Enhancing Digital Agriculture with XAI: Case Studies on Tabular Data and Future Directions

Given the pivotal role of agriculture in ensuring food security, fostering economic stability, and addressing environmental sustainability, the sector has increasingly embraced smart farming solutions to respond to recent climate and societal challenges, such as rising water and food demands. These solutions provide actionable insights crucial for decision-making, enabling farm stakeholders to optimize resources, improve yields, and mitigate risks. However, the complexity of the predictive models often associated with this type of solutions results in a lack of transparency, hindering trust and adoption. To respond to such challenges, this paper explores the application of explainable AI (XAI) techniques to agriculture tabular data. Specifically, we focus on two case studies: wheat yield prediction and grapes produced for wine purposes yield prediction. Through these case studies, we propose initial contributions on how XAI techniques can be applied in the context of agriculture and how generated explanations can be adapted to the users' level of expertise. Finally, as part of ongoing and future research directions, we introduce AgriUXE (Agricultural eXperience Enhanced through eXplainability), a novel user-centered digital platform designed to augment the explainability of multimodal data and machine learning model predictions for sustainable smart farming solutions. By providing transparent, data-driven decisions and generating user-adaptive explanations, AgriUXE aims to support the optimization of the user experience within these solutions.