<![CDATA[Freshwater aquaculture requires continuous water quality monitoring because rapid changes in temperature, pH, dissolved oxygen, turbidity, total dissolved solids, and water level can affect fish health and pond productivity. This study evaluates a multimodal sensor system for real-time fish pond water quality monitoring and dashboard-based actuator control. The system integrates six sensors with Arduino Mega for signal acquisition, ESP32 for Wi-Fi communication, Firebase for cloud data storage and command exchange, and a Flutter dashboard for visualization and manual control. Field testing was conducted in two tilapia ponds with different initial conditions. Sensor performance was evaluated by comparing five measurable parameters with reference instruments using percentage error, accuracy, mean absolute error, and root mean square error, while turbidity was assessed through functional contrast testing and short-term stability because a turbidity reference instrument was unavailable. The average accuracy of the five validated parameters was 87.37% in pond 1 and 95.58% in pond 2. Temperature and water level showed the highest accuracy, above 98% in both ponds. Dissolved oxygen and total dissolved solids showed larger deviations, especially in pond 1, indicating sensitivity to field conditions and calibration stability. Actuator commands for the aerator and circulation pumps responded within 1-2 seconds under stable network conditions. The results show that the system is useful as a preliminary field-validated monitoring and semi-automatic control platform, but further work is required for long-term drift testing, turbidity validation using a commercial meter, and automatic control evaluation.]]>
