An IoT-Enabled Intelligent Biofloc Monitoring Framework for Aquaculture with Machine Learning

The increasing demand for efficient and sustainable aquaculture has been driving the application of Biofloc technology that promotes water quality and fish well-being. Nonetheless, manual checks of water parameters are challenging to achieve because they consume time and are prone to human errors. The current research presents an IoT-enabled smart Biofloc monitoring system with integration in machine learning for enhanced real-time water quality management in fish rearing. IoT sensors monitor the important parameters of ammonia, carbon monoxide, total dissolved solids, turbidity, temperature, and humidity, sending data through Arduino UNO and ESP8266 to a cloud platform. Machine learning models process data to forecast trends and identify anomalies, allowing for proactive decision-making. A mobile/web application provides real-time monitoring, alerts, and automated control over aeration and feeding. This system minimizes human intervention, cuts fish mortality, and maximizes resource use, which ensures a cost-effective, scalable, and sustainable method for Biofloc-based aquaculture.