Precise environmental control is essential to optimize plant growth and resource efficiency in hydroponic cultivation. This study presents a smart Internet of things framework for hydroponic lettuce (Lactuca sativa L.) cultivation that integrates real-time monitoring, adaptive nutrient management, and multi-modal image-based health analysis. The architecture incorporates context-aware sensor fusion, multi-objective energy-cost optimization, a self-adaptive decision engine, and integrated vision analytics. A 14-day experimental cycle evaluated growth rates, leaf quality, nutrient accuracy, water efficiency, and energy consumption. The system achieved a growth rate of 1.8 cm/day, 97% nutrient delivery accuracy, and 92% water efficiency, while reducing overall energy usage by 20% compared to conventional automated systems. An ablation study confirmed that predictive and adaptive controls are vital to maintaining crop health and maximizing productivity. These findings validate the proposed framework as a highly scalable and reliable automation solution that enhances resource sustainability and yield consistency in controlled-environment agriculture.
A 2026 study studied this question.