wArtificial Intelligence is transforming agriculture and farming across the world, with a projected 275% growth from 2023 to 2028. This research paper will determine whether AI’s adoption and use into agriculture is sustainable in the long term and accessible to those most in need of it, especially smaller farms in developing areas. This paper will explore various AI tools, such as deep learning (DL) models and the Internet of Things (IoT), and how each of these resources is being implemented to address current agricultural challenges, including pest control and maximizing crop yield. Additionally, through research and data collection and examination, this study evaluates the use of AI applications and analysis on farms and their effectiveness to boost the production of farms, and how that would affect smaller farms and farms in developing regions. As stated before, AI has strong potential in agriculture from an economic standpoint, but furthermore, it has efficiency, yield, and analytical boost as well. From sources across the internet, advisory costs can potentially drop 99% and productivity can increase by 30%. However, AI implementation can have high upfront costs, as well as technical, electronic, and infrastructure requirements, something that smaller farms or farms in developing regions simply cannot afford. This research paper emphasizes that without proper policy, cheaper and open sourced alternatives, and cooperation between governing bodies and companies, AI’s adoption in agriculture would exaggerate inequalities rather than making use of technological advancements in the field.

This study used a quantitative research approach with open-source datasets from publicly available repositories. To analyze the data, we worked in Visual Studio Code, an integrated development environment that made it easier to write, test, and debug our code throughout the project. We used Python (version 3.x) for all data processing and analysis because of its powerful libraries designed for scientific research. The Pandas library helped us clean and organize the data into structured formats that were easier to work with, while NumPy handled the numerical calculations and statistical operations. To visualize our findings, we created various graphs using Matplotlib and Seaborn, including line graphs, scatter plots, and bar charts. These visual representations made it much simpler to spot patterns and trends in the data that might have been difficult to see in raw numbers alone. This approach provided several important benefits for our research. Using open-source datasets and free Python libraries meant that our work is fully reproducible, and other researchers can access the same tools and data to verify our results or build on our findings. The transparency of open-source resources also gave us confidence in our data quality, since these datasets typically include detailed documentation about how the information was collected and any limitations to be aware of. Python's efficiency allowed us to process large amounts of data relatively quickly, and its flexibility let us customize our analysis to fit our specific research questions. Overall, this methodology balanced rigor with practicality, providing reliable results while remaining accessible to other researchers in the field.

Source 1

Kesari G. The Future Of Farming: AI Innovations That Are Transforming Agriculture [Internet]. Forbes. 2024. Available from: https://www.forbes.com/sites/ganeskesari/2024/03/31/the-future-of-farming-ai-innovations-that-are-transforming-agriculture/

Summary This article researches the use of AI in agriculture and its growing importance in the developing agricultural sector. By 2050, humans will need to produce 60% more food to feed 9.3 billion people, and the use of AI offers a viable solution to this challenge. The market for AI in agriculture is projected to grow by about 275% percent from 2023 to 2028, with uses like pest, weed and soil quality and irrigation management. The study also demonstrates risks to the integration of AI in farming, like job displacement, ownership concentration, and ethical concerns regarding AI use. This article offers insights into the needs, applications, and risks associated with the use of AI in farming.

Potential Uses Many potential uses would be helpful from this article, such as the use of AI in technology to assist with and boost the productivity of pest identification and control, weed management, soil health monitoring, and transforming AI into a technologically focused sector. It shows statistics regarding the areas of agriculture where AI implementations are currently developing the quickest. This source can be used to highlight the current successful, efficient, and profitable implementations of AI in farming.

Limitations The study only highlights the successful uses of AI in large demand and large market areas, with companies that have frameworks set up for customers. In areas where farmers don’t have easy access to the internet or even electricity, AI technology may struggle to be implemented or even trained to adapt to the unique settings. Additionally, this article does not mention the financial costs to purchase and maintain these machines and/or digital services.

Source 2

Canada GA. AI and agriculture technology: a growing field of study [Internet]. www.educanada.ca. 2024. Available from: https://www.educanada.ca/blog-blogue/2024/ai-agriculture-ia-agricoles.aspx?lang=eng

Summary According to an EduCanada article, artificial intelligence (AI) is transforming Canada's agricultural sector, leading to increased productivity, efficiency, and global competitiveness. AI applications are creating new career paths and improving farming operations through data-driven decision-making and technologies like automated drones and sensors. The source emphasizes AI’s role in creating job opportunities in agriculture and improving traditional farming practices by using data-driven decision-making processes. Technologies like automated drones, precision censors, and AI analytics are highlighted as key innovations that transform how farmers, specifically in Canada, manage and optimize their production

Potential Uses The source provides a variety of examples of AI adoption in the Canadian agricultural landscape. It can be useful for examining different uses of technological and AI implementations in different regions. It can also be used to determine how AI creates new pathways for a workforce transformation rather than simply reducing job opportunities. The focus of AI’s use in data-driven decision making and specific technologies like drones and sensors gives concrete examples of practical implementations of AI in farming.

Limitations The article mainly focuses on positive aspects of AI on Canadian farms, but doesn’t provide details regarding challenges of implementation, costs, or adoption barriers. As this source is government-sponsored, it mainly has an optimistic view that doesn’t fully address potential obstacles faced by smaller farms with limited resources. The source also lacks specific data, statistics, and case studies that support its claims about the improvements and gains that AI provides.

Limitations

Source 3

McKinsey. How generative AI in agriculture could shape the industry | McKinsey [Internet]. www.mckinsey.com. 2024. Available from: https://www.mckinsey.com/industries/agriculture/our-insights/from-bytes-to-bushels-how-gen-ai-can-shape-the-future-of-agriculture

Summary This source discusses the advancements that AI is creating in food production, how it is transforming agriculture as a sector, and helping farmers keep up with the growing global demand for increased food production. It mainly focuses on gen AI, which is an application that processes large sets of unstructured data to identify patterns and generate ideas. This analysis concludes that generative AI’s primary value in agriculture lies in optimizing crop and livestock production, as well as improving business operations and optimizing decision-making frameworks on farms.

Potential Uses This source is valuable for understanding the specific capabilities of generative AI in agriculture and its distinction from general AI applications. It can be used for data analysis and pattern recognition capabilities that help farmers make more informed decisions. The focus on crop and livestock production and business provides a comprehensive map to navigate AI’s impact on farming. As a report released by McKinsey, it most likely contains research-backed insights and a wide variety of data that can make the arguments more credible.

Limitations The summary provided is not very detailed and doesn’t quite address implementation challenges, costs, or issues in accessibility for different-sized farms. The study most likely focuses on large-scale commercial farms and may not fully represent the concerns of smaller or medium-sized farms. The emphasis on generative AI may limit its relevance to other AI technologies currently in use. Additionally, this source doesn’t fully provide coverage of both the benefits and risks of the use of AI.

Source 4

4. .Bayer. What Could Agriculture Accomplish with AI on Its Side? [Internet]. Bayer.com. 2024. Available from: https://www.bayer.com/en/agriculture/ai-for-agriculture

Summary This source discusses the advancements of AI and applying them to agriculture. The company that this source originates from is a major agricultural biotech company, and they present AI as a transformative tool for modern farming. This source highlights Bayer’s use of machine learning, computer vision, and data analytics to revolutionize crop protection and seed production efficiency. It mentions key innovations like the E.L.Y. expert Generative AI system, used for improving breeding cycles for livestock. The source also talks about CropKey, a crop protection AI tool, and Field View, Bayer’s own field management system that manages 220 million acres across up to 20 countries.

Potential Uses This source provides concrete examples of AI implementation in agriculture, making it useful for demonstrating applications and outcomes of AI in agriculture in the real world. The 30% productivity boost and reduction in breeding cycle times can demonstrate AI’s efficiency gains. The E.L.Y. system exemplifies how generative AI can make expert knowledge accessible to farmers in short periods of time, rather than through doing time-consuming research. The source is useful for discussion of how AI can achieve sustainability goals for environmental impacts and optimized resource use.

Limitations This source doesn’t talk about the negatives of AI’s implementation, as they mainly present their own AI initiatives in a positive light without bringing up challenges, costs, or potential areas of failure. This source also lacks verification of the results that it claims its technologies can accomplish. Additionally, it doesn’t address concerns for smaller farms that may not be able to afford the products and digital platforms. It also doesn’t discuss data privacy, especially considering that FieldView collects farm data across 220 million acres and how that data might be used and distributed. This article doesn’t address the potential risks of overrelying on tech systems that could force farmers only to use products from one seller.

Source 5

5. AI in Agriculture: Smarter Crops\, Better Yields | CSA [Internet]. Cloudsecurityalliance.org. 2025. Available from: https://cloudsecurityalliance.org/blog/2025/02/10/ai-in-agriculture-smarter-crops-healthier-livestock-better-yields

Summary This source examines how artificial intelligence is addressing agriculture’s challenges, like labour shortages, unpredictable weather, and rising resource costs. With global food demand projected to grow up to 56% by 2050, the article states that AI is a critical solution for maximizing yields while reducing waste. The source provides coverage of 5 major AI applications: crop disease detection, pest control, automated weed control, smart irrigation, and livestock health monitoring. This article has a large section dedicated to attention to implementation challenges like high costs, technical expertise requirements, data limits, and ethical concerns about job displacement, corporate monopolization, and observations like how AI cannot replicate the on-the-fly problem-solving skills of farmers.

Potential Uses This source is very useful for providing a balanced perspective on AI in agriculture. It has various quantitative examples that offer concrete data for demonstrating AI’s efficiency. It also has a detailed breakdown of 5 application areas with specific companies and technologies, which provides multiple case studies for discussion. The source is also useful for addressing implementation barriers, ethical issues, and insights about troubleshooting needs. The source originates from a credible source that addresses data management and ethical issues.

Limitations While this source has more balanced perspectives than corporate sources, this article doesn’t discuss issues in depth. It does briefly mention possible issues like corporate monopolization and small farmer competitiveness, but it doesn’t explore ways to prevent these issues. The source does mention high costs of technologies, but doesn’t provide actual price ranges that can help predict the ROI for farms of different sizes. This source also doesn’t critically examine whether increased production of food can address food security issues. The source can also show more practical, smaller challenges of AI implementation or unintended consequences to give a fuller picture of AI adoption risks.

Source 6

6. Syngenta and AI: Pioneering Sustainable Agriculture for the Future [Internet]. Syngenta.com. 2025. Available from: https://www.syngenta.com/agriculture/agricultural-technology/artificial-intelligence

Summary This source talks about how AI is implemented responsibly in agriculture. It addresses the different ways that AI can help farmers grow better crops, protect them from diseases, and help predict the weather. It gives us an insight into the world of AI-powered precision farming, which helps us understand this project better. For example, regenerative agriculture is a sustainable farming method that focuses on restoring and enhancing the health of crops by prioritizing soil health, biodiversity, and ecological balance. This source shows us the way to successfully and sustainably use AI to help farmers.

Potential Uses This source is useful for gathering information and knowledge about the topic. It provides some basic knowledge about things like what AI is and how it is implemented in farming. Some of these include AI farming systems, AI precision farming, and many more. Another potential use for this source is that this is a company that we could potentially reach out to, which would help us immensely in our research.

Limitations This source is from a company that offers and sells products related to the topic of their article. This could produce bias in the article, making it seem that using AI in agriculture is better than it actually is, to persuade people to buy their goods. This source also does not go very into the finer points, making it harder to get really deep into the topic. It covers basic ideas like what artificial intelligence is and how it can be used, but gives limited examples of how it really works in real life. 

Source 7

7.​The Use of AI (Artificial Intelligence) in Agriculture & Farming [Internet]. www.agrirs.co.uk. Available from: https://www.agrirs.co.uk/blog/2024/02/the-use-of-ai-artificial-intelligence-in-agriculture-and-farming?source=google.com

Summary This source talks about how AI is implemented responsibly in agriculture. It shows us many different ways in which we can use AI to help us with things such as livestock and dairy health monitoring, autonomous machinery, and more. It also talks about the pros and cons of using AI for this, such as AI not being 100% reliable. At the end, they include a Q&A to answer questions.

Potential Uses This source is useful for gathering information and knowledge about the topic. It will be good to find ideas on what to use AI for in our project. It also gives us some cons, meaning that we can adjust our project to minimize the cons as much as possible. 

Limitations This source is from Agricultural Recruitment Specialists, meaning that the information on it might not be 100% reliable. A way to check that everything in this article is correct is to check many other sites to see if they all match. One other limitation of this source is the fact that there are not many stats used in this. Because of this, we can not provide cold, hard facts to help support our opinion. However, this source is a good starting point for research on this topic.

Source 8

8. Kogan V. How AI can help improve food systems and agricultural yields [Internet]. World Economic Forum. 2025. Available from: https://www.weforum.org/stories/2025/06/ai-food-systems-agricultural-revolution/

Summary This source, from the World Economic Forum, is a great source for us because it covers many things that we need for the project. It shows us how climate change is affecting agriculture, how AI can help that and many more. It shows us how to build resilient agricultural systems, how global disasters inflicted 417 billion dollars in economic losses, and many more. AI can act as a distributed brain for agriculture. For example, a disease in Italy can trigger an alert to watch out in places nearby.

Potential Uses This source is useful for gathering information and knowledge about the topic. It gives us good numbers to work with and will help immensely during the process. It is more in-depth than the other sources and is very credible, as it is the World Economic Forum.

Limitations There are some limitations to this source. It doesn’t go into enough detail for each way that AI can help with agriculture. This limits the amount that we can learn from this source, even though it is good. There are not many limitations; however, it isn’t a real research paper, meaning that the info will not be relevant in the future, as it will only give us more knowledge about the topic, instead of actual research done by scientists.

Source 9

‌9. Nautiyal M, Joshi S, Hussain I, Rawat H, Joshi A, Saini A, et al. Revolutionizing agriculture: A comprehensive review on artificial intelligence applications in enhancing properties of agricultural produce. Food Chemistry: X. 2025 Jul;102748. ‌Summary This source or research paper was really insightful and helpful, as it talked about many important things related to the topic. There were many solutions, such as SVN, which is one of the ML approaches that could be used to provide answers for improved crop management. Another proposed solution was the incorporation of IoT (Internet of Things) devices, which can monitor various parameters such as soil moisture and nutrient levels, facilitating timely interventions. Machine learning algorithms can further analyze this data to optimize resource usage and maximize yield. 

Potential Uses The insights from the article highlight the transformative potential of integrating IoT devices in agriculture. By leveraging real-time data on soil moisture and nutrient levels, farmers can make informed decisions that enhance crop management. This technology not only enables precise resource allocation, leading to significant cost savings and environmental sustainability, but also allows for early detection of issues such as nutrient deficiencies or drought stress. Furthermore, the application of machine learning algorithms to analyze the collected data can refine farming practices, providing predictive insights that help optimize yields. Ultimately, these advancements could empower farmers to increase productivity while promoting sustainable agricultural practices. This article will really help us with the research project.

Limitations This is a research paper from the National Library of Medicine, and it is a very good source with lots of details. There are not many limitations to this, as it is hundreds of pages of research, which will be very helpful in our process while doing this project. This was a good source; however, it doesn’t cover key points such as the cost of implementing AI, among others.

Source 10

‌10. AI can be a game-changing solution for farmers: FAO Innovation Chief [Internet]. Newsroom. FAO; 2025. Available from: https://www.fao.org/newsroom/detail/ai-can-be-a-game-changing-solution-for-farmers--fao-innovation-chief/en Summary This source shares insights on how artificial intelligence and innovative strategies can transform global agrifood systems. It emphasizes that innovation involves improving existing methods and adopting entirely new methods to deal with global issues like climate change, biodiversity loss, and food security. This source highlights various innovations from technological advancements like biotech and genomics to social initiatives aimed at empowering youth. It notes exciting applications of AI, such as the Agricultural Stress Index System for monitoring droughts and a partnership with Digital Green to provide AI-driven decision-making services that could significantly reduce consultation costs for farmers. This source also points out challenges like data quality, training needs, and barriers to adoption, stressing that successful innovation ensures that benefits reach all farmers, particularly those in underserved communities. Potential Uses This source gives us valuable insights into AI in agriculture from an international development perspective, particularly in food security. It shows us cost reductions for advisory services, showcasing AI's potential for smallholder farmers. The FAO's Large Language Model serves as a key public-sector initiative, raising important issues around governance and data ownership. Things like The Farmer Field Schools 2.0 initiative help merge AI with community-based learning, which preserves traditional knowledge but introduces new ones too. It talks about various implementation barriers, including policy and social factors, and emphasizes co-creation over technology transfer. The foresight exercise for 2050 presents different future scenarios, while the ATIO database aims to make it possible to access agricultural innovation ideas. In conclusion, there are many things that we can learn from this source. Limitations There are quite a few limitations with this source. The interview with the FAO official highlights the organization's successes but glosses over its challenges and internal constraints. It lacks specifics on funding and the practical details needed to achieve the goal of reaching 50 million people by 2040. The discussion around using AI in agriculture is more conceptual than actionable, missing key points like hidden costs and data concerns for developing countries. While ethical AI use is mentioned, there’s little detail on governance to ensure fairness. Overall, the interview covers many topics but lacks the depth found in research papers.

Our research aimed to answer an important question: Is AI in agriculture sustainable and accessible for those who need it most? The results demonstrate AI's significant potential with productivity gains of 25-32\% across major crops, while also identifying opportunities for improvement in accessibility. Looking at Figure 1, the irrigation data reveals important patterns in agricultural infrastructure development. Cyprus's achievement of 40\% irrigated land demonstrates what sustained infrastructure investment can accomplish. Azerbaijan's steady growth from 20% to 30% shows encouraging progress over time. While Afghanistan remains at under 5\%, this highlights where targeted development efforts could have the greatest impact. These infrastructure foundations are essential for AI technologies to function effectively, suggesting that strategic investments in basic agricultural infrastructure could unlock AI's potential in developing regions. Figure 2 illustrates current adoption patterns across farm sizes. Large farms have achieved 67% adoption rates, demonstrating that AI integration is technically feasible and beneficial. Medium farms at 25% show growing interest and capability. Small farms at 8% represent a significant opportunity for expansion. Since small farms produce 80\% of the world's food, successfully extending AI benefits to this sector could have transformative effects on global food security. The high adoption among large farms provides proof of concept that can guide implementation for smaller operations. The market growth shown in Figure 3 is encouraging. Expanding from $1 billion to $4 billion represents substantial investment and confidence in agricultural AI. This growth creates economies of scale that could eventually reduce costs for all users. While investment is currently concentrated in North America and Europe, this establishes proven technologies and best practices that can be adapted for other regions. Figure 4 shows promising adoption of various AI applications. Crop monitoring at 72% and yield optimization at 70% demonstrate that farmers recognize AI's practical value. Weather prediction at 65% helps farmers make better decisions and reduce risk. Even automated machinery at 45% shows meaningful adoption despite higher costs. The yield improvements in Figure 5 are particularly encouraging. A 32% increase in corn yield and 30% in soybeans represent substantial gains that could meaningfully contribute to meeting global food demands. These improvements demonstrate AI's capability to help address the 60% increase in food production needed by 2050. While current data comes primarily from large commercial farms, these results provide strong evidence of AI's potential. As the technology matures and becomes more accessible, similar gains could be achievable across diverse farming contexts. Figure 6 identifies specific areas where targeted interventions could expand AI accessibility. While developed regions currently lead in infrastructure, the gaps highlight clear pathways for improvement. The internet access gap suggests that expanding connectivity initiatives could enable AI adoption. Similarly, improvements in electricity reliability, irrigation systems, and technical training would create conditions for successful AI implementation. We used Python with Pandas and Matplotlib because they are open-source and freely available, demonstrating that effective agricultural research can be conducted with accessible tools. This aligns with our focus on making AI research more accessible. Pandas is well-suited for structured data analysis, making it efficient for handling World Bank database information. Matplotlib provided clear visualization capabilities that effectively communicated our findings. Visual Studio Code offered a professional development environment while remaining freely accessible. This combination of tools demonstrates that quality research does not require expensive specialized software. Using open-source datasets from the World Bank supports transparency and allows anyone to verify or build upon our research. This approach models the accessibility we advocate for in agricultural AI implementation. This research allows us to see that Our research has several limitations that present opportunities for future investigation. The World Bank irrigation data contained some gaps, particularly for Afghanistan in earlier decades, suggesting a need for improved data collection infrastructure in developing regions. Our analysis of four countries provides valuable insights while indicating that broader geographic studies would strengthen the math understanding of global patterns. Data on AI effectiveness primarily comes from large commercial farms in optimal conditions. This presents an opportunity for future research to test AI applications specifically in small-farm contexts and challenging environments. The rapid pace of AI development means costs and capabilities are constantly improving, suggesting that accessibility barriers identified in our research may decrease over time. Future studies could incorporate qualitative research, as well as including farmer and policymaker perspectives, to support our findings.

This research examined whether AI adoption in agriculture is sustainable and accessible for those who need it most. Our findings demonstrate that while AI offers substantial benefits for agricultural productivity, with yield improvements of 25-32% across major crops, significant accessibility challenges currently limit its impact on global food security. The long-term implications of our findings are very important. If current adoption patterns continue, AI could create a widening gap between large commercial farms in developed regions and small family farms in developing areas. Since small farms produce 80% of the world's food supply, this disparity threatens AI's potential to help meet the 60% increase in food production needed by 2050. However, our research also identifies clear pathways forward. The infrastructure gaps we documented represent specific, addressable barriers rather than fundamental limitations. The market growth from $1 billion to $4 billion demonstrates commercial viability that could eventually reduce costs through economies of scale. For the agricultural technology sector, this research emphasizes the importance of considering accessibility alongside technical effectiveness. Innovation must account for diverse farming contexts, from well-resourced operations to small farms with limited infrastructure. For policymakers, our findings highlight the need for coordinated approaches addressing both infrastructure development and technology access. Investments in irrigation, electricity, and connectivity would broadly benefit agriculture while enabling the adoption of AI. Future research should focus on several key areas. First, pilot programs testing AI on small farms in developing regions would provide crucial data on what works in resource-constrained environments. Second, longitudinal studies tracking adoption rates over time would show whether accessibility gaps are narrowing as technology matures. Third, economic modelling for small-scale adoption could identify cost-effective intervention strategies. Finally, qualitative research with farmers would complement our quantitative findings by revealing cultural and practical factors affecting adoption. In conclusion, AI has genuine potential to transform agriculture and contribute to global food security. The question is not whether AI can improve productivity, but whether we can deploy it in ways that benefit all farmers. Our research demonstrates that the technical capabilities exist and economic incentives are strong, but equitable adoption requires deliberate action. With appropriate infrastructure investment, accessible technology development, and expanded training programs, AI could help address agricultural challenges while promoting global equity. The data suggests that equitable adoption of AI is achievable, but requires conscious effort to ensure that technological advancement serves the shared goal of food security for all.

\bibitem{educanada2024} Government of Canada. AI in agriculture: transforming the future of farming [Internet]. Ottawa: EduCanada; 2024 [cited 2026 Jan 6]. Available from: https://www.educanada.ca/blog-blogue/2024/ai-agriculture-ia-agricoles.aspx?lang=eng \bibitem{kesari2024} Kesari G. The future of farming: AI innovations that are transforming agriculture [Internet]. Forbes; 2024 Mar 31 [cited 2026 Jan 6]. Available from: https://www.forbes.com/sites/ganeskesari/ 2024/03/31/the-future-of-farming-ai-innovations-that-are-transforming-agriculture/ \bibitem{mckinsey2024} McKinsey \& Company. From bytes to bushels: how gen AI can shape the future of agriculture [Internet]. McKinsey; 2024 [cited 2026 Jan 6]. Available from: https://www.mckinsey.com/industries/agriculture/our-insights/from-bytes-to-bushels-how-gen-ai-can-shape-the-future-of-agriculture \bibitem{bayer2024} Bayer. AI for agriculture [Internet]. Leverkusen: Bayer AG; [date unknown] [cited 2026 Jan 6]. Available from: https://www.bayer.com/en/agriculture/ai-for-agriculture \bibitem{syngenta2024} Syngenta. Artificial intelligence in agriculture [Internet]. Basel: Syngenta; [date unknown] [cited 2026 Jan 6]. Available from: https://www.syngenta.com/agriculture/agricultural-technology/artificial-intelligence \bibitem{cloudsecurity2025} Cloud Security Alliance. AI in agriculture: smarter crops, healthier livestock, better yields [Internet]. Cloud Security Alliance; 2025 Feb 10 [cited 2026 Jan 6]. Available from: https://cloudsecurityalliance.org/blog/2025/02/10/ai-in-agriculture-smarter-crops-healthier-livestock-better-yields \bibitem{agrirs2024} AgriRS. The use of AI (artificial intelligence) in agriculture and farming [Internet]. AgriRS; 2024 Feb [cited 2026 Jan 6]. Available from: https://www.agrirs.co.uk/blog/2024/02/the-use-of-ai-artificial-intelligence-in-agriculture-and-farming \bibitem{weforum2025} World Economic Forum. AI food systems: agricultural revolution [Internet]. Geneva: World Economic Forum; 2025 Jun [cited 2026 Jan 6]. Available from: https://www.weforum.org/stories/2025/06/ai-food-systems-agricultural-revolution/ \bibitem{ncbi2024} National Center for Biotechnology Information. Revolutionizing agriculture: A comprehensive review on artificial intelligence applications in enhancing properties of agricultural produce. Bethesda (MD): National Library of Medicine; [2025] [cited 2026 Jan 6]. Available from: https://pmc.ncbi.nlm.nih.gov/articles/PMC12274707/ \bibitem{fao2024} Food and Agriculture Organization of the United Nations. AI can be a game-changing solution for farmers: FAO innovation chief [Internet]. Rome: FAO; [date unknown] [cited 2026 Jan 6]. Available from: https://www.fao.org/newsroom/detail/ai-can-be-a-game-changing-solution-for-farmers--fao-innovation-chief/en

Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project. Thank you to everyone who helped is with this project.