Enhancing Hydroponics Efficiency Using Iot-Based Automated Monitoring And Sustainable Crop Production System

Abstract

The increasing demand for sustainable agricultural practices, coupled with the challenges of limited arable land and water resources, has driven the need for more efficient and innovative farming systems. One of the main challenges in enhancing hydroponics efficiency with IoT-based systems is the high initial cost of setting up advanced sensor networks and automation technologies. The objective of this study is to develop and evaluate an IoT-based automated monitoring system to optimize hydroponics efficiency, enhance crop yield, and reduce resource waste. Environmental and nutrient parameters such as pH, temperature, humidity, and light intensity were continuously collected using sensor networks. Pre-processing, including data cleaning and Gray-Level Co-occurrence Matrix (GLCM) analysis, enabled accurate detection of subtle environmental changes impacting crop health. Growth optimization was achieved using a hybrid Poplar Optimization Algorithm–Smart Flower Optimization Algorithm (POA-SFOA), allowing precise control over water, nutrients, and light inputs. The Multiplex Adaptive Modality Fusion Graph Attention Network (MAMFGAT) was applied to analyze sensor data interdependencies, enabling smart, adaptive decision-making. This system supports sustainable agriculture by maximizing yield, minimizing resource use, and automating operations for long-term efficiency. The result shows that the proposed system increases crop yield by about 25-30% as compared to 10-15% for the semi-automated and baseline yield for the traditional methods, implemented using Python software. Future work can explore integrating AI-driven predictive analytics for early stress detection and yield forecasting in hydroponic systems.