Vague Set–Driven Decision Support System for Early Warning of Water Quality Deterioration in Aquaculture

India, the world’s second-largest fish producer, relies heavily on aquaculture, which supports millions livelihoods. Sustaining this sector requires effective pond management, particularly the regulation of key water quality parameters—temperature, pH, dissolved oxygen, ammonia, hydrogen sulfide, hardness, alkalinity, TDS, and turbidity that directly influence fish growth, immunity, and survival. These parameters frequently deteriorate due to organic load accumulation and sudden temperature fluctuations, often going unnoticed by small and marginal farmers until losses become severe. This study proposes a vague set–driven decision support system to provide early warnings of water quality degradation in aquaculture ponds. The model incorporates truth and falsity membership functions to capture uncertainties associated with multiple physico-chemical parameters and their interdependencies (e.g., temperature–DO, pH–ammonia, hardness–alkalinity). Using optimal parameter thresholds from coldwater, warm-water and brackish systems aquaculture standards, the system computes a Vague Water Quality Risk Index (VWQRI) and generates interval-based alerts (Normal, Caution & Critical). Results indicate that vague-set modeling enhances interpretability and reduces false alarms under uncertain or overlapping conditions, offering a robust and adaptable tool for preventive pond management and sustainable aquaculture production.