A Bayesian network approach to knowledge integration and representation of farm irrigation: 2. Model validation

Abstract

For models to be useful, they need to adequately describe the systems they represent. he probabilistic nature of Bayesian network models has traditionally meant that model alidation is difficult. In this paper we present a process to validate Inteca-Farm, a ayesian network model of farm irrigation that we described in the first paper of this series. We assessed three aspects of the quality of model predictions, namely, bias, accuracy, and skill, for the two variables for which validation data are available directly or indirectly. We also examined model predictions for any systematic errors. The validation results show that the bias and accuracy of the two validated variables are within accep..