wireless connectivity, considering that IoT devices are the building blocks of wireless sensor networks (WSN), which it is not always available in farms or rural areas. Another significant limitation to the adoption of these systems is cost, which often prevents its adoption by small farmers, who have increasingly smaller profit margins, but also with larger farms, as scalability of systems it is not fully explored. The high cost is related to the degree of customization required for installation, research and development, up-dates and maintenance and costs associated with data transmission. There are other technical considerations, such as the power source. In many cases there is no access to constant power, therefore, the systems depend on batteries and solar panels for their operation, so consumption and energy conservation becomes an important limitation. Multiple sensors produce huge amounts of data that requires storage (locally or cloud-based) and computing power to be analyzed. This, associated with the lesser technical expertise by farmers, becomes a major setback to IoT-based monitoring [130,131].“

References:

113.     Saiz-Rubio, V.; Rovira-Más, F. From Smart Farming towards Agriculture 5.0: A Review on Crop Data Management. Agronomy 2020, 10.

114.     Liu, J. Design and Implementation of an Intelligent Environmental-Control System: Perception, Network, and Application with Fused Data Collected from Multiple Sensors in a Greenhouse at Jiangsu, China. Int J Distrib Sens Netw 2016, 12, 5056460, doi:10.1177/155014775056460.

115.     Pitakphongmetha, J.; Boonnam, N.; Wongkoon, S.; Hora-nont, T.; Somkiadcharoen, D.; Prapakornpilai, J. Internet of Things for Planting in Smart Farm Hydroponics Style. In Proceedings of the 2016 International Computer Science and Engineering Conference (ICSEC); 2016; pp. 1–5.

116.     Palande, V.; Zaheer, A.; George, K. Fully Automated Hy-droponic System for Indoor Plant Growth. Procedia Comput Sci 2018, 129, 482–488, doi:10.1016/J.PROCS.2018.03.028.

117.     Ferrández-Pastor, F.J.; García-Chamizo, J.M.; Nieto-Hidalgo, M.; Mora-Martínez, J. Precision Agriculture Design Method Using a Distributed Computing Architecture on Internet of Things Context. Sensors (Switzerland) 2018, 18, doi:10.3390/s18061731.

118.     Kodali, R.K.; Jain, V.; Karagwal, S. IoT Based Smart Greenhouse. In Proceedings of the 2016 IEEE Region 10 Humanitarian Technology Conference (R10-HTC); 2016; pp. 1–6.

119.     Jiao, J.; Ma, H.; Qiao, Y.; Du, Y.; Kong, W.; Wu, Z. Design of Farm Environmental Monitoring System Based on the Internet of Things. Advance Journal of Food Science and Technology 2014, 6, 368–373, doi:10.19026/ajfst.6.38.

120.     Jayaraman, P.P.; Yavari, A.; Georgakopoulos, D.; Morshed, A.; Zaslavsky, A. Internet of Things Platform for Smart Farming: Experiences and Lessons Learnt. Sensors (Switzer-land) 2016, 16, doi:10.3390/s16111884.

121.     Pooja, S.; Uday, D. V; Nagesh, U.B.; Talekar, S.G. Application of MQTT Protocol for Real Time Weather Monitoring and Precision Farming. In Proceedings of the 2017 International Conference on Electrical, Electronics, Communica-tion, Computer, and Optimization Techniques (ICEECCOT); 2017; pp. 1–6.

122.     Crisnapati, P.N.; Wardana, I.N.K.; Aryanto, I.K.A.A.; Hermawan, A. Hommons: Hydroponic Management and Monitoring System for an IOT Based NFT Farm Using Web Technology. In Proceedings of the 2017 5th International Conference on Cyber and IT Service Management (CITSM); 2017; pp. 1–6.

123.     Lamprinos, I.; Charalambides, M. Experimental Assessment of Zigbee as the Communication Technology of a Wireless Sensor Network for Greenhouse Monitoring. International Journal of Advanced Smart Sensor Network Systems 2015, 5, 1–10, doi:10.5121/ijassn.2015.5401.

124.     Chieochan, O.; Saokaew, A.; Boonchieng, E. IOT for Smart Farm: A Case Study of the Lingzhi Mushroom Farm at Maejo University. In Proceedings of the 2017 14th Interna-tional Joint Conference on Computer Science and Software Engineering (JCSSE); 2017; pp. 1–6.

125.     Akkaş, M.A.; Sokullu, R. An IoT-Based Greenhouse Moni-toring System with Micaz Motes. Procedia Comput Sci 2017, 113, 603–608, doi:10.1016/J.PROCS.2017.08.300.

126.     Abdul Halim, A.A.; Hassan, M.N.; Zakaria, A.; Kama-rudin, L.; Abu Bakar, A. Internet of Things Technology for Greenhouse Monitoring and Management System Based on Wireless Sensor Network. ARPN Journal of Engineering and Applied Sciences 2016, 11, 13169–13175.

127.     Singh, T.A.; Chandra, J. IOT Based Green House Monitor-ing System. Journal of Computer Science 2018, 14, 639–644, doi:10.3844/jcssp.2018.639.644.

128.     Cambra, C.; Sendra, S.; Lloret, J.; Lacuesta, R. Smart System for Bicarbonate Control in Irrigation for Hydroponic Precision Farming. Sensors (Switzerland) 2018, 18, doi:10.3390/s18051333.

129.     Yan, M.; Liu, P.; Zhao, R.; Liu, L.; Chen, W.; Yu, X.; Zhang, J. Field Microclimate Monitoring System Based on Wireless Sensor Network. Journal of Intelligent & Fuzzy Sys-tems 2018, 35, 1325–1337, doi:10.3233/JIFS-169676.

130.     Yadav, S.; Kaushik, A.; Sharma, M.; Sharma, S. Disruptive Technologies in Smart Farming: An Expanded View with Sentiment Analysis. AgriEngineering 2022, 4, 424–460, doi:10.3390/agriengineering4020029.

131.     Terence, S.; Purushothaman, G. Systematic Review of In-ternet of Things in Smart Farming. Transactions on Emerg-ing Telecommunications Technologies 2020, 31, doi:10.1002/ett.3958.

For table 4, the next section was added to expand the discussion about benefits and disadvantages of the Integration of Artificial Intelligence (AI) .

“AI algorithms can analyze vast amounts of sensor data to make real-time adjustments to nutrient levels, irrigation schedules, and environmental controls, maximizing yield and minimizing resource loss [162,163]. Table 4 resumes the advantages and disadvantages of AI applications over soilless systems.

Given the great number of articles and applications of artificial intelligence in agriculture in general and in soilless systems in particular, the main benefits of this technology include increased efficiency, improved crop quality, reduced labor costs, better decision-making, and more sustainable practices [192]. The optimization of crop yields, by efficiently managing factors such as water, fertilizer, and pest control are one of the main advantages of AI in soilless culture. This optimization leads to higher returns on investment for farmers. AI enables more precise control over irrigation and soil fertilizer application, resulting in higher resource use efficiency. For example, [167] evaluated the performances of four bio-inspired algorithm optimized extreme learning machine (ELM) models for predicting daily reference evapotranspiration (ETo) across China, demonstrated that the values predicted by all ELM models agreed well with the FAO-56 Penman–Monteith values. This means that farmers can achieve higher yields with the same resources or maintain yields by lowering resource use, contributing to sustainable agricultural practices. Other benefit of AI is the reduction in pest and disease by enabling early detection and diagnosis through image signal processing techniques [193]. This early diagnosis, such as identifying powdery mildew, allows for timely intervention and reduces the impact of pests and diseases on crops. Energy use is a key factor in modern agriculture, where AI can contribute to its efficient management be-tween smart greenhouses and soilless systems, allowing cost savings and sustainability. This involves the integration of various technologies, such as bio-inspired algorithms, automation, and dynamic pricing based on real-time metrics.
Regarding automation, AI-driven robotic systems are being utilized for various tasks, including irrigation, harvesting, counting, and other mechanical farming processes. This automation improves efficiency and reduces the labor intensity of farming operations. Also, AI-powered robots platforms can perform unsafe tasks, such as toxic pesticide application and UV-C treatments, to impede the spread of powdery mildew [194–196]. Taking into consideration the above, AI technologies, including bio-inspired algorithms and machine learning, enable precision agriculture. This precision ensures accurate and targeted application of resources, minimizing waste and maximizing productivity. This leads to enhanced agricultural sustainability. By addressing challenges such as re-source optimization, pest control, and energy efficiency, AI contributes to environmentally friendly and economically viable farming practices. AI is no longer just a research topic, as commercially viable AI technologies for agriculture are starting to appear [197]. This suggests ongoing advancements in the field, providing farmers with access to more sophisticated and effective tools for improving their farming practices. However, this promising frontier also presents several challenges that require critical consideration. One of the main constraints of AI implementation is cost, one reason being the expensive sensors (up to $1000+ dollars) [198], considering that for several monitoring instances, multiple sensors, cameras (RGB, thermal, multispectral), and other hardware is required, and for automation, actuators, fans, heathers, lightning, dehumidifiers, and motors are required. As was stated by [199] the cost of installation of AI systems on farms was enormous and out of reach for smallholder farmers. In contrast, larger farms can take the risk of absorbing this higher cost and are more willing to invest [200]. To implement these technologies, technical expertise is needed, as it can be complex and require specialized knowledge to implement and maintain, requiring greater computational resources. This can be a challenge for growers who are not familiar with the technology or who lack technical expertise. That’s the situation in Europe, where the aging of the population and the shortage of young and progressive farmers raises concerns about technology adoption [201], considering that is well-know that less educated and older farmers are less inclined to adopt precision farming technologies [200]. There are also obstacles to transfer this technology to developing countries, due to farm size, less connectivity, reduced infrastructure, and economic issues, among others. Concern-ing predictive models, [202] indicated that the absence of appropriate historical data poses a significant obstacle to the integration of AI systems in agriculture, necessary for accurate predictions and the training of AI and ML systems. Moreover, studies have suggested that the creation of algorithms for assessing greenhouse parameters should be calibrated with local conditions and its specific requirements [203].

References:

162.     Soori, M.; Arezoo, B.; Dastres, R. Artificial Intelligence, Machine Learning and Deep Learning in Advanced Robotics, a Review. Cognitive Robotics 2023, 3, 54–70, doi:10.1016/J.COGR.2023.04.001.

163.     Javaid, M.; Haleem, A.; Khan, I.H.; Suman, R. Under-standing the Potential Applications of Artificial Intelligence in Agriculture Sector. Advanced Agrochem 2023, 2, 15–30, doi:10.1016/J.AAC.2022.10.001.

167.     Wu, L.; Zhou, H.; Ma, X.; Fan, J.; Zhang, F. Daily Reference Evapotranspiration Prediction Based on Hybridized Extreme Learning Machine Model with Bio-Inspired Optimization Algorithms: Application in Contrasting Climates of China. J Hydrol (Amst) 2019, 577, 123960, doi:10.1016/J.JHYDROL.2019.123960.

192.     Maraveas, C. Incorporating Artificial Intelligence Technol-ogy in Smart Greenhouses: Current State of the Art. Ap-plied Sciences (Switzerland) 2023, 13, doi:10.3390/app13010014.

193.     Fernando, S.D.; Gamage, A.; Silva, D.H. De Machine Learning to Aid in the Process of Disease Detection and Management in Soilless Farming. In Proceedings of the 2022 IEEE 7th International conference for Convergence in Technology (I2CT); 2022; pp. 1–5.

194.     Fernando, S.; Nethmi, R.; Silva, A.; Perera, A.; Silva, R. De; Abeygunawardhana, P.W.K. AI Based Greenhouse Farming Support System with Robotic Monitoring. In Pro-ceedings of the 2020 IEEE REGION 10 CONFERENCE (TENCON); 2020; pp. 1368–1373.

195.     Talaviya, T.; Shah, D.; Patel, N.; Yagnik, H.; Shah, M. Implementation of Artificial Intelligence in Agriculture for Optimisation of Irrigation and Application of Pesticides and Herbicides. Artificial Intelligence in Agriculture 2020, 4, 58–73, doi:10.1016/J.AIIA.2020.04.002.

196.     Sammons, P.J.; Furukawa, T.; Bulgin, A. Autonomous Pesticide Spraying Robot for Use in a Greenhouse.; 2005.

197.     Wakchaure, M.; Patle, B.K.; Mahindrakar, A.K. Applica-tion of AI Techniques and Robotics in Agriculture: A Re-view. Artificial Intelligence in the Life Sciences 2023, 3, 100057, doi:10.1016/J.AILSCI.2023.100057.

198.     Garrity, J. Harnessing the Internet of Things for Global Development. SSRN Electronic Journal 2015, doi:10.2139/ssrn.2588129.

199.     Kendall, H.; Clark, B.; Li, W.; Jin, S.; Jones, Glyn.D.; Chen, J.; Taylor, J.; Li, Z.; Frewer, Lynn.J. Precision Agriculture Technology Adoption: A Qualitative Study of Small-Scale Commercial “Family Farms” Located in the North China Plain. Precis Agric 2022, 23, 319–351, doi:10.1007/s11119-021-09839-2.

200.     Maloku, D. Adoption Of Precision Farming Technologies: Usa And Eu Situation. SEA: Practical Application of Science 2020, 7–14.

201.     The European Economic and Social Committee (EESC) Boosting the Use of Artificial Intelligence in Europe’s Micro, Small and Medium-Sized; Brussels, Belgium, 2021;

202.     Karnawat, M.; Trivedi, S.K.; Nagar, D.; Nagar, R. Future of AI in Agriculture. Biotica Research Today 2020, 2, 927–929.

203.     Aytenfsu, S.A.; Beyene, A.M.; Getaneh, T.H. Controlling the Interior of Greenhouses Using Elman Recurrent Neural Network. In Proceedings of the 2020 Fourth World Confer-ence on Smart Trends in Systems, Security and Sustainabil-ity (WorldS4); 2020; pp. 32–39.

We also expand the discussion of table 5, which wasn’t required by the reviewer. We added the following:

“However, there are also potential limitations that need to be addressed in the context of soilless farming. A recurring problem with these technologies is the high initial cost of implementation [262,263]. Additionally, accessibility to these technologies in rural areas may pose challenges, because communication infrastructure (cellular connectivity, internet) is not always available [264]. When these technologies are implemented in real operating environments, the integration of them can be complex, because interoperability is not well established, mainly due to being an area still in development with much research being done in parallel. Therefore, ensuring seamless integration and interoperability among these technologies is crucial for their effective functioning [265,266]. The energy consumption of platforms where AI, machine learning and communications technologies operate can be a limitation, especially in remote or off-grid farming locations [267]. This can impact the sustainability of smart farming systems, particularly when considering renewable energy sources. Also, renewable energy sources suffer from intermittency. For example, solar power generation is affected by factors such as time of day, weather conditions, and seasonal changes, so energy storage technologies, such as batteries, becomes a necessity [268]. AI and machine learning models depend heavily on data quality, hence inaccurate or low-quality data can lead to incorrect decisions and recommendations in smart farming systems [212,269]. These data intensive systems are susceptible to security breaches and privacy concerns among farmers [270], as was discussed previously. Solutions involve ensuring diverse and high-quality datasets, developing explainable AI models, investing in secure communication protocols, addressing intermittency with energy storage, and invest in research to make this technology more available. Additionally, there's a need for government support, subsidies, and education programs to make these technologies more accessible to farmers, promoting widespread adoption in the agricultural sector [271].”

References:

212.     Jain, A.; Patel, H.; Nagalapatti, L.; Gupta, N.; Mehta, S.; Guttula, S.; Mujumdar, S.; Afzal, S.; Sharma Mittal, R.; Munigala, V. Overview and Importance of Data Quality for Machine Learning Tasks. In Proceedings of the Proceed-ings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; Association for Computing Machinery: New York, NY, USA, 2020; pp. 3561–3562.

262.     Walter, A.; Finger, R.; Huber, R.; Buchmann, N. Smart Farming Is Key to Developing Sustainable Agriculture. Proceedings of the National Academy of Sciences 2017, 114, 6148–6150, doi:10.1073/pnas.1707462114.

263.     Sørensen, C.A.G.; Kateris, D.; Bochtis, D. ICT Innovations and Smart Farming. In Proceedings of the Information and Communication Technologies in Modern Agricultural De-velopment; Salampasis, M., Bournaris, T., Eds.; Springer International Publishing: Cham, 2019; pp. 1–19.

264.     López, M.; Damsgaard, S.B.; Rodríguez, I.; Mogensen, P. Connecting Rural Areas: An Empirical Assessment of 5G Terrestrial-LEO Satellite Multi-Connectivity. In Proceedings of the 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring); 2023; pp. 1–5.

265.     Roussaki, I.; Doolin, K.; Skarmeta, A.; Routis, G.; Lopez-Morales, J.A.; Claffey, E.; Mora, M.; Martinez, J.A. Building an Interoperable Space for Smart Agriculture. Digital Communications and Networks 2023, 9, 183–193, doi:https://doi.org/10.1016/j.dcan.2022.02.004.

266.     Khatoon, P.S.; Ahmed, M. Importance of Semantic Interop-erability in Smart Agriculture Systems. Transactions on Emerging Telecommunications Technologies 2022, 33, e4448, doi:https://doi.org/10.1002/ett.4448.

267.     Jawad, H.M.; Nordin, R.; Gharghan, S.K.; Jawad, A.M.; Ismail, M. Energy-Efficient Wireless Sensor Networks for Precision Agriculture: A Review. Sensors (Switzerland) 2017, 17, doi:10.3390/s17081781.

268.     Meral, M.E.; Dinçer, F. A Review of the Factors Affecting Operation and Efficiency of Photovoltaic Based Electricity Generation Systems. Renewable and Sustainable Energy Reviews 2011, 15, 2176–2184, doi:https://doi.org/10.1016/j.rser.2011.01.010.

269.     Okafor, N.U.; Alghorani, Y.; Delaney, D.T. Improving Data Quality of Low-Cost IoT Sensors in Environmental Monitoring Networks Using Data Fusion and Machine Learning Approach. ICT Express 2020, 6, 220–228, doi:https://doi.org/10.1016/j.icte.2020.06.004.

270.     Wiseman, L.; Sanderson, J.; Zhang, A.; Jakku, E. Farmers and Their Data: An Examination of Farmers’ Reluctance to Share Their Data through the Lens of the Laws Impacting Smart Farming. NJAS - Wageningen Journal of Life Sciences 2019, 90–91, 100301, doi:https://doi.org/10.1016/j.njas.2019.04.007.

271.     Yoon, C.; Lim, D.; Park, C. Factors Affecting Adoption of Smart Farms: The Case of Korea. Comput Human Behav 2020, 108, 106309, doi:https://doi.org/10.1016/j.chb.2020.106309.

These modifications can be found in the manuscript from lines: 511 to 535, 608 to 670, and 782 to 806.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 3: A more in-depth discussion of the repologies of AI applications is necessary. For example, there is no clear separation between predictive and machine learning methods as machine learning algorithms can also be used as predictive algorithms as well as classification ones; therefore, it should be further specified which predictive algorithms that do not adopt machine learning techniques are used in soilless crop systems. Similarly, computer vision techniques are also used in robotics and cybernetic systems.

Thank you for your insightful comment number 3. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the specific revisions I have implemented in the manuscript.

6.1. Clarifying AI Applications in Soilless Agriculture: Beyond Predictive Analytics

The advent of Artificial Intelligence (AI) and Data Analytics has revolutionized many industries, with agriculture being no exception. Integrating these technologies into soilless crop systems has opened a new frontier for innovation and efficiency. This section delves into the multifaceted role of AI in these systems, distinguishing between predictive algorithms and machine learning techniques and exploring their unique contributions to soilless agriculture. Predictive algorithms have long been employed to forecast various aspects of crop management, from nutrient requirements to yield estimation. These algorithms, which can be as straightforward as linear regression models or as complex as non-linear time-series analyses, serve as the backbone for decision-making processes. They are particularly valuable in soilless crop systems where precision and control are paramount. Machine learning, a dynamic subset of AI, extends beyond predictive capabilities to include classification, clustering, and reinforcement learning. In the controlled environments of soilless agriculture, machine learning algorithms leverage large datasets to uncover patterns and insights imperceptible to the human eye or traditional methods. For instance, neural networks may be utilized to predict plant stress levels, while support vector machines could classify the health of plants based on spectral data. However, it is essential to recognize that not all predictive algorithms in soilless crop systems employ machine-learning techniques. There are a variety of statistical methods and mathematical models that rely on predefined rules and equations, offering a different approach to prediction. These non-ML predictive algorithms are crucial in scenarios where transparency and interpretability are necessary, or data may be too scarce or noisy for complex machine-learning models. Furthermore, the application of computer vision techniques extends into the realms of robotics and cybernetics, which are increasingly becoming intertwined with AI in modern agriculture. In soilless farming, computer vision is not only used for static image analysis but is also integrated into robotic systems for dynamic tasks such as automated harvesting or real-time growth monitoring. As we continue exploring AI's capabilities and applications in soilless crop systems, it is imperative to establish a clear understanding of the various technologies at play. This section aims to clarify by dissecting the roles and responsibilities of different AI applications and setting the stage for future innovations that will further enhance the precision and productivity of soilless agriculture.

These modifications can be found in the manuscript from lines 572 to 601.

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 4: A brief discussion on AI-based DSS used in soilless crop systems must be included in paragraph 6.2 as the AI techniques of decision support systems are very vast and different from each other.

Thank you for your insightful comment number 1. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the specific revisions I have implemented in the manuscript.

Using AI-based decision support systems (DSS) in soilless crop systems offers a transformative approach to optimizing cultivation parameters such as nutrient levels, irrigation timing, and environmental conditions. These systems can analyze large datasets, identify patterns, and make predictive recommendations, enhancing yield and resource efficiency [204–206]. AI has played a pivotal role in transforming agriculture and protecting it from various threats, such as weather, population growth, labor issues, and food security concerns. The numerous applications of AI in agriculture, including tasks like irrigation, weeding, and spraying, are often implemented through sensors in robots and drones. These technologies help conserve water, reduce pesticide and herbicide use, preserve soil fertility, and optimize labor, leading to increased agricultural output and improved quality [207]. In this regard, [208] presented the development and implementation of a smart agriculture IoT system based on deep reinforcement learning (DRL). The system integrates advanced information technologies, including AI and cloud computing, with agricultural production to increase food production while reducing the consumption of resources. The AI model technique used in the cloud layer is DRL, which makes immediate, intelligent decisions, such as determining the water needed for irrigation to enhance crop growth.

In an innovative way, the research by [209] discusses the results of an international competition focused on autonomous greenhouses that combined horticultural expertise with AI to improve fresh food production with fewer resources. Teams applied various AI algorithms, ranging from supervised and unsupervised learning to reinforcement machine learning, to control the greenhouse environment remotely. The use of AI demonstrated the potential to outperform traditional manual growing methods. To fur-ther optimize the operation of AI technologies for agriculture, [210] proposed a novel approach using AI-based soft sensors combined with remote sensing models utilizing deep learning architectures. The study involves preprocessing techniques to clean miss-ing data and remove noise from agricultural land images, with subsequent feature representation and classification processes demonstrating significant improvements in computational efficiency and accuracy in agricultural applications. Building upon these foundations, discussing the diversity of AI-based DSS and their specific applications in soilless crop systems is crucial. AI-based DSS vary significantly in complexity and function, from simple regression models to sophisticated deep learning algorithms capable of strategic planning and real-time adaptive management. For example, while some DSS may employ traditional statistical methods for short-term forecasting, others lever-age complex neural networks for comprehensive analysis and long-term planning. These systems are tailored to the unique needs of soilless operations, considering factors like production scale, crop types, and automation levels. Moreover, integrating AI-based DSS in soilless agriculture goes beyond mere data analysis; it encompasses the entire decision-making process, from data collection and preprocessing to action implementation. This holistic approach ensures that every soilless farming operation is optimized for efficiency and sustainability.

In conclusion, AI-based DSS are indispensable in soilless crop systems, providing a level of analysis and foresight that is unparalleled. These systems not only contribute to more sustainable and productive farming practices but also represent a significant advancement in the field of precision agriculture. Our discussion aims to clearly under-stand the diverse and powerful AI techniques that drive decision-making in soilless agriculture, addressing the specific needs and challenges of this innovative farming approach [211].

References:

204.     Sankaranarayanan, S. Applications of Artificial Intelligence for Smart Agriculture. In AI-Based Services for Smart Cities and Urban Infrastructure; 2021; pp. 277–288.

205.     Panpatte Suraj and Ganeshkumar, C. Artificial Intelligence in Agriculture Sector: Case Study of Blue River Technology. In Proceedings of the Proceedings of the Second International Conference on Information Management and Machine Intelligence; Goyal Dinesh and Gupta, A.K. and P.V. and G.M. and P.M., Ed.; Springer Singapore: Singapore, 2021; pp. 147–153.

206.     Daoliang, L.; Chang, L. Recent Advances and Future Out-look for Artificial Intelligence in Aquaculture. Smart Agri-culture 2020, 2, 1–20, doi:10.12133/j.smartag.2020.2.3.202004-SA007.

207.     Sharma, S.; Verma, K.; Hardaha, P. Implementation of Artificial Intelligence in Agriculture. Journal of Computational and Cognitive Engineering 2022, 2, 155–162, doi:10.47852/bonviewJCCE2202174.

208.     Bu, F.; Wang, X. A Smart Agriculture IoT System Based on Deep Reinforcement Learning. Future Generation Computer Systems 2019, 99, 500–507, doi:10.1016/J.FUTURE.2019.04.041.

209.     Hemming, S.; de Zwart, F.; Elings, A.; Righini, I.; Petropoulou, A. Remote Control of Greenhouse Vegetable Production with Artificial Intelligence—Greenhouse Cli-mate, Irrigation, and Crop Production. Sensors 2019, 19, doi:10.3390/s19081807.

210.     Wongchai, A.; Shukla, S.K.; Ahmed, M.A.; Sakthi, U.; Jagdish, M.; kumar, R. Artificial Intelligence - Enabled Soft Sensor and Internet of Things for Sustainable Agriculture Using Ensemble Deep Learning Architecture. Computers and Electrical Engineering 2022, 102, 108128, doi:10.1016/J.COMPELECENG.2022.108128.

211.     Sachithra, V.; Subhashini, L.D.C.S. How Artificial Intelli-gence Uses to Achieve the Agriculture Sustainability: Sys-tematic Review. Artificial Intelligence in Agriculture 2023, 8, 46–59, doi:10.1016/J.AIIA.2023.04.002.

These modifications can be found in the manuscript from lines:

673 to 718

These changes effectively address your concerns and enhance the overall quality of the paper.

Comment 5: Finally, an in-depth study is needed on the potential limitations and the solutions necessary to address them summarized in Tab. 6.

Thank you for your insightful comment number 5. I value the opportunity to refine my manuscript based on your feedback. Below is my detailed response to your comment and the specific revisions I have implemented in the manuscript.

“To address the limitations and hurdles to widespread adoption of soilless agriculture, several strategic approaches and solutions can be considered, such as providing farmers with the necessary knowledge and training to adopt soilless agriculture techniques effectively through education [341,342]. Providing financial incentives such as grants, subsidies, and tax breaks for farmers and businesses to adopt soilless agricul-ture can help offset initial setup costs and encourage investment in this method, especially for smallholder farmers [343,344]. Developing supportive policies and regulations that recognize and promote soilless agriculture can create an enabling environment for its adoption [345]. This includes zoning regulations, water usage policies, and agricultural subsidies designed to support soilless farming.

The introduction of automation in farming systems, can optimize power consumption. By introducing automated systems and technologies, farmers can reduce energy consumption while maintaining or even increasing yield efficiency [346]. The afore-mentioned, together with the integration of alternative powering, such as renewable energy sources, allows to reduce energy consumption and environmental impact. Re-search has shown that soilless cultivation optimally utilizes water, fertilizer, and land resources, achieving efficiencies of 90%, 70%, and 75%, respectively. Soilless agriculture uses water more efficiently than traditional soil-based farming, as the water and nutrient solutions are recirculated, reducing overall water consumption. By eliminating soil disturbance, it alleviates land pressure and degradation while facilitating year-round crop intensification. This method complements traditional soil-based farming, diminishes the adverse effects of agrochemicals on the environment, addresses climate change, and enhances productivity in arid regions [347]. Educating farmers, agricultural communities, and the general public about these benefits and techniques of soilless agriculture is crucial for its social acceptance [348]. This can be achieved through work-shops, seminars, and educational campaigns. Highlighting the advantages such as higher yields, efficient water usage, and reduced environmental impact can help in in-creasingawareness and understanding.

References:

341.     Knight, J.; Weir, S.; Woldehanna, T. The Role of Education in Facilitating Risk-Taking and Innovation in Agriculture. J Dev Stud 2003, 39, 1–22, doi:10.1080/00220380312331293567.

342.     Takahashi, K.; Muraoka, R.; Otsuka, K. Technology Adop-tion, Impact, and Extension in Developing Countries’ Agri-culture: A Review of the Recent Literature. Agricultural Economics 2020, 51, 31–45, doi:https://doi.org/10.1111/agec.12539.

343.     Giri, S.; Daw, T.M.; Hazra, S.; Troell, M.; Samanta, S.; Basu, O.; Marcinko, C.L.J.; Chanda, A. Economic Incen-tives Drive the Conversion of Agriculture to Aquaculture in the Indian Sundarbans: Livelihood and Environmental Implications of Different Aquaculture Types. Ambio 2022, 51, 1963–1977, doi:10.1007/s13280-022-01720-4.

344.     Goodman, W.; Minner, J. Will the Urban Agricultural Revolution Be Vertical and Soilless? A Case Study of Controlled Environment Agriculture in New York City. Land use policy 2019, 83, 160–173, doi:https://doi.org/10.1016/j.landusepol.2018.12.038.

345.     Lanre Tajudeen, A.; Solomon Taiwo, O. Soilless Farming – A Key Player in the Realisation of “Zero Hunger” of the Sustainable Development Goals in Nigeria. International Journal of Ecological Science and Environmental Engineering 2018, 5, 1–7.

346.     Randolph, O.; Asiabanpour, B. Automation of an Off-Grid Vertical Farming System to Optimize Power Consump-tion. In Proceedings of the Advances in Parallel & Distributed Processing, and Applications; Arabnia, H.R., Deligiannidis, L., Grimaila, M.R., Hodson, D.D., Joe, K., Sekijima, M., Tinetti, F.G., Eds.; Springer International Publishing: Cham, 2021; pp. 1015–1022.

347.     Gebereegziher, W.G. Soilless Culture Technology to Transform Vegetable Farming, Reduce Land Pressure and Degradation in Drylands. Cogent Food Agric 2023, 9, 2265106, doi:10.1080/23311932.2023.2265106.

348.     Muller, A.; Ferré, M.; Engel, S.; Gattinger, A.; Holzkämper, A.; Huber, R.; Müller, M.; Six, J. Can Soil-Less Crop Production Be a Sustainable Option for Soil Con-servation and Future Agriculture? Land use policy 2017, 69, 102–105, doi:https://doi.org/10.1016/j.landusepol.2017.09.014.

These modifications can be found in the manuscript from lines 996 to 1023.

These changes effectively address your concerns and enhance the overall quality of the paper.