Methods of Neuro-Simulation for Field Development

This paper introduces a methodology for optimizing field development schemes. The use of numerical simulation models in establishing field development strategies is a widely practiced approach. In field development studies, a large number of scenarios which result in a time consuming and expensive process must be considered. The objective of this paper is to structure the field development schemes using artificial neural networks (ANNs) in conjunction with numerical reservoir simulation; a process we call neuro-simulation. In neuro-simulation, a few field development scenarios are examined using a numerical simulator. The results of these studies are then used to train the ANN. The trained ANN is used as a predictive tool for field development purposes. Using neuro-simulation, the number of numerical simulations is significantly reduced. The use of the neuro-simulation approach becomes practical especially during the early life of the field when the recovery data and the field properties are sparse and sporadic. The neuro-simulation approach provides the flexibility of considering any location as a potential site in contrast to the conventional simulation approach when the well locations are restricted to the predefined block centers. The neuro-simulation approach is faster and more efficient than its conventional counterpart. The results obtained from neuro-simulation compare well with the results obtained from a reservoir simulator.