INTELLIGENT TEA DISEASE DETECTION USING ARTIFICIAL INTELLIGENCE: TRENDS, INNOVATIONS, AND PERSPECTIVES

Tea (Camellia sinensis) is one of the most economically significant crops worldwide, supporting millions of livelihoods and contributing substantially to agricultural economies, particularly in countries such as India, China, Sri Lanka, and Kenya. However, tea production is severely affected by various diseases including anthracnose, gray blight, red rust, brown blight, etc. which significantly reduce yield and quality. Traditional disease detection methods rely on manual inspection, which is time-consuming, subjective, and inefficient for large plantations. Recent advancements in Machine Learning (ML) and Artificial Intelligence (AI), particularly deep learning techniques, have enabled automated, accurate, and real-time tea disease classification systems using image analysis.This chapter presents a comprehensive overview of ML and AI-based tea disease classification methods, including traditional machine learning techniques, deep learning models such as Convolutional Neural Networks (CNNs), transfer learning, object detection models such as YOLO, and emerging transformer-based architectures. Recent advancements such as hybrid CNN-Transformer models, attention mechanisms, explainable AI, and lightweight edge-based models are discussed. The chapter also covers dataset preparation, feature extraction, model training, evaluation metrics, challenges, and future research directions. The integration of AI into tea disease detection represents a transformative step toward precision agriculture, enabling early detection, improved crop management, and enhanced productivity.