IoT-based multi-sensor data fusion for freshwater ecosystem monitoring: a case study of Lake Tana, Ethiopia

This paper investigated an efficient real-time data collection mechanism for Lake Tana using sensor fusion and the Internet of Things (IoT). The rapid proliferation of invasive aquatic weeds in freshwater ecosystems necessitates robust long-term monitoring and efficient data acquisition techniques. Smart IoT-based sensor networks enable real-time acquisition of key aquatic parameters, such as pH, total nitrogen, total phosphorus, and chlorophyll-a. This study presented an IoT-based sensor fusion framework for improving the accuracy and reliability of environmental monitoring. Sensor fusion algorithms, such as weighted, Kalman, extended Kalman, unscented Kalman, Bayesian, and Particle filter, are used to enhance the precision of the collected data. The experimental dataset consisted of 192 sensor observations collected over three months using multiple sensors deployed in Lake Tana. Experimental results demonstrated that the unscented Kalman sensor fusion significantly enhanced measurement accuracy and stability, achieving 81.46%, 84.10%, and 93.72% improvements over the no-fusion approach in reducing variance for TP, TN, and Chl-a, respectively. WF and PF achieved a 96.24% improvement in pH. These findings demonstrated that the sensor fusion approach effectively reduces measurement uncertainty and provides more reliable water parameter estimates, making it a promising solution for real-time IoT-enabled environmental monitoring applications.