A Study of Explainable AI In Smart Agriculture

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Artificial Intelligence is changing agriculture by helping farmers decide what to plant, when to water, and how to identify sick crops before they spread disease throughout a field.However, most AI systems work like "black boxes" they give answers without explaining how they arrived at them.For a farmer who relies on one harvest, a recommendation without a reason is hard to trust.This paper explores Explainable Artificial Intelligence (XAI) as the key to connecting powerful AI models with the people who need to act on their advice.We look at how techniques like SHAP, LIME, Grad-CAM, and attention mechanisms make complex AI predictions easier to understand for farmers.We also review how these methods are used in crop monitoring, disease detection, soil analysis, irrigation planning, and predicting yields.The paper compares traditional AI with XAI, and includes a case study on detecting diseases in tomato and apple leaves.This case study shows how a visual heat map can turn a simple label like "diseased" into a clear reason like "diseased because of the brown lesions on the leaf edges."The paper ends with a discussion on how XAI affects farmer trust and adoption, the challenges of using it in rural India, and the future of making agriculture both smart and easy to understand.