Multi-sensor Acquisition, Data Fusion, Criteria Mining and Alarm Triggering for Decision Support in Urban Water Infrastructure Systems

Frequent adjustment of the drinking water treatment process as a simultaneous response to climate variations, and the impact those variations have on water quality, has been a grand challenge in water resource management in recent years. An early warning system with the aid of satellite remote sensing and local sensor networks, which provides timely and quantitative knowledge to monitor the quality of water, may be a soluition to this challenge. The development of such an early warning system is addressed to discover and evaluate the severity in a discrete event mode in this paper. The early warning system in the current study is able to empower the urban water ifrastructure systems with the integration of advanced data science, environmental monitoring, computational intelligence, and satellite remote sensing data. By developing a graphical user interface, end-users who do not have knowledge or skill in the field of integrated sensing, monitoring, networking, modeling can take advantage of the user-friendly early warning system. Practical implementation of the proposed early warning system was assessed at the largest resrvoir, Lake Mead, in Las Vegas in the United States. It uniquely demonstrates how such a system can benefit the drinking water treatment plant throughout decision support actions via multi-sensor acquisition, data fusion, criteria mining and alarm trigerring.