Leaf-Based Plant Disease Detection and Explainable AI

AI can help solve real agricultural problems affecting livelihoods: The paper emphasizes that plant disease detection using AI and machine learning has practical applications for millions of rural farmers in India whose economic survival depends on crop yields, demonstrating how responsible AI development can address genuine societal needs beyond developed markets.

Explainability is essential for farmer adoption: The research highlights that Explainable AI (XAI) is necessary to make deep learning models' disease detection decisions interpretable to end-users (farmers and agricultural practitioners), suggesting that AI systems must be transparent and understandable—not just accurate—to be responsibly deployed in real-world agricultural contexts.

Multiple approaches exist for disease detection: The survey evaluates both traditional machine learning techniques and deep learning methods for identifying plant diseases from leaf images, indicating that responsible AI implementation should consider multiple technical approaches rather than defaulting to the most complex solutions.

Data availability matters for responsible deployment: By summarizing available datasets for plant disease detection, the paper acknowledges that responsible AI development requires adequate, quality training data—a foundational requirement often overlooked when deploying AI systems in resource-limited agricultural settings.

Sustainable practices require transparent solutions: The research frames disease detection AI as part of promoting "sustainable agricultural practices," suggesting that responsible AI in agriculture must balance technological innovation with environmental and economic sustainability goals for farming communities.