Enhancing transparency and trust in agricultural decision-making through explainable artificial intelligence

Milos Ilić; Aleksandra Stojnev Ilić; Milan Grujev; Srecko Stamenković; Bojan Vasović

doi:10.71159/icemit2567I

Authors

Milos Ilić Toplica Academy of Applied Studies, Department of Business Studies Blace, Serbia
Aleksandra Stojnev Ilić University of Nis, Faculty of Electronic engineering, Serbia
Milan Grujev University of Nis, Faculty of Electronic engineering, Serbia; Institute for Artificial Intelligence Research and Development of Serbia, Novi Sad, Serbia
Srecko Stamenković Toplica Academy of Applied Studies, Department of Business Studies Blace, Serbia
Bojan Vasović Toplica Academy of Applied Studies, Department of Business Studies Blace, Serbia

DOI:

https://doi.org/10.71159/icemit2567I

Keywords:

Precision agriculture, feature attribution (SHAP, LIME), trust in AI

Abstract

The integration of artificial intelligence in agriculture has significantly advanced data-driven decision-making across the sector. However, the "black box" nature of many AI models poses challenges in transparency, trust, and adoption, particularly among stakeholders with limited technical expertise. Explainable AI (XAI) addresses this limitation by making model predictions interpretable and understandable. This paper explores the application of XAI across seven critical agricultural domains: crop yield prediction, pest and disease detection, precision agriculture, soil health analysis, weather risk management, plant breeding and genomics, and market forecasting. For each application, we examine how XAI techniques—such as feature attribution, saliency maps, and rule-based explanations—can enhance interpretability, improve user confidence, and support actionable insights. Through case studies and model analyses, we demonstrate that incorporating explainability not only improves transparency but also leads to better-informed decisions, increased efficiency, and more sustainable farming practices. The findings highlight the transformative potential of XAI as a bridge between complex algorithms and practical agricultural use, promoting responsible and inclusive AI deployment in the agri-food sector.

References

Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J.M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023). Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence. Information Fusion, 99, 101805. https://doi.org/10.1016/j.inffus.2023.101805

Antoniadi, A. M., Du, Y., Guendouz, Y., Wei, L., Mazo, C., Becker, B. A., & Mooney, C. (2021). Current challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systematic review. Applied Sciences, 11(11), 5088. https://doi.org/10.3390/app11115088

Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., & Yang, GZ. (2019). XAI-Explainable artificial intelligence. Science Robotics, 4(37) eaay7120. doi:10.1126/scirobotics.aay7120. PMID: 33137719

Hsieh, W., Bi, Z., Jiang, C., Liu, J., Peng, B., Zhang, S., Pan, X., Xu, J., Wang, J., Chen, K., Feng, P., Wen, Y., Song, X., Wang, T., Liu, M., Yang, J., Li, M., Jing, B., Ren, J., Song, J., Tseng, H., Zhang, Y., Yan, L.K.Q., Niu, Q., Chen, S., Wang, Y., Liang, C.X. (2024). A comprehensive guide to explainable AI: from classical models to LLMs. https://doi.org/10.48550/arXiv.2412.00800

Kumar, S., & Kumar, M. (2024). Enhancing agricultural decision-making through an explainable AI-based crop recommendation system. In International Conference on Signal Processing and Advance Research in Computing (SPARC) (pp. 540–546). Amity School of Engineering and Technology, Amity University, Lucknow Campus, U.P., India. https://doi.org/10.1109/sparc61891.2024.10829064

Konda, O., Mohammad, R., Mishra, S., Rajeev, N., & Verma, A. (2024). Harvesting Insights: Leveraging Explainable AI to Optimize Farming Practices. In International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET), Indore, India (pp. 1-8). Acropolis Institute of Technology and Research. https://doi.org/10.1109/acroset62108.2024.10743799

Linheiro, E. S. M., Shinde, G. R., Mahalle, P. N., & Mirajka, R. (2023). Explainable AI (XAI) for Agriculture. In P. N. Mahalle, G. R. Shinde, & P. M. Joshi (Eds.), Industry 4.0 Convergence with AI, IoT, Big Data and Cloud Computing: Fundamentals, Challenges and Applications IoT and Big Data Analytics (pp. 161-176). Bentham Books. https://doi.org/10.2174/9789815179187123040014

Martin, J., Mittal, R., Malik, V., Jeribi, F., Siddiqui, S. T., Hossain, M. A., & Swapna, S. L. (2024). XAI-Powered Smart Agriculture Framework for Enhancing Food Productivity and Sustainability. IEEE Access, 12, 168412 – 168427, https://doi.org/10.1109/access.2024.3492973

Mohan, R. N. V. J., Rayanoothala, P. S., & Sree, R. P. (2025). Next-gen agriculture: integrating AI and XAI for precision crop yield predictions. Frontiers in Plant Science, 15, 1-16. https://doi.org/10.3389/fpls.2024.1451607

Ngo, Q.H., Kechadi, T., Le-Khac, NA. (2022). OAK4XAI: Model Towards Out-of-Box eXplainable Artificial Intelligence for Digital Agriculture. In M. Bramer, & F. Stahl, (Eds), Artificial Intelligence XXXIX. SGAI-AI 2022. Lecture Notes in Computer Science(), vol 13652 (pp. 238-251). Springer, Cham. https://doi.org/10.1007/978-3-031-21441-7_17

Porfírio, R. P. da C., Madeira, R. N., & Santos, P. A. (2024). AgriUXE: Integrating Explainable AI and Multimodal Data for Smart Agriculture. In International Symposium on Sensing and Instrumentation in 5G and IoT Era (ISSI) (pp. 1–6). IEEE. https://doi.org/10.1109/issi63632.2024.10720487

Turgut, O., Kök, İ., & Özdemir, S. (2024). AgroXAI: Explainable AI-driven crop recommendation system for agriculture 4.0. In IEEE International Conference on Big Data (BigData), (pp. 7208-7217). Washington, DC, USA. https://doi.org/10.48550/arxiv.2412.16196

Vale, D., El-Sharif, A., & Ali, M. (2022). Explainable artificial intelligence (XAI) post-hoc explainability methods: Risks and limitations in non-discrimination law. AI and Ethics, 2(4), 815-826. https://doi.org/10.1007/s43681-022-00142-y