SMART AQUAPONIC SYSTEM USING FUZZY LOGIC AND CONVOLUTIONAL NEURAL NETWORK (CNN)

Aquaponics is an innovative and sustainable farming method that combines aquaculture (fish farming) and hydroponics (soilless plant cultivation) in a symbiotic environment. While aquaponics offers significant advantages, such as reduced water usage and efficient nutrient recycling, it faces challenges, including the need for precise monitoring, early disease detection, and optimal resource management. Traditional systems often lack real-time data analysis and predictive capabilities, leading to inefficiencies, crop losses, and increased operational risks. To address these limitations, this study introduces a smart aquaponic system that integrates fuzzy logic, convolutional neural networks (CNNs), and IoT technologies to enhance yield and resource management. The proposed system employs sensor-based monitoring to collect real-time data on critical parameters such as water quality, temperature, pH levels, and nutrient concentrations. A fuzzy logic model evaluates the health of fish and plants using predefined rules, effectively managing uncertainties in biological systems. Additionally, a CNN-based plant disease detection module achieves exceptional performance, with a precision of 93%, recall of 91%, and an accuracy of 92%, enabling early identification and mitigation of diseases. The system is accessible via a mobile application, providing farmers with user-friendly tools for remote monitoring and management. By enhancing real-time monitoring, predictive analytics, and disease detection, this research supports global sustainability goals, offering a scalable solution for modernizing aquaponics and advancing food security.