Abstract: Building sustainable smart water delivery systems is facing considerable obstacles globally due to the increasing rise of modern cities. Water quality has a variety of effects on how we live our daily lives. Traditional efforts to control urban water quality were mostly focused on conducting routine inspections of quality indicators from the physical, chemical, and biological groups. However, the unavoidable delay for biological indicators has elevated the risk to your health. In this article, we start by looking at the concerns and conducting research. Then, we provide a solution by developing a methodology for risk analysis for the urban water supply system. Indicators are required to identify threats and track changes in the quality of the water. We recommend employing an adaptive frequency analysis (Adp-FA) technique to resolve the data using the indicators' frequency domain for their internal linkages and forecasts. We also investigate how well this strategy scales across indicator, geographic, and temporal domains. For the application, we selected data sets of industrial quality from four different Norwegian urban water supply systems: Oslo, Bergen, Strommen, and Aalesund. We examine the spectrogram, rate the timeliness and precision of the predictions, and compare it to traditional ANN and Random Forest methods. The results show that our method works better in most instances. It is possible to support early alerts for concerns to industrial water quality.
|
DOI:
10.17148/IJARCCE.2022.11775
