Mining monitored data for decision-making with a Bayesian network model

A Bayesian network model of Anabaena blooms in Grahamstown Dam, near Newcastle, Australia is described. This model meets the criteria of being decision-focused, data driven, transparent, and capable of being used by non-expert modellers. red data were arranged in a consistently formatted database from which the model could ‘learn’ probabilistic relationships between model elements such as pumped nutrient load, lake water column nutrient concentrations, and Anabaena concentrations. This ‘minimal model’ produced useful insights into ecosystem relationships and provided a basic model for later development. uent modelling and elicitation of conditional probabilities from experts strengthened components of the model for which there is little data available. The approach to incorporating elicited data is described and some simple scenario testing is also presented. ment outcomes resulting from application of the model are presented.