International Journal of Aquaculture, 2026, Vol.16, No.5, 378-396 http://www.aquapublisher.com/index.php/ija 385 verification of product safety and environmental compliance (Premkkumar et al., 2023). Blockchain-based smart contracts can also support secure sharing of health and management data among stakeholders in disease early-warning networks. Integrated AI-IoT platforms can combine real-time sensing, disease classification, and time series prediction, enabling operators to receive automated recommendations and alerts through web or mobile terminals, while historical logs support auditing and optimization of management strategies (Katta et al., 2025; Rohini et al., 2026). For ecological pond aquaculture, production process traceability can enhance product credibility and market competitiveness, and also provide data support for regulatory authorities to carry out quality and safety supervision, tailwater discharge management, and green aquaculture evaluation. 4 Analysis of the Application Effects of Digital Monitoring in Ecological Pond Aquaculture 4.1 Improving water quality regulation efficiency The primary application effect of digital monitoring in ecological pond aquaculture is reflected in the improvement of water quality regulation efficiency. Pond water environments have obvious dynamic characteristics, and indicators such as dissolved oxygen, water temperature, pH, ammonia nitrogen, nitrite, and turbidity are affected by multiple factors, including weather changes, feeding intensity, stocking density, algal growth, and sediment conditions. Traditional management mainly relies on manual pond inspection and regular testing, which often only capture water quality conditions at a specific point in time and cannot promptly reflect changing trends in the water environment. Through the coordinated application of multi-parameter sensors, microcontrollers, and wireless communication technologies, digital monitoring systems can continuously collect and display key indicators such as temperature, pH, dissolved oxygen, and turbidity in real time, thereby providing a data basis for rapid corrective actions (Chen et al., 2022). Compared with traditional manual testing, calibrated low-cost sensors can significantly improve the reliability of real-time monitoring; in some systems, after linear regression correction, the accuracy can reach 76%-97%, with relative errors below 4% (Jais et al., 2024). In specific management processes, digital monitoring can transform water quality data into intuitive trend charts and alarm information, helping aquaculture operators judge the direction and degree of pond environmental changes. For example, when dissolved oxygen continues to decline, the system can remind operators to start aeration equipment in time; when ammonia nitrogen or nitrite increases, operators can take measures such as water exchange, sediment improvement, feeding reduction, or the application of microbial preparations according to actual conditions; when pH fluctuates greatly, operators can also make comprehensive judgments by considering algal community changes and weather conditions. Monitoring architectures based on fuzzy logic and artificial intelligence can further integrate multi-source data and automatically control aerators, water pumps, and other equipment to maintain suitable dissolved oxygen and salinity levels during continuous operation and rapidly correct water quality deviations. As a result, water quality regulation no longer relies entirely on empirical judgment, but is instead based on continuous data, real-time feedback, and equipment linkage, making management measures more targeted and timely. The improvement of water quality regulation efficiency is also reflected in enhanced preventive management capacity. Digital monitoring can not only detect existing abnormalities, but also identify potential risks through the accumulation of continuous data. For example, low dissolved oxygen in the early morning during high-temperature seasons, weakened photosynthesis in rainy weather, and increased water load after excessive feeding can all be reflected in data changes in advance. Predictive and intelligent control further enhances this preventive capacity. IoT-machine learning-quantum optimization frameworks can predict water quality dynamics with relatively high accuracy and support a large number of targeted interventions, keeping fish survival rates above 90% in tropical ponds (Huang and Khabusi, 2025). Relevant reviews also show that continuous monitoring combined with automatic aeration, dosing, or water exchange can rapidly detect and mitigate abnormalities in dissolved oxygen, pH, and total ammonia nitrogen, reduce environmental risks, and stabilize aquaculture conditions (Figure 2) (Flores-Iwasaki et al., 2025). Therefore, digital monitoring helps ecological pond aquaculture shift from post-event treatment to pre-event prevention, thereby improving the stability of the entire aquaculture system.
RkJQdWJsaXNoZXIy MjQ4ODYzNA==