IoT-Enabled ML Framework for Efficient Biofloc Monitoring in Aquaculture

The study suggests a hybrid machine learning (ML) and Internet of Things (IoT) methodology for effective bio floc monitoring in sustainable aquaculture. Aquaculture's sustainability is hampered by issues with conventional methods, such as manual water quality monitoring, regular sensor calibration, and a slow reaction to anomalies in water quality. By integrating IoT sensors for real-time data collection with ML algorithms for prediction, the proposed approach overcomes these limitations and becomes more automated, precise, and resource-efficient. It shows risk assessment, resource optimization, and real-time monitoring of water quality metrics. The results demonstrate notable gains over traditional systems, with accuracy, precision, and recall levels of 92%, 91%, and 94%, respectively. Additionally, the proposed method reduces the frequency of interventions and resource consumption while increasing forecast accuracy to 90%. It provides an improved, more sustainable, and scalable aquaculture technology that enhances water quality and boosts production.