Building Bayesian Networks from Basin Modeling scenarios for Decision Making under geologic uncertainty

Basin and Petroleum Systems Modeling is important for understanding the geological mechanisms that characterize reservoir units. Bayesian Networks are useful for decision making in geological prospect analysis and exploration. We unify these two methodologies in this paper. The probabilistic description of the Bayesian Network is trained by using multiple scenarios of Basin and Petroleum Systems Modeling. A range of different input parameters are used for total organic content, heat flow, porosity, and faulting, to span a full categorical design for the Basin and Petroleum Systems Modeling scenarios. Given the consistent Bayesian Network for trap, reservoir and source attributes, we demonstrate important decision making applications such as evidence propagation and the value of information.