Real-time monitoring and predictive maintenance for sustainable aquaculture management

Abstract

The objective of this study is to investigate water quality monitoring in aquaculture systems using integrated sensors and predictive maintenance technologies, aiming to enhance production efficiency and reduce environmental impact. This research is focusing on remote sensing, on-site sensor monitoring, and machine learning for time-series forecasting, anomaly detection, and fault classification. Artificial Intelligence (AI), as a field of computer science that aims to simulate and reproduce intelligent human functions, plays a pivotal role in this approach. While AI [1] is increasingly adopted in public institutions in Romania to improve governance processes, its application in aquaculture brings significant improvements in system automation, decision support, and predictive capabilities. The frameworks developed by the Blue-GreenWay and iPREMAS projects provide a robust foundation for understanding aquaculture water quality management. The methodology integrates remote sensing data and in-situ water quality sensors to continuously monitor critical parameters such as temperature, dissolved oxygen, and chlorophyll-a concentration. A predictive maintenance platform employing machine learning algorithms was implemented, with data collected in a case study at the Ovidius Aqua Line sturgeon farm. The combined system effectively detected changes in water quality, providing timely alerts and enabling proactive maintenance scheduling. These results highlight improved operational efficiency, optimized feed management, and a reduced risk of disease outbreaks, in line with the established theoretical framework. Additionally, the integration of these technologies allowed for more precise water resource management, ensuring long-term sustainability Findings offer valuable insights for sustainable aquaculture management and environmental protection, emphasizing practical applications in facility management and future water quality forecasting. Our results demonstrate the potential of combining the technologies developed in the Blue-GreenWay and iPREMAS projects for effective water quality monitoring in aquaculture systems, contributing to the sustainable management of water resources in aquatic resources.