Field development planning using reservoir models is a key step in the field development process. Numerical optimization of specific field development strategies is often used to aid planning, and Bayesian Optimization is a popular optimization method that has been applied in the past.

This article proposes a Bayesian Optimization workflow comprising a Stochastic Bayes Linear proxy model and a combination of experimental and sequential design techniques.  The workflow is demonstrated by optimizing several field development strategies in a synthetic North Sea reservoir model.  The performance and practical implications of the approach are important in designing an accurate and computationally efficient optimization workflow under geological uncertainty, and ultimately are factors in developing decision support tools for field development.