This study presents the development of an integrated intelligent system designed to enhance monitoring, prediction, and decision-making in the Sri Lankan tea industry. The system addresses key challenges across both plantation and factory operations, where traditional processes rely on manual observation and experience, leading to inefficiencies, delayed issue detection, and inconsistent outcomes. The proposed system integrates tea yield prediction and tracking, tea leaf disease detection with advisory support, environmental condition monitoring with predictive analysis, and belt condition monitoring in tea processing machines. IoT devices are used for real-time data collection, while machine learning and deep learning models are applied to generate predictions, classifications, and alerts. A centralised backend system and mobile application support real-time monitoring and decision-making. The results demonstrate improved monitoring accuracy, early issue detection, enhanced operational efficiency, and proactive data-driven management within tea production and processing environments.
Kuruppu et al. (Fri,) studied this question.