Construction and application of Bayesian networks in flood decision supporting system

Abstract

A Bayesian network is a graphical model that encodes probabilistic relationships among variables of interest. Bayesian networks are based on probability theory. We describe the principle of Bayesian probability and Bayesian networks. The automated creation of Bayesian networks can be separated into two tasks, structure learning, which consists of creating the structure of the Bayesian networks from the collected data, and parameter learning, which consists of calculating the numerical parameters for a given structure. We focus on the structure-learning problem of a flood decision supporting system. The algorithm WILD is used to discretize the continuous attributes in the flood database. The Bayesian network in the flood decision supporting system is obtained by K2. Explanations of the model are given. We describe an important process in exploiting decision supporting systems using Bayesian networks. It is shown that the model is correct and the Bayesian network is a good approach in a flood decision supporting system.