Optimizing Nutrient Formulations Through Artificial Intelligence Model to Reduce Excessive Fertigation in Lettuce Grown in Hydroponic Systems

Optimizing nutrient uptake is critical for maximizing productivity in hydroponically cultivated plants. In hydroponic systems, where soil is absent, essential nutrients must be precisely delivered through the water solution to support plant growth. Despite the widespread use of conventional nutrient formulations, limited research has focused on dynamically optimizing nutrient concentrations based on plant-specific needs at different growth stages. This study addresses the gap by leveraging Artificial Neural Networks (ANNs) to develop an intelligent nutrient management system for hydroponic lettuce cultivation. A novel approach was implemented to optimize nitrogen (N), phosphorus (P), and potassium (K) concentrations by utilizing real-time data collected through Ion-Selective Electrodes (ISE) sensors and the PlantEye platform. These datasets were used to train ANN models capable of predicting optimal NPK levels on a weekly basis, minimizing nutrient waste while maintaining high crop productivity. The results demonstrate that the AI-driven approach can reduce nutrient usage by up to 40% without compromising plant growth and yield when compared to traditional formulations. This preliminary study presents a significant advancement in sustainable hydroponic farming by introducing an adaptive, data-driven fertigation strategy. The findings have broad implications for precision agriculture, enabling resource-efficient nutrient management while reducing environmental impact. By integrating AI-based optimization, this study paves the way for more cost-effective, scalable, and environmentally sustainable hydroponic production systems.