This introductory course focuses on petroleum data types—such as field data, laboratory data, and simulated data—and the modern data analytics tools available for working with these datasets.

Over two days, participants will explore artificial intelligence (AI) algorithms that have been successfully applied to a wide range of petroleum engineering challenges. The course introduces machine learning models and their hybridization with fuzzy logic techniques, as well as selected information theory methods that can support engineering analysis, reservoir characterization, and decision-making processes.

The program provides a broad yet sufficiently detailed introduction to petroleum data analytics, placing analytical tools in the context of the types of data routinely encountered in petroleum engineering. Topics include AI algorithms such as evolutionary programming and swarm intelligence; machine learning techniques including various neural networks and Support Vector Machines (SVM); an introduction to fuzzy logic and its integration with machine learning; and information theory approaches such as the Akaike Information Criterion (AIC).

All methods are presented from a conceptual standpoint and illustrated with practical examples drawn from the petroleum exploration and production (E&P) industry.