Skip to Main Content
Skip Nav Destination
GEOREF RECORD

Stochastic representation and conditioning of process-based geological model by deep generative and recognition networks

S. W. Cheung, A. Kushwaha, H. Sun and X. H. Wu
Stochastic representation and conditioning of process-based geological model by deep generative and recognition networks
Petroleum Geoscience (February 2024) PRE-ISSUE PUBLICATION

Abstract

Accurate and realistic geological modeling is the core of oil and gas development and production. In recent years, process-based methods are developed to produce highly realistic geological models by simulating the physical processes that reproduce the sedimentary events and develop the geometry. However, the complex dynamic processes are extremely expensive to simulate, making process-based models difficult to be conditioned to field data. In this work, we propose a comprehensive generative adversarial network framework as a machine-learning-assisted approach for mimicking the outputs of process-based geological models with fast generation. The main objective of our work is to obtain a continuous parametrization of the highly realistic process-based geological models which enables us to calibrate the models and condition the models to data. Numerical results are presented to illustrate the capability of our proposed methodology.


ISSN: 1354-0793
EISSN: 2041-496X
Serial Title: Petroleum Geoscience
Serial Volume: PRE-ISSUE PUBLICATION
Title: Stochastic representation and conditioning of process-based geological model by deep generative and recognition networks
Affiliation: Lawrence Livermore National Laboratory, Center for Applied Scientific Computing, Livermore, CA, United States
Pages: article petgeo2022-032
Published: 20240226
Text Language: English
Publisher: Geological Society Publishing House for EAGE (European Association of Geoscientists & Engineers), London, United Kingdom
References: 48
Accession Number: 2024-023773
Categories: Economic geology, geology of energy sources
Document Type: Serial
Bibliographic Level: Analytic
Illustration Description: illus. incl. 1 table
Secondary Affiliation: SambaNova Systems, USA, United StatesExxonMobil Upstream Research Company, USA, United States
Country of Publication: United Kingdom
Secondary Affiliation: GeoRef, Copyright 2024, American Geosciences Institute. Reference includes data from GeoScienceWorld, Alexandria, VA, United States. Reference includes data from The Geological Society, London, London, United Kingdom
Update Code: 202414
Close Modal

or Create an Account

Close Modal
Close Modal