AI-POWERED PLANT HEALTH ASSESSMENT: AUTOMATED CLASSIFICATION FOR ENHANCED CROP MONITORING AND PRODUCTIVITY

Abstract

Plant disease classification plays a vital role in advancing modern agriculture, transitioning from 
traditional manual diagnosis to intelligent, automated systems powered by machine learning. 
Historically, identification of plant diseases relied on visual inspections, expert advice, and lab tests—
 methods that were accurate for small-scale use but often subjective, slow, and inconsistent. These 
limitations resulted in delayed treatment and substantial crop losses, highlighting the inefficiency and 
high cost of conventional approaches, especially at scale. To address this, the proposed system 
introduces an innovative machine learning-based solution capable of accurately classifying plant 
diseases using sparse and categorical IoT data. It incorporates comprehensive data preprocessing 
techniques, including handling missing values, label encoding, and class imbalance correction using 
the Synthetic Minority Oversampling Technique (SMOTE), ensuring a high-quality dataset for model 
training. The classification pipeline integrates multiple models—Gaussian Naive Bayes, Support 
Vector Machines, K-Nearest Neighbors, and a novel Decision Tree Classifier. Among these, the 
Decision Tree model demonstrated superior performance, achieving an accuracy of 99.07% with 
precision, recall, and F1-scores consistently exceeding 98%, confirming its robustness and reliability. 
This research is significant in offering real-time, data-driven diagnostics that enable early disease 
detection and precise pesticide recommendations. It not only improves crop yield and reduces 
financial losses but also promotes environmentally sustainable agriculture by limiting excessive 
chemical usage. By overcoming the limitations of traditional methods—such as subjectivity, delay, 
and lack of scalability—this system presents a transformative approach to plant disease management 
through advanced machine learning, marking a pivotal shift toward precision agriculture.