Information Gathering in Bayesian Networks

The optimal design of data acquisition is not obvious in Bayesian Network models. The dependency structure may vary dramatically, which makes learning and information evaluation complicated and sometimes non-intuitive. Our application, and the motivation for working on this topic, is prospect selection for petroleum exploration in the North Sea. Here, the data gathering is often carried out during seasonal campaigns, and it is useful to plan the experimentation and to understand which data are likely to be most informative. We use information measures to compare possible future observation sets. Four information measures are studied: Shannon Entropy, sum of Variances, Node-wise Entropy and overall Prediction Error. The Shannon Entropy is commonly considered the standard measure of information, and the Node-wise Entropy measure can be interpreted as an approximation to the former. The Variance measure links uncertainty and variance. The Prediction Error measure is tied to decision making rules. The results lead to new insight about prospect selection. For example, the Node-wise Entropy and the Variance measure behaves similarly, and the optimal observation set of Shannon Entropy does not correspond to what we intuitively would consider as minimizing unknown information in this case.