A MACHINE LEARNING APPROACH FOR EARLY DETECTION OF FISH DISEASES BY ANALYSING WATER QUALITY

Abstract

Aquaculture plays a vital role in global food production, but fish diseases pose a significant threat to productivity and sustainability. Early detection of fish diseases is crucial to prevent large-scale losses and ensure healthy aquatic ecosystems. This project proposes a machine learning-based system that analyzes water quality parameters to predict and detect fish diseases at an early stage. The system collects real-time data such as pH, temperature, dissolved oxygen, ammonia, and turbidity using sensors. Machine learning models including Random Forest, Support Vector Machine, and Neural Networks are employed to analyze patterns and identify anomalies associated with disease outbreaks. By correlating water quality variations with fish health conditions, the system provides timely alerts and actionable insights to fish farmers. The proposed approach enhances disease prediction accuracy, reduces manual monitoring efforts, and promotes sustainable aquaculture practices.