MACHINE LEARNING IN AGRICULTURE: A FARMER-CENTERED DECISION SUPPORT MODEL BASED ON EXPLAINABLE AI (XAI).

• Grant number: 25/02843-2
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: June 15, 2025
• End date: September 14, 2025
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Lucas Gabriel Zanon
• Grantee: Elvio José Sêneda Filho
• Supervisor: Francesco Marcelloni
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: Università di Pisa, Italy
• Associated to the scholarship: 24/03042-0 - Performance Management in Agtechs: a predictive approach based on machine learning and grey system theory, BP.MS

Abstract

Increasing food demand and pressure for more efficient and sustainable food systems have led to the Smart Farming concept, which encompasses use of technologies such as Machine Learning approaches and Internet of Things in agriculture. Nevertheless, application of Machine Learning algorithms may lack explainability and interpretability, leading to challenges in understanding models functioning and communicating results to non-specialist decision-makers. In this scenario, Explainable Artificial Intelligence (XAI) aims to make Artificial Intelligence models (such as Machine Learning ones) both more interpretable and understandable. This project aims to incorporate XAI techniques to the candidate's MSc. research, enhancing explainability of the proposed ML model and building a farmer-centered decision support model. This research is classified as quantitative, axiomatic and normative and has the following expected results: a literature review, a computational implementation and an illustrative application of XAI techniques for decision-making in agriculture. The main contributions may be for both academics and practitioners: advancements in XAI applications in agriculture; a practical-oriented approach based on a partnership with an Agtech company; strengthening the results of the MSc. project linked to this research; and, finally, consolidating international partnerships.