Real-Time Water Quality Monitoring Using Autonomous Underwater Vehicles with Embedded AI

The work in this research is under the area of AUVs, which are specialized unmanned surface vessels with fixed or rotating propellers to implement real-time water quality monitoring systems with AI. The extended procedures of monitoring water quality that is using point samples collected at specific intervals and then analyzed at laboratories are sometimes insufficient to reflect changes in water quality in real-time. In response to this, the study examines the feasibility of utilizing AUVs to enable volumetric, repetitive surveillance of temperature, pH, turbidity, dissolved oxygen, and pollutants’ concentrations. The use of AI in AUVs help in the real time processing of information gathered by the AUVs improving the quality of water analysis. Thus, the data from the sensors is used to implement machine learning techniques including detection of anomalies, identification of trends and modeling the future conditions of water. It is also relevant to augment the capability of monitor based systems in terms of making them respond to problems that may exist in difficult, or risky, territories. Sampling entails gathering data from different aquatic settings and analyzing the data with artificial intelligence algorithms inserted in the AUVs. The tests shown by the results reveal that AUVs are accurate in measuring water quality parameters, and the use of AI provides appropriate results of conditions different from the norm. For this purpose, a comparative analysis of AI models such as Neural Networks, Random Forests and Support Vector Machines is conducted to highlight the efficiency of complex data analysis methods.