Federated Learning for Smart and Sustainable Aquaponics: A Decentralized AI Approach for Urban Resilience

Abstract

The majority of machine learning models rely on centralized methods, which require large data transfers to central repositories. Federated learning, a decentralized machine learning approach, offers a solution by enabling local computations and aggregating local models to build a global model. While federated learning has been applied in some agricultural domains, its use in aquaponics remains unexplored. Aquaponics, a sustainable agricultural method combining fish farming and soil-less plant production, presents unique opportunities for federated learning applications, particularly in urban farming environments. By using edge-based federated learning, we improve scalability, data privacy, and sustainability and also, reduce data transmission needs in smart urban agriculture. This research, a collaboration between research teams from three countries, highlights how federated learning and deep learning can enhance environmental monitoring and sustainability in urban resilience strategies, particularly in smart agriculture. The Flower framework was used to implement federated learning, and ResNet-18 was employed for fish disease detection. This paper introduces novel contributions in federated learning and deep learning techniques for the management of aquaponics systems, highlighting the potential of these technologies to optimize aquaponics systems' efficiency.