Exploiting the full potential of Bayesian networks in predictive ecology

Although ecological models used to make predictions from underlying covariates have a record of success, they also suffer from limitations. They are typically unable to make predictions when the value of one or more covariates is missing during the testing. Missing values can be estimated but methods are often unreliable and can result in poor accuracy. Similarly, missing values during the training can hinder parameter estimation of many ecological models. Bayesian networks can handle these and other limiting issues, such as having highly correlated covariates. However, they are rarely used to their full potential. Indeed, Bayesian networks are commonly used to evaluate the knowledge of experts by constructing the network manually and often (incorrectly) interpreting the resulting network causally. We provide an approach to learn a Bayesian network fully from observed data, without relying on experts and show how to appropriately interpret the resulting network, both to identify how the variables (covariates and target) are interrelated and to answer probabilistic queries. We apply this method to the case study of a mountain pine beetle infestation and find that the trained Bayesian network has a predictive accuracy of 0.88 AUC. We classify the covariates as primary and secondary in terms of contributing to the prediction and show that the predictive accuracy does not deteriorate when the secondary covariates are missing and degrades to only 0.76 when one of the primary covariates is missing. As a complement to the previous work on constructing Bayesian networks by hand, we show that if instead, both the structure and parameters are learned only from data, we can achieve more accurate predictions as well as generate new insights about the underlying processes.

Automated summary

The limitations of ecological models and the potential of Bayesian networks are discussed in this study. A new method is proposed to learn and interpret Bayesian networks fully from observed data. Through a case study, it is found that using this method can lead to more accurate predictions and insights into the relationships between covariates.