Data Perception Quality Risk Analysis for Long-Term Smart Water Supply

Abstract

The rapid growth of modern cities around the world has created significant obstacles to the
building of sustainable smart water supply systems. The standard of the water we drink is
becoming increasingly important in shaping the way cities are run. The physical, chemical,
and biological groupings of quality indicators have traditionally been the primary emphasis
of urban water quality control. However, due to the inherent lag for biological signs, the
health risk has escalated, leading to incidents like widespread infections in numerous major
cities. We begin this work by defining the issue at hand and discussing its technical
obstacles and open research concerns. We then propose a remedy by developing a risk
analysis framework for the municipal water system. We put the suggested method through
its paces by putting it through a battery of tests against both traditional Artificial Neural
Networks and Random Forests, looking at how well each performs and how much time
each takes. The outcomes demonstrate that our approach outperforms competing methods
in the vast majority of cases. It is possible to provide early warnings and additional decision
support for risks associated with water quality in the industrial sector.