A prototype Bayesian belief network for the diagnosis of acidification in Welsh rivers

摘要

The paper describes the development of a prototype Bayesian Belief Network (BBN) that models acidification in Welsh Rivers. It was based on data from the 102 river sites surveyed in the 1995 Welsh Acid Waters Survey. The objectives of the study were: a) to test the suitability of BBNs for the diagnosis of river health; and b) to test the viability of a data-based approach to the development of a prototype. The results of performance tests on the model, based upon its ability to predict pH, aluminium concentration and trout density using macroinvertebrate data, are compared to those achieved by three multiple linear regression (MLR) models. The results of like-for-like tests on the MLR models and three simple BBNs are also presented. The results of like-for-like tests on the MLR models and three simple BBNs are also presented. Following a discussion of the results, it is concluded that: a) BBNs are well suited to the task of diagnosis, because they model the causal relationships of the system in a non-linear way and offer flexibility of use; b) their potential can only be fully realised if sufficient data are available for the reliable evaluation of their conditional probabilities; and c) the data-based approach to prototype development was efficient and effective.