Adaptive Approach to Petroleum Reservoir Simulation

This book presents unique features of the adaptive modeling approach based on new machine learning algorithms for petroleum exploration, development, and production. The adaptive approach helps simulation engineers and geoscientists to create adequate geological and hydrodynamic models. This approach is proven to be a real alternative to traditional techniques, such as deterministic modeling. Currently, machine-learning algorithms grow in popularity because they provide consistency, predictiveness, and convenience. The primary purpose of this book is to describe the theoretical state of the adaptive approach and show some examples of its implementation in simulation and forecasting different reservoir processes.

Supports reservoir engineers to create adequate geological and hydrodynamic models Presents some novel mechanisms of artificial intelligence applied to petroleum exploration, development and production Describes simulation and forecasting petroleum reservoir processes

Autorentext

Stanislav Ursegov was born in Ukhta, Komi Republic, Russia in 1975. He graduated from the Ukhta State Technical University as a mining engineer degree in Petroleum Reservoir Development and Production in 1999 and defended his PhD in Petroleum Engineering in 2007. Stanislav is dedicated and results-driven research scientist and reservoir engineer with almost twenty years of robust experience in one of the world's largest oil and gas companies - LUKOIL (in the PechorNIPIneft Branch of the LUKOIL-Engineering Ltd.), in addition to the world-renown scientific research and educational center - Skolkovo Institute of Science and Technology in Moscow. His main areas of expertise are resource assessment & characterization, field development planning, thermal and chemical enhanced oil recovery, deterministic and adaptive geological and hydrodynamic modeling. Stanislav is an author of more than thirty peer review journal articles and eight patents. In 2014, he received the Academician I.M. Gubkin Award.

Armen Zakharian is of Armenian descent, although he was born in the Krasnoyarsk region of Siberia in Russia in 1951. In 1977, he graduated from the Moscow Petroleum University named after I.M. Gubkin with a mining engineer degree in Geology and Exploration of Oil and Gas Fields, and, in 1985, he defended his PhD in Petroleum Geology at the Moscow State University named after M.V.Lomonosov. He worked as a field geologist for fourteen years in Yakutia, Far East, and Ukraine. Then, in 1996, he started programming and mathematical modeling of petroleum reservoir development processes. He created three applied software systems ArmGeologist, Delphor, and Cervart, which are successfully used in different petroleum companies and institutions such as LUKOIL, TNK-BP (now it is a part of Rosneft) and others. His main scientific interests is computer forecasting. He is an author of more than ten peer review journal articles. Armen got married and has two daughters.

Klappentext

This book presents unique features of the adaptive modeling approach based on new machine learning algorithms for petroleum exploration, development, and production. The adaptive approach helps simulation engineers and geoscientists to create adequate geological and hydrodynamic models. This approach is proven to be a real alternative to traditional techniques, such as deterministic modeling. Currently, machine-learning algorithms grow in popularity because they provide consistency, predictiveness, and convenience. The primary purpose of this book is to describe the theoretical state of the adaptive approach and show some examples of its implementation in simulation and forecasting different reservoir processes.

Inhalt
Introduction.- Value of information for reservoir simulation.- Contrasts between adaptive and deterministic models.- Alternatives for mathematical apparatus of adaptive simulation - neural networks and fuzzy logic.- Adaptive geological modeling.- Adaptive hydrodynamic modeling.- Adaptive forecasting.- Adaptive software system Cervart.- Conclusion.