Leaf-Based Plant Disease Detection and Explainable AI

TL;DR

This survey addresses plant leaf disease detection and the role of explainable AI in agriculture, focusing on the Indian context. It catalogs common leaf diseases, major datasets, and a spectrum of methods from conventional ML to CNNs and Vision Transformers, highlighting performance trends. It also discusses XAI approaches (SHAP, LIME, Grad-CAM, InterpretML) and their application to plant-disease classification to improve transparency. The paper outlines future directions, including disease-stage identification, multi-disease detection, and disease quantification, arguing that explainability is essential for practical adoption by farmers and policymakers.

Abstract

The agricultural sector plays an essential role in the economic growth of a country. Specifically, in an Indian context, it is the critical source of livelihood for millions of people living in rural areas. Plant Disease is one of the significant factors affecting the agricultural sector. Plants get infected with diseases for various reasons, including synthetic fertilizers, archaic practices, environmental conditions, etc., which impact the farm yield and subsequently hinder the economy. To address this issue, researchers have explored many applications based on AI and Machine Learning techniques to detect plant diseases. This research survey provides a comprehensive understanding of common plant leaf diseases, evaluates traditional and deep learning techniques for disease detection, and summarizes available datasets. It also explores Explainable AI (XAI) to enhance the interpretability of deep learning models' decisions for end-users. By consolidating this knowledge, the survey offers valuable insights to researchers, practitioners, and stakeholders in the agricultural sector, fostering the development of efficient and transparent solutions for combating plant diseases and promoting sustainable agricultural practices.

Figures (5)

• Figure 2: Learning Performance vs. Explainability
• Figure 3: Black-Box incorporated into the workflow.
• Figure 4: Explainable AI incorporated into the workflow.
• Figure 5: Taxonomy of Interpretability.
• Figure 6: Depicting XAI solution for leaf-based plant disease detection.