Towards Smart Agriculture: An Explainable Machine Learning–Based Decision Support System for Early Detection of Plant Leaf Diseases

Plant leaf diseases represent one of the most significant threats to agricultural productivity, food security, and farmer livelihoods worldwide. While machine learning (ML) and deep learning (DL) models have demonstrated high accuracy in plant disease classification, their real-world adoption remains limited due to lack of transparency, poor interpretability, and insufficient decision-oriented outputs. This study proposes an innovative and exploratory explainable machine learning–based decision support system (XAI-DSS) for early detection of plant leaf diseases. The proposed framework integrates intelligent disease prediction with explainable artificial intelligence mechanisms to provide transparent, trustworthy, and farmer-centric recommendations. The article presents a comprehensive system architecture, analytical evaluation, comparative discussion, and future research directions. By bridging the gap between predictive performance and interpretability, the proposed approach contributes toward sustainable, smart, and responsible agricultural intelligence.