A Smart Aquaculture Monitoring System with Automated Fish Disease Identification

Aquaculture plays a crucial role in meeting the growing global demand for seafood. However, chal-lenges such as disease outbreaks can significantly impact production. Moreover, the chance of disease outbreaks is increased by the low-quality water parameters. The proposed system aims to address these challenges by machine learning for effective monitoring and disease detection. This system integrates realtime data from various sensors to monitor critical environmental parameters such as water quality, temperature, and pH levels. We utilize machine learning to detect diseases. To train and categorize the diseases, a Convolutional Neural Network classification algorithm is used. Early detection of diseases improves the chances of successful intervention, reducing economic losses. By providing early detection and immediate alerts to operators, it minimizes the risk of disease outbreaks and ensures timely interventions. This not only improves the overall health and welfare of farmed fish but also optimizes resource utilization and reduces labor costs, contributing to the long-term success of aquaculture endeavors while meeting the global demand for high-quality seafood.