Methodology for Bayesian Belief Network Development to Facilitate Compliance with Water Quality Regulations

Abstract

Limited resources and drinking water quality requirements pose significant challenges to those managing small and rural drinking water distribution systems (WDSs). Real-time monitoring technologies could support regulatory compliance, if shortcomings such as false readings and data corruption could be overcome. Bayesian Belief Networks (BBNs) are proposed as a means to mitigate technological shortcomings and increase certainty about the state of a given WDS. This paper describes a methodology for the development of BBNs that integrates known system characteristics with real-time monitoring technologies to support the water quality compliance of small or rural WDSs. Expert judgement was used both in the development of the structure of the BBN and in quantifying the required probability relationships. The results of a case study application of this methodology suggest that it is useful in developing a BBN to support decision making for a WDS with limited use of realtime monitoring technology.

A fuzzy Bayesian belief network for safety assessment of oil and gas pipelines

“…BBNs have proven to be effective for capturing and integrating qualitative and quantitative information from various sources, and they thus have the ability to strengthen decisions when empirical data are lacking (Joseph, Adams, & McCabe, 2010;Lampis & Andrews, 2009). BBNs provide both predictive and diagnostic capabilities and allow for updating the probability distributions with new evidence when such become available (Kabir et al, 2015).…”

“…The conditional probabilities shown in Figure 3 which will be used in Equation (3), can be obtained through expert knowledge elicitation (Joseph et al, 2010), or training from data (Cooper & Herskovits, 1992). Where multiple experts are considered, credibility of each decision-maker on the decision can be elicited by considering experience and confidence on the assessment (Kiremidjian, 1985;Tesfamariam et al, 2010).…”

“…Sensitivity analysis assumes that input parameters to the model are uncertain; it shows the designer the variation of the system reliability, given some variation of the input parameters' values (Joseph et al, 2010;Leu & Chang, 2013). It refers to how sensitive the performance of a model is to minor changes in the input parameters.…”

Seismic risk analysis using Bayesian belief networks

“…7.1, which will be used in Equations 7.1 and 7.2, can be obtained through expert knowledge elicitation (Katsis et al 2008;Joseph et al 2010), or training from data (Cooper and Herskovits 1992;Bouckaert et al 2011). Where multiple experts are considered, credibility of each decision maker on the decision can be elicited by considering experience and confi dence on the assessment (Kiremidjian 1985;.…”

Activity-Based Data Fusion for Automated Progress Tracking of Construction Projects

“…As different technologies are being employed in construction projects, an enormous amount of data is being collected automatically or semiautomatically, with a resultant strong demand for a reliable data management system. This situation is not unique to construction projects, because other sectors of the civil engineering domain, such as water distribution networks, are also equipped with a variety of sensors and data acquisition systems that generate a wide variety of data for the support of data fusion and real-time decision making (Joseph, Adams, & McCabe, 2010). A number of data management systems have been proposed for use in the civil engineering domain as a means of dealing with the exponentially growing amount of research data.…”