There are two schools of thought on the application of Artificial Intelligence (AI) techniques in reservoir characterization and modeling. The first school considers AI as a step forward in the future of reservoir characterization and modeling in line with the increased advancement in technology. The other school argues that AI techniques are "black boxes" with vague architectures, whose concepts do not follow fundamental petroleum engineering principles.
This paper presents AI as a "white box", highlighting its basic concepts, revealing the architectural composition of some of its techniques, and showcasing examples of its successful applications in various reservoir characterization and modeling tasks. AI techniques are used in the prediction of oil and gas reservoir properties such as porosity, permeability, water saturation, well-bore stability and identification of lithofacies. The recent developments in the hybridization and "ensemblage" of some AI techniques are also discussed.
The outcome of this paper will provide a better understanding of the basic concepts of AI and offer a strong background for further study of AI techniques. Overall, it will provide an appraisal of the successful applications of AI in petroleum engineering and increase the necessary synergy required for a multi-disciplinary collaboration among petroleum engineers, computer scientists and mathematicians; and to ensure the delivery of the future AI-driven/AI-assisted reservoir models for better exploration, production and management of petroleum resources.