Large language models for agricultural and rural development: An application of foundational models in extension

Paul A. Hill; Lendel K. Narine

doi:10.37433/aad.v7i2.603

Authors

Paul A. Hill Utah State University Extension, USA https://orcid.org/0009-0007-2119-4739
Lendel K. Narine Utah State University Extension, USA https://orcid.org/0000-0001-6962-2770

DOI:

https://doi.org/10.37433/aad.v7i2.603

Keywords:

agricultural extension, AI foundational models, ChatGPT, rural development, SDG 2: Zero Hunger

Abstract

This study investigates the applicability, practicality, and effectiveness of a low-cost AI foundational model (FM) in agricultural extension through the development, fine-tuning, and evaluation of a custom GPT named Utah PeachBot, built using OpenAI’s GPT platform. The research focused on facilitating real-time, evidence-based advisory service support for Extension agents assisting small-scale peach producers in Utah. Methods involved training the GPT with curated, research-based horticultural resources and assessing model outputs through an expert panel of six Extension agents. Results showed high reliability and accuracy for general inquiries about peach cultivation. However, inconsistencies in regional specificity and the practicality of recommendations emerged as limitations. Feedback indicated a need for iterative fine-tuning of the model through continuous expert feedback and integration of local, context-specific data. Recommendations include a phased approach to implementing customized GPTs in agricultural advisory services to improve information dissemination, decision-making quality, and operational efficiency within extension systems.

Downloads

Download data is not yet available.

References

Antwi-Agyei, P., & Stringer, L. C. (2021). Improving the effectiveness of agricultural Extension services in supporting farmers to adapt to climate change: Insights from northeastern Ghana. Climate Risk Management, 32, 100304. https://doi.org/10.1016/j.crm.2021.100304 DOI: https://doi.org/10.1016/j.crm.2021.100304

Banh, L., & Strobel, G. (2023). Generative artificial intelligence. Electronic Markets, 33, Article 63(2023). https://doi.org/10.1007/s12525-023-00680-1 DOI: https://doi.org/10.1007/s12525-023-00680-1

Birss, D. (2023, March 15). How to research and write using generative AI tools [Online course]. LinkedIn Learning. https://www.linkedin.com/learning/how-to-research-and-write-using-generative-ai-tools

Davis, K., Burton, S., Amudavi, D., Mekonnen, D. A., Flohrs, A., Riese, J., Lamb, C., & Zerfu, E. (2010). In-depth assessment of the public agricultural Extension system of Ethiopia and recommendations for improvement. International Food Policy Research Institute. https://ebrary.ifpri.org/digital/collection/p15738coll2/id/7610/

Dhillon, R., & Moncur, Q. (2023). Small-scale farming: A review of challenges and potential opportunities offered by technological advancements. Sustainability, 15(21), 15478. https://doi.org/10.3390/su152115478 DOI: https://doi.org/10.3390/su152115478

Elbasi, E., Mostafa, N., Zaki, C., AlArnaout, Z., Topcu, A. E., & Saker, L. (2024). Optimizing agricultural data analysis techniques through AI-powered decision-making processes. Applied Sciences, 14(17), Article 8018. https://doi.org/10.3390/app14178018 DOI: https://doi.org/10.3390/app14178018

Food and Agricultural Organization. (2017). Information and communication technology (ICT) in Agriculture. https://www.fao.org/family-farming/detail/en/c/1200067/

Ganpat, W. G., Narine, L. K., & Harder, A. (2017). The impact of farm visits on farmers’ satisfaction with extension: Examining the dependence on individual methods in the Caribbean. Journal of International Agricultural and Extension Education, 24(3), 20–35. https://doi.org/10.5191/jiaee.2017.24303 DOI: https://doi.org/10.5191/jiaee.2017.24303

Hauer, T. (2022). Importance and limitations of AI ethics in contemporary society. Humanities and Social Sciences Communications, 9, Article 272. https://doi.org/10.1057/s41599-022-01300-7 DOI: https://doi.org/10.1057/s41599-022-01300-7

Ibrahim, A., Senthilkumar, K., & Saito, K. (2024). Evaluating responses by ChatGPT to farmers’ questions on irrigated lowland rice cultivation in Nigeria. Scientific Reports, 14(1), 3407. https://doi.org/10.1038/s41598-024-53916-1 DOI: https://doi.org/10.1038/s41598-024-53916-1

Kassem, H. S., Alotaibi, B. A., Muddassir, M., & Herab, A. (2021). Factors influencing farmers' satisfaction with the quality of agricultural extension services. Evaluation and Program Planning, 85, 101912. https://doi.org/10.1016/j.evalprogplan.2021.101912 DOI: https://doi.org/10.1016/j.evalprogplan.2021.101912

Khan, R. P., Gupta, S., Daum, T., Birner, R., & Ringler, C. (2025). Leveling the field: A review of the ICT revolution and agricultural Extension in the Global South. Journal of International Development, 37(1), 1–21. https://doi.org/10.1002/jid.3949 DOI: https://doi.org/10.1002/jid.3949

Koutsouris, A. (2018). Role of extension in agricultural technology transfer: A critical review. In N. Kalaitzandonakes, E. Carayannis, E. Grigoroudis, & S. Rozakis (Eds.), From agriscience to agribusiness (pp. 337–359). Springer. https://doi.org/10.1007/978-3-319-67958-7_16 DOI: https://doi.org/10.1007/978-3-319-67958-7_16

Langyintuo, A. (2020). Smallholder farmers’ access to inputs and finance in Africa. In S. Gomez y Paloma, L. Riesgo, & K. Louhichi (Eds.), The role of smallholder farms in food and nutrition security (pp. 133-152). Springer. https://doi.org/10.1007/978-3-030-42148-9_7 DOI: https://doi.org/10.1007/978-3-030-42148-9_7

Law, L. (2024). Application of generative artificial intelligence (GenAI) in language teaching and learning: A scoping literature review. Computers and Education Open, 6, 100174. https://doi.org/10.1016/j.caeo.2024.100174 DOI: https://doi.org/10.1016/j.caeo.2024.100174

Li, J., Xu, M., Xiang, L., Chen, D., Zhuang, W., Yin, X., & Li, Z. (2024). Foundation models in smart agriculture: Basics, opportunities, and challenges. Computers and Electronics in Agriculture, 222, 109032. https://doi.org/10.1016/j.compag.2024.109032 DOI: https://doi.org/10.1016/j.compag.2024.109032

Lindblom, J., Lundström, C., Ljung, M., & Jonsson, A. (2017). Promoting sustainable intensification in precision agriculture: Review of decision support systems development and strategies. Precision Agriculture, 18, 309–331. https://doi.org/10.1007/s11119-016-9491-4 DOI: https://doi.org/10.1007/s11119-016-9491-4

Maake, M. M. S., & Antwi, M. A. (2022). Farmers’ perceptions of effectiveness of public agricultural Extension services in South Africa: An exploratory analysis of associated factors. Agriculture & Food Security, 11, Article 34. https://doi.org/10.1186/s40066-022-00372-7 DOI: https://doi.org/10.1186/s40066-022-00372-7

Mapiye, O., & Dzama, K. (2024). Strengthening research-Extension-farmer-input linkage system for sustainable smallholder livestock farming in Africa: Progress and prospects. Tropical Animal Health and Production, 56, Article 363. https://doi.org/10.1007/s11250-024-04210-9 DOI: https://doi.org/10.1007/s11250-024-04210-9

Mehrabi, Z., McDowell, M. J., Ricciardi, V., Levers, C., Martinez, J. D., Mehrabi, N., Wittman, H., Ramankutty, N., & Jarvis, A. (2021). The global divide in data-driven farming. Nature Sustainability, 4, 154–160. https://doi.org/10.1038/s41893-020-00631-0 DOI: https://doi.org/10.1038/s41893-020-00631-0

Moor, M., Banerjee, O., Abad, Z. S. H., Kromholz, H., Leskovec, J., Topol, E., & Rajpurkar, P. (2023). Foundation models for generalist medical artificial intelligence. Nature, 616, 259–265. https://doi.org/10.1038/s41586-023-05881-4 DOI: https://doi.org/10.1038/s41586-023-05881-4

Nachibi, S. U., Arimiyaw, A. W., Ganee, E. M., & Morgan, A. K. (2024). Dissemination of climate-smart agriculture practices in the Upper West Region of Ghana: Insights from local stakeholders and institutions. International Journal of Agricultural Sustainability, 22(1), 2421069. https://doi.org/10.1080/14735903.2024.2421069 DOI: https://doi.org/10.1080/14735903.2024.2421069

OpenAI. (2023a, November 6). Introducing GPTs. https://openai.com/index/introducing-gpts/

OpenAI. (2023b, November). Creating a GPT. https://help.openai.com/en/articles/8554397-creating-a-gpt

OpenAI. (2024). Fine-tuning GPT-4o models. https://platform.openai.com/docs/guides/fine-tuning

Peng, B., Li, C., He, P., Galley, M., & Gao, J. (2023). Instruction tuning with GPT-4. arXiv preprint. https://arxiv.org/abs/2304.03277.

Saravanan, R. (Ed.). (2010). ICTs for agricultural Extension: Global experiments, innovations and experiences. New Indian Publishing Agency. https://doi.org/10.59317/9789389992816 DOI: https://doi.org/10.59317/9789389992816

Schmidgall, S., Achterberg, J., Miconi, T., Kirsch, L., Ziaei, R., Hajiseyedrazi, S. P., & Eshraghian, J. (2023). Brain-inspired learning in artificial neural networks: A review. arXiv preprint. https://arxiv.org/abs/2305.11252. DOI: https://doi.org/10.1063/5.0186054

Shaikh, T. A., Rasool, T., Veningston, K., & Yaseen, S. M. (2024). The role of large language models in agriculture: Harvesting the future with LLM intelligence. Progress in Artificial Intelligence, 14, 117-164. https://doi.org/10.1007/s13748-024-00359-4 DOI: https://doi.org/10.1007/s13748-024-00359-4

Smith, J. A., & Patel, R. (2023). Data-driven decision making in agriculture: Enhancing productivity and sustainability through predictive analytics. Journal of Agricultural Informatics, 14(3), 45-62. https://doi.org/10.17700/jai.2023.14.3.384

Somanje, A. N., Mohan, G., & Saito, O. (2021). Evaluating farmers’ perception toward the effectiveness of agricultural Extension services in Ghana and Zambia. Agriculture & Food Security, 10(1), Article 53. https://doi.org/10.1186/s40066-021-00325-6 DOI: https://doi.org/10.1186/s40066-021-00325-6

Suvedi, M., & Sasidhar, P. V. K. (2024). Essential competencies for Extension educators. Michigan State University. https://www.canr.msu.edu/csus/uploads/Essential%20Competencies_Full%20Book.pdf

Swanson, B. E., & Rajalahti, R. (2010). Strengthening agricultural Extension and advisory systems: procedures for assessing, transforming, and evaluating Extension systems. Agriculture and Rural Development (Working Paper No. 45). World Bank. http://documents.worldbank.org/curated/en/873411468159312382 DOI: https://doi.org/10.1596/23993

Tzachor, A., Devare, M., Richards, C., Pypers, P., Ghosh, A., Koo, J., Johal, S., & King, B. (2023). Large language models and agricultural extension services. Nature Food, 4(11), 941-948. https://doi.org/10.1038/s43016-023-00867-x DOI: https://doi.org/10.1038/s43016-023-00867-x

Wiles, O., Gowal, S., Stimberg, F., Rebuffi, S. A., Ktena, I., Dvijotham, K. D., & Cemgil, A. T. (2022). A fine-grained analysis on distribution shift. International Conference on Learning Representations. https://openreview.net/forum?id=Dl4LetuLdyK

World Bank. (2012). Agricultural innovation systems: An investment sourcebook. World Bank Group. https://documents1.worldbank.org/curated/es/140741468336047588/pdf/672070PUB0EPI0067844B09780821386842.pdf

World Bank. (2017). ICT in agriculture: Connecting smallholders to knowledge, networks, and institutions (Updated edition). World Bank Group. https://documents1.worldbank.org/curated/pt/522141499680975973/pdf/117319-PUB-Date-6-27-2017-PUBLIC.pdf

Xu, Z., Adeyemi, A. E., Catalan, E., Ma, S., Kogut, A., & Guzman, C. (2023). A scoping review on technology applications in agricultural Extension. PLOS ONE, 18(11), e0292877. https://doi.org/10.1371/journal.pone.0292877 DOI: https://doi.org/10.1371/journal.pone.0292877